http://wiki.math.uwaterloo.ca/statwiki/api.php?action=feedcontributions&user=J244yang&feedformat=atomstatwiki - User contributions [US]2022-05-28T02:38:05ZUser contributionsMediaWiki 1.28.3http://wiki.math.uwaterloo.ca/statwiki/index.php?title=Surround_Vehicle_Motion_Prediction&diff=49761Surround Vehicle Motion Prediction2020-12-07T05:55:13Z<p>J244yang: /* Prediction performance analysis and application to motion planning */</p>
<hr />
<div>DROCC: '''Surround Vehicle Motion Prediction Using LSTM-RNN for Motion Planning of Autonomous Vehicles at Multi-Lane Turn Intersections'''<br />
== Presented by == <br />
Mushi Wang, Siyuan Qiu, Yan Yu<br />
<br />
== Introduction ==<br />
<br />
This paper presents a surrounding vehicle motion prediction algorithm for multi-lane turn intersections using a Long Short-Term Memory-based (LSTM) Recurrent Neural Network (RNN). More specifically, it focused on the improvement of in-lane target recognition and achieving human-like acceleration decisions at multi-lane turn intersections by introducing the learning-based target motion predictor and prediction-based motion predictor. A data-driven approach to predict the trajectory and velocity of surrounding vehicles on urban roads at multi-lane turn intersections was described. LSTM architecture, a specific kind of RNN capable of learning long-term dependencies, is designed to manage complex vehicle motions in multi-lane turn intersections. The results show that the forecaster improves the recognition time of the leading vehicle and contributes to the improvement of prediction ability.<br />
<br />
== Previous Work ==<br />
The autonomous vehicle trajectory approaches previously used motion models like Constant Velocity and Constant Acceleration. These models are linear and are only able to handle straight motions. There are curvilinear models such as Constant Turn Rate and Velocity and Constant Turn Rate and Acceleration which handle rotations and more complex motions. Together with these models, Kalman Filter is used to predicting the vehicle trajectory. Kalman filtering is a common technique used in sensor fusion for state estimation that allows the vehicle's state to be predicted while taking into account the uncertainty associated with inputs and measurements. However, the performance of the Kalman Filter in predicting multi-step problems is not that good. Recurrent Neural Network performs significantly better than it. <br />
<br />
There are 3 main challenges to achieving fully autonomous driving on urban roads, which are scene awareness, inferring other drivers’ intentions, and predicting their future motions. Researchers are developing prediction algorithms that can simulate a driver’s intuition to improve safety when autonomous vehicles and human drivers drive together. To predict driver behavior on an urban road, there are 3 categories for the motion prediction model: (1) physics-based; (2) maneuver-based; and (3) interaction-aware. Physics-based models are simple and direct, which only consider the states of prediction vehicles kinematically. The advantage is that it has minimal computational burden among the three types. However, it is impossible to consider the interactions between vehicles. Maneuver-based models consider the driver’s intention and classified them. By predicting the driver maneuver, the future trajectory can be predicted. Identifying similar behaviors in driving is able to infer different drivers' intentions which are stated to improve the prediction accuracy. However, it still an assistant to improve physics-based models. <br />
<br />
Recurrent Neural Network (RNN) is a type of approach proposed to infer driver intention in this paper. Interaction-aware models can reflect interactions between surrounding vehicles, and predict future motions of detected vehicles simultaneously as a scene. While the prediction algorithm is more complex in computation which is often used in offline simulations. As Schulz et al. indicate, interaction models are very difficult to create as "predicting complete trajectories at once is challenging, as one needs to account for multiple hypotheses and long-term interactions between multiple agents" [6].<br />
<br />
== Motivation == <br />
Research results indicate that little research has been dedicated on predicting the trajectory of intersections. Research regarding intersections have previously concentrated only on maneuver-level predictions of activities such as crossing, stopping or making turns. Trajectory level prediction has also been mainly focused on structured environments that enforce classifiable behavior but has not been extensively researched in multi-lane turn intersections. This is important since different drivers have varied driving behaviors as they travel through intersections. <br />
Moreover, public data sets for analyzing driver behavior at intersections are not enough, and these data sets are not easy to collect. A model is needed to predict the various movements of the target around a multi-lane turning intersection. It is very necessary to design a motion predictor that can be used for real-time traffic.<br />
<br />
<center><br />
[[ File:intersection.png |300px]]<br />
</center><br />
<br />
== Framework == <br />
The LSTM-RNN-based motion predictor comprises three parts: (1) a data encoder; (2) an LSTM-based RNN; and (3) a data decoder depicts the architecture of the surrounding target trajectory predictor. The proposed architecture uses a perception algorithm to estimate the state of surrounding vehicles, which relies on six scanners. The output predicts the state of the surrounding vehicles and is used to determine the expected longitudinal acceleration in the actual traffic at the intersection. The following image gives a visual representation of the model.<br />
<br />
<center>[[Image:Figure1_Yan.png|800px|]]</center><br />
<br />
== LSTM-RNN based motion predictor == <br />
<br />
=== Sensor Outputs ===<br />
<br />
The input of the target perceptions is from the output of the sensors. The data collected in this article uses 6 different sensors with feature fusion to detect traffic in the range up to 100m: 1) LiDAR system outputs: Relative position, heading, velocity, and box size in local coordinates; 2) Around-View Monitoring (AVM) and 3)GPS outputs: acquire lanes, road marker, global position; 4) Gateway engine outputs: precise global position in urban road environment; 5) Micro-Autobox II and 6) a MDPS are used to control and actuate the subject. All data are stored in an industrial PC.<br />
<br />
=== Data ===<br />
Multi-lane turn intersections are the target roads in this paper. The dataset was collected using a human driven Autonomous Vehicle(AV) that was equipped with sensors to track motion the vehicle's surroundings. In addition, the motion sensors they used a front camera, Around-View-Monitor and GPS to acquire the lanes, road markers and global position. The data was collected in the urban roads of Gwanak-gu, Seoul, South Korea. The training model is generated from 484 tracks collected when driving through intersections in real traffic. The previous and subsequent states of a vehicle at a particular time can be extracted. After post-processing, the collected data, a total of 16,660 data samples were generated, including 11,662 training data samples, and 4,998 evaluation data samples.<br />
<br />
=== Motion predictor ===<br />
This article proposes a data-driven method to predict the future movement of surrounding vehicles based on their previous movement, which is the sequential previous motion. The motion predictor based on the LSTM-RNN architecture in this work only uses information collected from sensors on autonomous vehicles, as shown in the figure below. The contribution of the network architecture of this study is that the future state of the target vehicle is used as the input feature for predicting the field of view. <br />
<br />
<br />
<center>[[Image:Figure7b_Yan.png|500px|]]</center><br />
<br />
<br />
==== Network architecture ==== <br />
A RNN is an artificial neural network that is suitable for use with sequential data because it has recurrent connections on its hidden nodes and thus, can retain its state or memory while processing the next input or sequence of inputs. For this reason, RNNs can be used to analyze time-series data where the pattern of the data depends on the time flow. This is an impossible task for traditional artificial neural networks, which assume the inputs are independent of one another. RNNs can also contain feedback loops that allow activations to flow alternately in the loop. <br />
<br />
In line with traditional neural networks, RNNs still suffer from the problem of vanishing gradients. An LSTM avoids this by making errors flow backward without a limit on the number of virtual layers. This property prevents errors from increasing or declining over time, which can make the network train improperly. The figure below shows the various layers of the LSTM-RNN and the number of units in each layer. This structure is determined by comparing the accuracy of 72 RNNs, which consist of a combination of four input sets and 18 network configurations.<br />
<br />
<center>[[Image:Figure8_Yan.png|800px|]]</center><br />
<br />
==== Input and output features ==== <br />
In order to apply the motion predictor to the AV in motion, the speed of the data collection vehicle is added to the input sequence. The input sequence consists of relative X/Y position, relative heading angle, speed of surrounding target vehicles, and speed of data collection vehicles. The output sequence is the same as the input sequence, such as relative position, heading, and speed.<br />
<br />
==== Encoder and decoder ==== <br />
In this study, the authors introduced an encoder and decoder that process the input from the sensor and the output from the RNN, respectively. The encoder normalizes each component of the input data to rescale the data to mean 0 and standard deviation 1, while the decoder denormalizes the output data to use the same parameters as in the encoder to scale it back to the actual unit. <br />
==== Sequence length ==== <br />
The sequence length of RNN input and output is another important factor to improve prediction performance. In this study, 5, 10, 15, 20, 25, and 30 steps of 100 millisecond sampling times were compared, and 15 steps showed relatively accurate results, even among candidates The observation time is very short.<br />
<br />
== Motion planning based on surrounding vehicle motion prediction == <br />
In daily driving, experienced drivers will predict possible risks based on observations of surrounding vehicles, and ensure safety by changing behaviors before the risks occur. In order to achieve a human-like motion plan, based on the model predictive control (MPC) method, a prediction-based motion planner for autonomous vehicles is designed, which takes into account the driver’s future behavior. The cost function of the motion planner is determined as follows:<br />
\begin{equation*}<br />
\begin{split}<br />
J = & \sum_{k=1}^{N_p} (x(k|t) - x_{ref}(k|t)^T) Q(x(k|t) - x_{ref}(k|t)) +\\<br />
& R \sum_{k=0}^{N_p-1} u(k|t)^2 + R_{\Delta \mu}\sum_{k=0}^{N_p-2} (u(k+1|t) - u(k|t))^2 <br />
\end{split}<br />
\end{equation*}<br />
where <math>k</math> and <math>t</math> are the prediction step index and time index, respectively; <math>x(k|t)</math> and <math>x_{ref} (k|t)</math> are the states and reference of the MPC problem, respectively; <math>x(k|t)</math> is composed of travel distance px and longitudinal velocity vx; <math>x_{ref} (k|t)</math> consists of reference travel distance <math>p_{x,ref}</math> and reference longitudinal velocity <math>v_{x,ref}</math> ; <math>u(k|t)</math> is the control input, which is the longitudinal acceleration command; <math>N_p</math> is the prediction horizon; and Q, R, and <math>R_{\Delta \mu}</math> are the weight matrices for states, input, and input derivative, respectively, and these weight matrices were tuned to obtain control inputs from the proposed controller that were as similar as possible to those of human-driven vehicles. The weight matrices were used for the controller, for the proposed and conventional motion predictors. The dynamic constraints for the controller were defined as follors <br />
$$\begin{bmatrix} p_{x}(k+1|t)\\ v_{x}(k+1|t)\end{bmatrix} = \begin{bmatrix}1 & dt \\0 &1-dt/\tau \end{bmatrix}\begin{bmatrix} p_{x}(k|t)\\ v_{x}(k|t)\end{bmatrix} + \begin{bmatrix} 0 & dt/\tau\end{bmatrix}u(k|t) $$<br />
The constraints of the control input are defined as follows:<br />
\begin{equation*}<br />
\begin{split}<br />
&\mu_{min} \leq \mu(k|t) \leq \mu_{max} \\<br />
&||\mu(k+1|t) - \mu(k|t)|| \leq S<br />
\end{split}<br />
\end{equation*}<br />
Where <math>u_{min}</math>, <math>u_{max}</math>and S are the minimum/maximum control input and maximum slew rate of input respectively.<br />
<br />
Determine the position and speed boundary based on the predicted state:<br />
\begin{equation*}<br />
\begin{split}<br />
& p_{x,max}(k|t) = p_{x,tar}(k|t) - c_{des}(k|t) \quad p_{x,min}(k|t) = 0 \\<br />
& v_{x,max}(k|t) = min(v_{x,ret}(k|t), v_{x,limit}) \quad v_{x,min}(k|t) = 0<br />
\end{split}<br />
\end{equation*}<br />
Where <math>v_{x, limit}</math> are the speed limits of the target vehicle.<br />
<br />
== Prediction performance analysis and application to motion planning ==<br />
=== Accuracy analysis ===<br />
The proposed algorithm was compared with the results from three base algorithms, a path-following model with <br />
constant velocity, a path-following model with traffic flow and a CTRV model.<br />
<br />
We compare those algorithms according to four sorts of errors, The <math>x</math> position error <math>e_{x,T_p}</math>, <br />
<math>y</math> position error <math>e_{y,T_p}</math>, heading error <math>e_{\theta,T_p}</math>, and velocity error <math>e_{v,T_p}</math> where <math>T_p</math> denotes time <math>p</math>. These four errors are defined as follows:<br />
<br />
\begin{equation*}<br />
\begin{split}<br />
e_{x,Tp}=& p_{x,Tp} -\hat {p}_{x,Tp}\\ <br />
e_{y,Tp}=& p_{y,Tp} -\hat {p}_{y,Tp}\\ <br />
e_{\theta,Tp}=& \theta _{Tp} -\hat {\theta }_{Tp}\\ <br />
e_{v,Tp}=& v_{Tp} -\hat {v}_{Tp}<br />
\end{split}<br />
\end{equation*}<br />
<center>[[Image:Figure10.1_YanYu.png|500px|]]</center><br />
<br />
The proposed model shows significantly fewer prediction errors compare to the based algorithms in terms of mean, <br />
standard deviation(STD), and root mean square error(RMSE). Meanwhile, the proposed model exhibits a bell-shaped <br />
curve with a close to zero mean, which indicates that the proposed algorithm's prediction of human divers' <br />
intensions are relatively precise. On the other hand, <math>e_{x,T_p}</math>, <math>e_{y,T_p}</math>, <math>e_{v,T_p}</math> are bounded within <br />
reasonable levels. For instant, the three-sigma range of <math>e_{y,T_p}</math> is within the width of a lane. Therefore, <br />
the proposed algorithm can be precise and maintain safety simultaneously.<br />
<br />
=== Motion planning application ===<br />
==== Case study of a multi-lane left turn scenario ====<br />
The proposed method mimics a human driver better, by simulating a human driver's decision-making process. <br />
In a multi-lane left turn scenario, the proposed algorithm correctly predicted the trajectory of a target vehicle, even when the target vehicle was not following the intersection guideline.<br />
<br />
==== Statistical analysis of motion planning application results ====<br />
The data is analyzed from two perspectives, the time to recognize the in-lane target and the similarity to <br />
human driver commands. In most of cases, the proposed algorithm detects the in-line target no late than based <br />
algorithm. In addition, the proposed algorithm only recognized cases later than the base algorithm did when <br />
the surrounding target vehicles first appeared beyond the sensors’ region of interest boundaries. This means <br />
that these cases took place sufficiently beyond the safety distance, and had little influence on determining <br />
the behaviour of the subject vehicle.<br />
<br />
<center>[[Image:Figure11_YanYu.png|500px|]]</center><br />
<br />
In order to compare the similarities between the results from the proposed algorithm and human driving decisions, <br />
this article introduced another type of error, acceleration error <math>a_{x, error} = a_{x, human} - a_{x, cmd}</math>. where <math>a_{x, human}</math><br />
and <math>a_{x, cmd}</math> are the human drivers' acceleration history and the command from the proposed algorithm, <br />
respectively. The proposed algorithm showed more similar results to human drivers’ decisions than the base <br />
algorithm. <math>91.97\%</math> of the acceleration error lies in the region <math>\pm 1 m/s^2</math>. Moreover, the base algorithm <br />
possesses a limited ability to respond to different in-lane target behaviours in traffic flow. Hence, the proposed <br />
model is efficient and safe.<br />
<br />
== Conclusion ==<br />
A surrounding vehicle motion predictor based on an LSTM-RNN at multi-lane turn intersections was developed and its application in an autonomous vehicle was evaluated. The model was trained by using the data captured on the urban road in Seoul in MPC. The evaluation results showed precise prediction accuracy and so the algorithm is safe to be applied on an autonomous vehicle. Also, the comparison with the other three base algorithms (CV/Path, V_flow/Path, and CTRV) revealed the superiority of the proposed algorithm. The evaluation results showed precise prediction accuracy. In addition, the time-to-recognize in-lane targets within the intersection improved significantly over the performance of the base algorithms. The proposed algorithm was compared with human driving data, and it showed similar longitudinal acceleration. The motion predictor can be applied to path planners when AVs travel in unconstructed environments, such as multi-lane turn intersections.<br />
<br />
== Future works ==<br />
This paper has identified several venues for future research, which include:<br />
<br />
1.Developing trajectory prediction algorithms using other machine learning algorithms, such as attention-aware neural networks.<br />
<br />
2.Applying the machine learning-based approach to infer lane change intention at motorways and main roads of urban environments.<br />
<br />
3.Extending the target road of the trajectory predictor, such as roundabouts or uncontrolled intersections, to infer yield intention.<br />
<br />
4.Learning the behavior of surrounding vehicles in real time while automated vehicles drive with real traffic.<br />
<br />
== Critiques ==<br />
The literature review is not sufficient. It should focus more on LSTM, RNN, and the study in different types of roads. Why the LSTM-RNN is used, and the background of the method is not stated clearly. There is a lack of concept so that it is difficult to distinguish between LSTM-RNN based motion predictor and motion planning.<br />
<br />
This is an interesting topic to discuss. This is a major topic for some famous vehicle companies such as Tesla, which now already has a good service called Autopilot to give self-driving and Motion Prediction. This summary can include more diagrams in architecture in the model to give readers a whole view of how the model looks like. Since it is using LSTM-RNN, include some pictures of the LSTM-RNN will be great. I think it will be interesting to discuss more applications by using this method, such as Airplane, boats.<br />
<br />
Autonomous driving is a very hot topic, and training the model with LSTM-RNN is also a meaningful topic to discuss. By the way, it would be an interesting approach to compare the performance of different algorithms or some other traditional motion planning algorithms like KF.<br />
<br />
There are some papers that discussed the accuracy of different models in vehicle predictions, such as Deep Kinematic Models for Kinematically Feasible Vehicle Trajectory Predictions[https://arxiv.org/pdf/1908.00219.pdf.] The LSTM didn't show good performance. They increased the accuracy by combing LSTM with an unconstrained model(UM) by adding an additional LSTM layer of size 128 that is used to recursively output positions instead of simultaneously outputting positions for all horizons.<br />
<br />
It may be better to provide the results of experiments to support the efficiency of LSTM-RNN, talk about the prediction of training and test sets, and compared it with other autonomous driving systems that exist in the world.<br />
<br />
The topic of surround vehicle motion prediction is analogous to the topic of autonomous vehicles. An example of an application of these frameworks would be the transportation services industry. Many companies, such as Lyft and Uber, have started testing their own commercial autonomous vehicles.<br />
<br />
It would be really helpful if some visualization or data summary can be provided to understand the content, such as the track of the car movement.<br />
<br />
The model should have been tested in other regions besides just Seoul, as driving behaviors can vary drastically from region to region.<br />
<br />
Understandably, a supervised learning problem should be evaluated on some test dataset. However, supervised learning techniques are inherently ill-suited for general planning problems. The test dataset was obtained from human driving data which is known to be extremely noisy as well as unpredictable when it comes to motion planning. It would be crucial to determine the successes of this paper based on the state-of-the-art reinforcement learning techniques.<br />
<br />
It would be better if the authors compared their method against other SOTA methods. Also one of the reasons motion planning is done using interpretable methods rather than black boxes (such as this model) is because it is hard to see where things go wrong and fix problems with the black box when they occur - this is something the authors should have also discussed.<br />
<br />
A future area of study is to combine other source of information such as signals from Lidar or car side cameras to make a better prediction model.<br />
<br />
It might be interesting and helpful to conduct some training and testing under different weather/environmental conditions, as it could provide more generalization to real-life driving scenarios. For example, foggy weather and evening (low light) conditions might affect the performance of sensors, and rainy weather might require a longer braking distance.<br />
<br />
This paper proposes an interesting, novel model prediction algorithm, using LSTM_RNN. However, since motion prediction in autonomous driving has great real-life impacts, I do believe that the evaluations of the algorithm should be more thorough. For example, more traditional motion planning algorithms such as multi-modal estimation and Kalman filters should be used as benchmarks. Moreover, the experiment results are based on Korean driving conditions only. Eastern and Western drivers can have very different driving patterns, so that should be addressed in the discussion section of the paper as well.<br />
<br />
The paper mentions that in the future, this research plans to learn the real life behaviour of automated vehicles. Seeing a possible improvement in road safety due to this research will be very interesting.<br />
<br />
This predictor is also possible to be applied in the traffic control system.<br />
<br />
This prediction model should consider various conditions that could happen in an intersection. However, normal prediction may not work when there is a traffic jam or in some crowded time periods like rush hours.<br />
<br />
It would be better that the author could provide more comparison between the LSTN-RNN algorithm and other traditional algorithm such as RNN or just LSTM.<br />
<br />
The paper has really good results for what they aimed to achieve. However for the future work it would also be nice to have various climates/weathers to be included in the Seoul dataset. I think it's also important to consider it as different climates/weather (such as snowy roads, or rain) would introduce more noisier data (camera's image processing) and the human drivers behaviour would change as well to adapt to the new environment.<br />
<br />
It would be good to have a future work section to discusses shortage of current algorithms and the possible improvement.<br />
<br />
The summary explains the whole process well, but is missing the small details among the steps. It would be better to explain concepts such as RNN, modelling procedure for first time users.<br />
<br />
This paper presents a nice method, but does not seem particularly well developed. I would have liked to see some more ablations on this particular choice of RNN, as there are more efficient variants such as GRU which show similar performance in other tasks while being more amenable to real-time inference. Furthermore, the multi-model aspect seems slightly ad-hoc, it would have been nice to see a more rigorous formulation similar to seen in some recent work by Zeng et al. from Uber ATG: https://arxiv.org/pdf/2008.06041.pdf.<br />
<br />
The data used for this paper contains driver information exclusively to the urban roads of Gwanak-gu Seoul, hence the data may contain an inherited bias as drivers around the rest of the country, let alone the rest of the world, will have different habits based on different environments. It would be interesting to see if this model can be applied to other cities around the world and exhibit similar results or would there be a need to tune it based off geographic location.<br />
<br />
Since the data is based on urban roads, It would be better to include the details on performance of the model on high traffic area vs low traffic urban area. It would also be interesting to see the performance of the model with many pedestrians.<br />
<br />
While it would be nice to read more on why the authors chose LSTM-RNN, the paper exhibits a potential way to improve autonomous vehicle performance. It would be interesting to see how an army of robots would behave when this paper's method is applied in robotics, since robots' motions also follow a trajectory.<br />
<br />
An interesting topic, but the paper and accompanying summary are missing some details that would improve understandability. With respect to the background of the topic, a more detailed explanation of trajectories in the case of driving would help to better motivate the research. The addition of benchmarks and comparisons to current industry standards (if they are published publicly) would help to contextualize the results of the LSTM-RNN. An area of further study is applying these techniques to different weather situations and driving patterns in different countries. How does this model perform in regions where driver's very loosely follow the laws of the road? Further, could the research be generalized for controlled and uncontrolled turn lanes, especially on roads with higher speed limits?<br />
<br />
In the past, LSTM is a very popular model in natural language. It is interesting to see how it is used for motion prediction. Although the result is not good enough, it is still a good start. In the future, more language models can be used to see how well they can perform to do a comparison such as BiLSTM, Transformer, and Bert.<br />
<br />
LSTM-RNNs are really incredibly useful for sequential learning. The RNN should be able to predict, not only when a vehicle in front of the motion sensors, but it's likelihood of staying in motion vs coming to a sudden stop. There is no details in this review on the running time of the algorithm. In a field where split seconds could be the difference between an accident and a brake, running time cannot be stressed enough. Whether or not it is truly capable of dealing with real time traffic cannot be judged without relevant data and results being shown.<br />
<br />
== Reference ==<br />
[1] E. Choi, Crash Factors in Intersection-Related Crashes: An On-Scene Perspective (No. Dot HS 811 366), U.S. DOT Nat. Highway Traffic Safety Admin., Washington, DC, USA, 2010.<br />
<br />
[2] D. J. Phillips, T. A. Wheeler, and M. J. Kochenderfer, “Generalizable intention prediction of human drivers at intersections,” in Proc. IEEE Intell. Veh. Symp. (IV), Los Angeles, CA, USA, 2017, pp. 1665–1670.<br />
<br />
[3] B. Kim, C. M. Kang, J. Kim, S. H. Lee, C. C. Chung, and J. W. Choi, “Probabilistic vehicle trajectory prediction over occupancy grid map via recurrent neural network,” in Proc. IEEE 20th Int. Conf. Intell. Transp. Syst. (ITSC), Yokohama, Japan, 2017, pp. 399–404.<br />
<br />
[4] E. Strigel, D. Meissner, F. Seeliger, B. Wilking, and K. Dietmayer, “The Ko-PER intersection laserscanner and video dataset,” in Proc. 17th Int. IEEE Conf. Intell. Transp. Syst. (ITSC), Qingdao, China, 2014, pp. 1900–1901.<br />
<br />
[5] Henggang Cui, Thi Nguyen, Fang-Chieh Chou, Tsung-Han Lin, Jeff Schneider, David Bradley, Nemanja Djuric: “Deep Kinematic Models for Kinematically Feasible Vehicle Trajectory Predictions”, 2019; [http://arxiv.org/abs/1908.00219 arXiv:1908.00219].<br />
<br />
[6]Schulz, Jens & Hubmann, Constantin & Morin, Nikolai & Löchner, Julian & Burschka, Darius. (2019). Learning Interaction-Aware Probabilistic Driver Behavior Models from Urban Scenarios. 10.1109/IVS.2019.8814080.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Evaluating_Machine_Accuracy_on_ImageNet&diff=49760Evaluating Machine Accuracy on ImageNet2020-12-07T05:52:41Z<p>J244yang: /* Human Accuracy Measurement Process */</p>
<hr />
<div>== Presented by == <br />
Siyuan Xia, Jiaxiang Liu, Jiabao Dong, Yipeng Du<br />
<br />
== Introduction == <br />
ImageNet is one of the most influential dataset in machine learning with images and corresponding labels over 1000 classes. This paper intends to explore the causes for performance differences between human experts and machine learning models, more specifically, CNN, on ImageNet. <br />
<br />
Firstly, some images could belong to multiple classes. As a result, it is possible to underestimate the performance if we assign each image with only one label, which is what is being done in the top-1 metric. On the other hand, the top-5 metric looks at the top five predictions by the model for an image and checks if the target label is within those five predictions (Krizhevsky, Sutskever, & Hinton). Therefore, we adopt both top-1 and top-5 metrics where the performances of models, unlike human labelers, are linearly correlated in both cases.<br />
<br />
Secondly, in contrast to the uniform performance of models in classes, humans tend to achieve better performances on inanimate objects. Human labelers achieve similar overall accuracies as the models, which indicates spaces of improvements on specific classes for machines.<br />
<br />
Lastly, the setup of drawing training and test sets from the same distribution may favor models over human labelers. That is, the accuracy of multi-class prediction from models drops when the testing set is drawn from a different distribution than the training set, ImageNetV2. But this shift in distribution does not cause a problem for human labelers.<br />
<br />
== Experiment Setup ==<br />
=== Overview ===<br />
There are four main phases to the experiment, which are (i) initial multilabel annotation, (ii) human labeler training, (iii) human labeler evaluation, and (iv) final annotation overview. The five authors of the paper are the participants in the experiments. <br />
<br />
A brief overview of the four phases is as follows:<br />
[[File:Experiment Set Up.png |800px| center]]<br />
<br />
=== Initial multi-label annotation ===<br />
Three labelers A, B, and C provided multi-label annotations for a subset of size 20,000 from the ImageNet validation set, and all 20,683 images from the ImageNetV2 test sets. These experiences give A, B, and C extensive experience with the ImageNet dataset.<br />
<br />
=== Human Labeler Training === <br />
All five labelers trained on labeling a subset of the remaining ImageNet images. "Training" the human labelers consisted of teaching the humans the distinctions between very similar classes in the training set. For example, there are 118 classes of "dog" within ImageNet and typical human participants will not have working knowledge of the names of each breed of dog seen even if they can recognize and distinguish that breed from others. Local members of the American Kennel Club were even contacted to help with dog breed classification. To do this labelers were trained on class-specific tasks for groups like dogs, insects, monkeys beaver and others. They were also given immediate feedback on whether they were correct and then were asked where they thought they needed more training to improve. Unlike the two annotators in (Russakovsky et al., 2015), who had insufficient training data, the labelers in this experiment had up to 100 training images per class while labeling. This allowed the labelers to really understand the finer details of each class.<br />
<br />
=== Human Labeler Evaluation ===<br />
Class-balanced random samples, which contain 1,000 images from the 20,000 annotated images are generated from both the ImageNet validation set and ImageNetV2. Five participants labeled these images over 28 days.<br />
<br />
=== Final annotation Review ===<br />
All labelers reviewed the additional annotations generated in the human labeler evaluation phase.<br />
<br />
== Multi-label annotations==<br />
[[File:Categories Multilabel.png|800px|center]]<br />
<div align="center">Figure 3</div><br />
<br />
===Top-1 accuracy===<br />
With Top-1 accuracy being the standard accuracy measure used in classification studies, it measures the proportions of examples for which the predicted label matches the single target label. As many images often contain more than one object for classification, for example, Figure 3a contains a desk, laptop, keyboard, space bar, and more. With Figure 3b showing a centered prominent figure yet labeled otherwise (people vs picket fence), it can be seen how a single target label is inaccurate for such a task since identifying the main objects in the image does not suffice due to its overly stringent and punishes predictions that are the main image yet does not match its label.<br />
===Top-5 accuracy===<br />
With Top-5 considers a classification correct if the object label is in the top 5 predicted labels. Although it partially resolves the problem with Top-1 labeling, it is still not ideal since it can trivialize class distinctions. For instance, within the dataset, five turtle classes are given which is difficult to distinguish under such classification evaluations.<br />
<br />
===Multi-label accuracy===<br />
The paper then proposes that for every image, the image shall have a set of target labels and a prediction; if such prediction matches one of the labels, it will be considered as correct labeling. Due to the above-discussed limitations of Top-1 and Top-5 metrics, the paper claims it is necessary for rigorous accuracy evaluation on the dataset. <br />
<br />
===Types of Multi-label annotations===<br />
====Multiple objects or organisms====<br />
For the images containing more than one object or organism that corresponds to ImageNet, the paper proposed to add an additional target label for each entity in the image. With the discussed image in Figure 3b, the class groom, bow tie, suit, gown, and hoopskirt are all present in the foreground which is then subsequently added to the set of labels.<br />
====Synonym or subset relations====<br />
For similar classes, the paper considers them as under the same bigger class, that is, for two similarly labeled images, classification is considered correct if the produced label matches either one of the labels. For instance, warthog, African elephant, and Indian element all have prominent tusks, they will be considered subclasses of the tusker, Figure 3c shows a modification of labels to contain tusker as a correct label.<br />
====Unclear Image====<br />
In certain cases such as Figure 3d, there is a distinctive difficulty to determine whether a label was correct due to ambiguities in the class hierarchy, such as differentiating between a lakeshore or a seashore.<br />
<br />
===Collecting multi-label annotations===<br />
Participants reviewed all predictions made by the models on the dataset ImageNet and ImageNet-V2, the participants then categorized every unique prediction made by the models on the dataset into correct and incorrect labels in order to allow all images to have multiple correct labels to satisfy the above-listed method.<br />
===The multi-label accuracy metric===<br />
One prediction is only correct if and only if it was marked correct by the expert reviewers during the annotation stage. As discussed in the experiment setup section, after human labelers have completed labeling, a second annotation stage is conducted. In Figure 4, a comparison of Top-1, Top-5, and multi-label accuracies showed higher Top-1 and Top-5 accuracy corresponds with higher multi-label accuracy as expected. With multi-label accuracies measures consistently higher than Top-1 yet lower than Top-5 which shows a high correlation between the three metrics, the paper concludes that multi-label metrics measures a semantically more meaningful notion of accuracy compared to its counterparts.<br />
<br />
== Human Accuracy Measurement Process ==<br />
=== Bias Control ===<br />
Since three participants participated in the initial round of annotation, they did not look at the data for six months, and two additional annotators are introduced in the final evaluation phase to ensure fairness of the experiment. <br />
<br />
=== Human Labeler Training ===<br />
The three main difficulties encountered during human labeler training are fine-grained distinctions, class unawareness, and insufficient training images. Thus, three training regimens are provided to address the problems listed above, respectively. First, labelers will be assigned extra training tasks with immediate feedbacks on similar classes. Second, labelers will be provided access to search for specific classes during labeling. Finally, the training set will contain a reasonable amount of images for each class. There are difficult class distinctions for humans especially with the fine-grained distinction. To help humans perform well on these class distinction, the training tasks only contained images from certain animal families.<br />
<br />
=== Labeling Guide ===<br />
A labeling guide is constructed to distill class analysis learned during training into discriminative traits that could be used as a reference during the final labeling evaluation.<br />
<br />
=== Final Evaluation and Review ===<br />
Two samples, each containing 1000 images, are sampled from ImageNet and ImageNetV2, respectively, They are sampled in a class-balanced manner and shuffled together. Over 28 days, all five participants labeled all images. They spent a median of 26 seconds per image. After labeling is completed, an additional multi-label annotation session was conducted, in which human predictions for all images are manually reviewed. Comparing to the initial round of labeling, 37% of the labels changes due to participants' greater familiarity with the classes.<br />
<br />
== Main Results ==<br />
[[File:Evaluating Machine Accuracy on ImageNet Figure 1.png | center]]<br />
<br />
<div align="center">Figure 1</div><br />
<br />
===Comparison of Human and Machine Accuracies on Image Net===<br />
From Figure 1, we can see that the difference in accuracies between the datasets is within 1% for all human participants. As hypothesized, human testers indeed performed better than the automated models on both datasets. It's worth noticing that labelers D and E, who did not participate in the initial annotation period, actually performed better than the best automated model.<br />
===Comparison of Human and Machine Accuracies on Image Net===<br />
Based on the results shown in Figure 1, we can see that the confidence interval of the best 4 human participants and 4 best model overlap; however, with a p-value of 0.037 using the McNemar's paired test, it rejects the hypothesis that the FixResNeXt model and Human E labeler have the same accuracy with respect to the ImageNet validation dataset. Figure 1 also shows that the confidence intervals of the labeling accuracies for human labelers C, D, E do not overlap with the confidence interval of the best model with respect to ImageNet-V2 and with the McNemar's test yielding a p-value of <math>2\times 10^{-4}</math>, it is clear that the hypothesis human and machined models have same robustness to model distribution shifts ought to be rejected.<br />
<br />
== Other Observations ==<br />
<br />
[[File: Results_Summary_Table.png| 800px|center]]<br />
<br />
=== Difficult Images ===<br />
<br />
The experiment also shed some light on images that are difficult to label. 10 images were misclassified by all of the human labelers. Among those 10 images, there was 1 image of a monkey and 9 of dogs. In addition, 27 images, with 19 in object classes and 8 in organism classes, were misclassified by all 72 machine learning models in this experiment. Only 2 images were labeled wrong by all human labelers and models. Both images contained dogs. Researchers also noted that difficult images for models are mostly images of objects and exclusively images of animals for human labelers.<br />
<br />
=== Accuracies without dogs ===<br />
<br />
As previously discussed in the paper, machine learning models tend to outperform human labelers when classifying the 118 dog classes. To better understand to what extent does models outperform human labelers, researchers computed the accuracies again by excluding all the dog classes. Results showed a 0.6% increase in accuracy on the ImageNet images using the best model and a 1.1% increase on the ImageNet V2 images. In comparison, the mean increases in accuracy for human labelers are 1.9% and 1.8% on the ImageNet and ImageNet V2 images respectively. Researchers also conducted a simulation to demonstrate that the increase in human labeling accuracy on non-dog images is significant. This simulation was done by bootstrapping to estimate the changes in accuracy when only using data for the non-dog classes, and simulation results show smaller increases than in the experiment. <br />
<br />
In conclusion, it's more difficult for human labelers to classify images with dogs than it is for machine learning models.<br />
<br />
=== Accuracies on objects ===<br />
Researchers also computed machine and human labelers' accuracies on a subset of data with only objects, as opposed to organisms, to better illustrate the differences in performance. This test involved 590 object classes. As shown in the table above, there is a 3.3% and 3.4% increase in mean accuracies for human labelers on the ImageNet and ImageNet V2 images. In contrast, there is a 0.5% decrease in accuracy for the best model on both ImageNet and ImageNet V2. This indicates that human labelers are much better at classifying objects than these models are.<br />
<br />
=== Accuracies on fast images ===<br />
Unlike the CNN models, human labelers spent different amounts of time on different images, spanning from several seconds to 40 minutes. To further analyze the images that take human labelers less time to classify, researchers took a subset of images with median labeling time spent by human labelers of at most 60 seconds. These images were referred to as "fast images". There are 756 and 714 fast images from ImageNet and ImageNet V2 respectively, out of the total 2000 images used for evaluation. Accuracies of models and humans on the fast images increased significantly, especially for humans. <br />
<br />
This result suggests that human labelers know when an image is difficult to label and would spend more time on it. It also shows that the models are more likely to correctly label images that human labelers can label relatively quickly.<br />
<br />
== Related Work ==<br />
<br />
=== Human accuracy on ImageNet ===<br />
<br />
Russakovsky et al. (2015) studied two trained human labelers' accuracies on 1500 and 258 images in the context of the ImageNet challenge. The top-5 accuracy of the labeler who labeled 1500 images was the well-known human baseline on ImageNet. <br />
<br />
As introduced before, the researchers went beyond by using multi-label accuracy, using more labelers, and focusing on robustness to small distribution shifts. Although the researchers had some different findings, some results are also consistent with results from (Russakovsky et al., 2015). An example is that both experiments indicated that it takes human labelers around one minute to label an image. The time distribution also has a long tail, due to the difficult images as mentioned before.<br />
<br />
=== Human performance in computer vision broadly ===<br />
There are many examples of recent studies about humans in the area of computer vision, such as investigating human robustness to synthetic distribution change (Geirhos et al., 2017) and studying what characteristics do humans use to recognize objects (Geirhos et al., 2018). Other examples include the adversarial examples constructed to fool both machines and time-limited humans (Elsayed et al., 2018) and illustrating foreground/background objects' effects on human and machine performance (Zhu et al., 2016). <br />
<br />
=== Multi-label annotations ===<br />
Stock & Cissé (2017) also studied ImageNet's multi-label nature, which aligns with the researchers' study in this paper. According to Stock & Cissé (2017), the top-1 accuracy measure could underestimate multi-label by up to 13.2%. The authors suggest that releasing these labelled data to the public will allow for more robust models in the future.<br />
<br />
=== ImageNet inconsistencies and label error ===<br />
Researches have found and recorded some incorrectly labeled images from ImageNet and ImageNet V2 during this study. Earlier studies (Van Horn et al., 2015) also shown that at least 4% of the birds in ImageNet are misclassified. This work also noted that the inconsistent taxonomic structure in birds' classes could lead to weak class boundaries. Researchers also noted that the majority of the fine-grained organism classes also had similar taxonomic issues.<br />
<br />
=== Distribution shift ===<br />
There has been an increasing amount of studies in this area. One focus of the studies is distributionally robust optimization (DRO), which finds the model that has the smallest worst-case expected error over a set of probability distributions. Another focus is on finding the model with the lowest error rates on adversarial examples. Work in both areas has been productive, but none was shown to resolve the drop in accuracies between ImageNet and ImageNet V2. A recent [https://papers.nips.cc/paper/2019/file/8558cb408c1d76621371888657d2eb1d-Paper.pdf paper] also discusses quantifying uncertainty under a distribution shift, in other words whether the output of probabilistic deep learning models should or should not be trusted.<br />
<br />
== Conclusion and Future Work ==<br />
<br />
=== Conclusion ===<br />
Researchers noted that in order to achieve truly reliable machine learning, they need a deeper understanding of the range of parameters where the model still remain robust. Techniques from Combinatorics and sensitivity analysis, in particular, might yield fruitful results. This study has provided valuable insights into the desired robustness properties by comparing model performance to human performance. This is especially evident given the results of the experiment which show humans drastically outperforming machine learning in many cases and proposes the question of how much accuracy one is willing to give up in exchange for efficiency. The results have shown that current performance benchmarks are not addressing the robustness to small and natural distribution shifts, which are easily handled by humans.<br />
<br />
=== Future work ===<br />
Other than improving the robustness of models, researchers should consider investigating if less-trained human labelers can achieve a similar level of robustness to distributional shifts. In addition, researchers can study the robustness to temporal changes, which is another form of natural distribution shift (Gu et al., 2019; Shankar et al., 2019). Also, Convolutional Neural Network can be a candidate to improve the accuracy of classifying images.<br />
<br />
== Critiques ==<br />
# The method of using human to classify Imagenet is fully circular, since the label of imagenet itself is originally annotated by human beings. In fact, the classification scheme itself is intrinsically human construction. It is not logical to test human performance with human performance. This circular contsruction completely violates scientific principles.<br />
# Table 1 simply showed a difference in ImageNet multi-label accuracy yet does not give an explicit reason as to why such a difference is present. Although the paper suggested the distribution shift has caused the difference, it does not give other factors to concretely explain why the distribution shift was the cause.<br />
# With the recommendation to future machine evaluations, the paper proposed to "Report performances on dogs, other animals, and inanimate objects separately.". Despite its intentions, it is narrowly specific and requires further generalization for it to be convincing. <br />
# With choosing human subjects as samplers, no further information was given as to how they are chosen nor there are any background information was given. As it is a classification problem involving many classes as specific to species, a biology student would give far more accurate results than a computer science student or a math student. To make this study more plausible, more human labelers should be sampled.<br />
# As explaining the importance of multi-label metrics using comparison to Top-5 metric, the turtle example falls within the overall similarity (simony) classification of the multi-label evaluation metric, as such, if the Top-5 evaluation suggests any one of the turtle species were selected, the algorithm is considered to produce a correct prediction which is the intention. The example does not convey the necessity of changing to the proposed metric over the Top-5 metric. <br />
# With the definition in the paper regarding multi-label metrics, it is hard to see why expanding the label set is different from a traditional Top-5 metric or rather necessary, ergo does not yield the claim which the proposed metric is necessary for rigorous accuracy evaluation on ImageNet.<br />
# When discussing the main results, the paper discusses the hypothesis on distribution shift having no effects on human and machine model accuracies; the presentation is poor at best with no clear centric to what they are trying to convey to how (in detail) they resulted in such claims.<br />
# In the experiment setup of the presentation, there are a lot of key terms without detailed description. For example, Human labeler training using a subset of the remaining 30,000 unannotated images in the ImageNet validation set, labelers A, B, C, D, and E underwent extensive training to understand the intricacies of fine-grained class distinctions in the ImageNet class hierarchy. Authors should clarify each key term in the presentation otherwise readers are hard to follow.<br />
# Not sure how the human samplers were determined and simply picking several people will have really high bias because the sample is too small and they have different background which will definitely affect the results a lot. Also, it will be better if there are more comparisons between the model introduced and other models.<br />
# Given the low amount of human participants, it is hard to take the results seriously (there is too much variance). Also it's not exactly clear how the authors determined that the multi-label accuracy metric measures a semantically more meaningful notion of accuracy compared to its counterparts. For example, one of the issues with top-5 accuracy that they mention is: "For instance, within the dataset, five turtle classes are given which is difficult to distinguish under such classification evaluations." But it's not clear how multi-label accuracy would be better in this instance.<br />
# It is unclear how well the human labeler can perform labeling after training. So the final result is not that trust-worthy.<br />
# In this experiment set up, label annotators are the same as participants of the experiments. Even if there's a break between the annotating and evaluating human labeler evaluation, the impact of the break in reducing bias is not clear. One potential human labeling data is google's "I'm not a robot" verification test. One variation of the verification test asks users to select all the photos from 9 images that are related to a certain keyword. This allows for a more accurate measurement of human performance vs ImageNet performance. In addition, it's going to reduce the biases from the small number of experiment participants.<br />
# Following Table 2, the authors appear to try and claim that the model is better than the human labelers, simply because the model experienced a better increase in classification following the removal of dog photos then the human labeler did, however, a quick look at the table shows that most human labelers still performed better than the best model. The authors should be making the claim that human labelers are better at labeling dogs than the modal, but are still better overall after removing the dogs dataset.<br />
# The reason why human labeler outperforms CNN could be human had much more training. It would be more convincing if the paper could provide a metric in order to measure human labelers' training data set size.<br />
# Actually, in the multi-label case, it is vague to determine whether the machine learning model or the human labellers were giving the correct label. The structure of the dataset is pretty essential in training a network, in which data with uncertain label (even determined by human) should be avoided.<br />
# The authors mentioned that untrained labelers will likely be in lower accuracy, they can give a standard or definition about a well-trained labeler.<br />
# I believe the authors needed to include more information about how they determined the samples such as human samplers, and also more details on how to define unclear images.<br />
# It would be more convincing if the author could provide the criteria of being human samplers and unclear images, and the accuracy of the human labeler.<br />
# The summary only explains some model components but does not thoroughly goes through the big picture of the model; data-preprocessing, training, and prediction procedures. It would be nice to know the details as well.<br />
# It seems the core problem is more about the dataset itself and not the evaluation procedure. We would not have issues with top 1 and top 5 if Imagenet contained discernable classes with good labels. Of course, this is very expensive, and imagenet is an _excellent_ dataset given these constraints. It does not seem like their proposed solution, multiple labels per image, addresses their concerns properly, as other critiques have already mentioned. Furthermore, having multiple labels per image does not translate to real-life value the same way that the top 5 or top 1 metric does, as in the common case, there is one right answer for a classification problem.<br />
# The paper could provide details on ways to improve the accuracy and robustness of the model. Since the paper mentions CNN, it could provide details of the model and why CNN is a good candidate.<br />
# The accuracy of the model is directly correlated with how the images are labelled. In all multi-label annotations, the authors describe a predicted label as correct if it is within a set of "correct labels" where each image has a different number of correct labels. Perhaps it would yield better results if the model were to first identify the number of objects in the image first and then by using some form of criteria, it labels those identified objects in order of importance (i.e. objects that are closer are labelled first). The authors also never specified what criteria the model uses to "pick out" which object it will label in the image.<br />
# The paper mentions difficult images and fast images. It would be better if the paper had generalized the type of images that constitute difficult images (i.e., the paper mentions 118 dog classes, what are some general characteristics of difficult images?) In addition, it would be interesting to compare the performance between human and machine accuracy on non-fast images.<br />
# The paper meaingfully and correctly points out the problem that the current evaluation of ML algorithm by only using the accuracy on Imagnet as the bechmark is simplistic and probelmatic. However, the idea of comparing human performance with ML models is problematic, since it is hard or even impossible to control the various variables that can drastically change human performance: training time, domain knowledge, cognitive function, amount of work-load, and various environmental factors. In order to compare different experimental methods, the most important step is to carefully control the confounding variables to reach any meaningful conclusion.<br />
# The original question would be how ImageNet was created? The images can only be labeled by human labelers. There might be some mistakes and missing details. The combination of human evaluation and machine evaluation might be helpful to resolve this problem.<br />
# Regarding the difficult problems, CatsandDogs is a very popular dataset that in this day it is trivial for a non-deep CNN to classify with high accuracies. The author would do well to test this CNN with other classes, since its inconceivable that a CNN cannot learn the characteristics of a dog with relation to the other classes in Imagenet. Why would it be able to differentiate the breeds of dogs, but not other organisms?<br />
<br />
== Reference ==<br />
[1] Shankar, V., Roelofs, R., Mania, H., Fang, A., Recht, B., & Schmidt, L. (2020). Evaluating Machine Accuracy on ImageNet. ICML 2020.<br />
<br />
[2] Krizhevsky, A., Sutskever, I., & Hinton, G. E. ImageNet Classification with Deep Convolutional Neural Networks. 2. Retrieved from http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Speech2Face:_Learning_the_Face_Behind_a_Voice&diff=49755Speech2Face: Learning the Face Behind a Voice2020-12-07T05:46:42Z<p>J244yang: /* Ethical Considerations */</p>
<hr />
<div>== Presented by == <br />
Ian Cheung, Russell Parco, Scholar Sun, Jacky Yao, Daniel Zhang<br />
<br />
== Introduction ==<br />
This paper presents a deep neural network architecture called Speech2Face which utilizes millions of Internet/Youtube videos of people speaking to learn the correlation between a voice and the respective face. The model produces facial reconstruction images that capture specific physical attributes learning the correlations between faces and voices, such as a person's age, gender, or ethnicity, through a self-supervised procedure. Namely, the model utilizes the simultaneous occurrence of faces and speech in videos and does not need to model the attributes explicitly. This model explores what types of facial information could be extracted from speech without the constraints of predefined facial characterizations. Without any prior information or accurate classifiers, the reconstructions revealed correlations between craniofacial features and voice in addition to the correlation between dominant features (gender, age, ethnicity, etc.) and voice. The model is evaluated and numerically quantifies how closely the reconstruction, done by the Speech2Face model, resembles the true face images of the respective speakers.<br />
<br />
== Ethical Considerations ==<br />
<br />
The authors note that due to the potential sensitivity of facial information, they have chosen to explicitly state some ethical considerations. The first of which is privacy. The paper states that the method cannot recover the true identity of the face or produce faces of specific individuals, but rather will show average-looking faces. The paper also addresses that there are potential dataset biases that exist for the voice-face correlations, thus the faces may not accurately represent the intended population. The paper recommends that any further investigation or practical use of this technology will be tested to represent the intended population and also if the data does not reflect this, more representative data should be broadly collected. Finally, it acknowledges that the model uses demographic categories such as "White" and "Asian" that are defined by a commercial face attribute classifier.<br />
<br />
== Previous Work ==<br />
With visual and audio signals being so dominant and accessible in our daily life, there has been huge interest in how visual and audio perceptions interact with each other. Arandjelovic and Zisserman [1] leveraged the existing database of mp4 files to learn a generic audio representation to classify whether a video frame and an audio clip correspond to each other. These learned audio-visual representations have been used in a variety of setting, including cross-modal retrieval, sound source localization and sound source separation. This also paved the path for specifically studying the association between faces and voices of agents in the field of computer vision. In particular, cross-modal signals extracted from faces and voices have been proposed as a binary or multi-task classification task and there have been some promising results. Studies have been able to identify active speakers of a video, separate speech from multiple concurrent sources, predict lip motion from speech, and even learn the emotion of the agents based on their voices. Aytar et al. [6] proposed a student-teacher training procedure in which a well established visual recognition model was used to transfer the knowledge obtained in the visual modality to the sound modality, using unlabeled videos.<br />
<br />
Recently, various methods have been suggested to use various audio signals to reconstruct visual information, where the reconstructed subject is subjected to a priori. Notably, Duarte et al. [2] were able to synthesize the exact face images and expression of an agent from speech using a GAN model. A generative adversarial network (GAN) model is one that uses a generator to produce seemingly possible data for training and a discriminator that identifies if the training data is fabricated by the generator or if it is real [7]. This paper instead hopes to recover the dominant and generic facial structure from a speech.<br />
<br />
== Motivation ==<br />
It seems to be a common trait among humans to imagine what some people look like when we hear their voices before we have seen what they look like. There is a strong connection between speech and appearance, which is a direct result of the factors that affect speech, including age, gender, and facial bone structure. In addition, other voice-appearance correlations stem from the way we talk: language, accent, speed, pronunciations, etc. These properties of speech are often common among many different nationalities and cultures, which can, in turn, translate to common physical features among different voices. Namely, from an input audio segment of a person speaking, the method would reconstruct an image of the person’s face in a canonical form (frontal-facing, neutral expression). The goal was to study to what extent people can infer how someone else looks from the way they talk. Rather than predicting a recognizable image of the exact face, the authors are more interested in capturing the dominant facial features.<br />
<br />
== Model Architecture == <br />
<br />
'''Speech2Face model and training pipeline'''<br />
<br />
[[File:ModelFramework.jpg|center]]<br />
<br />
<div style="text-align:center;"> Figure 1. '''Speech2Face model and training pipeline''' </div><br />
<br />
<br />
<br />
The Speech2Face Model consists of two parts - a voice encoder which takes in a spectrogram of speech as input and outputs low dimensional face features, and a face decoder which takes in face features as input and outputs a normalized image of a face (neutral expression, looking forward). Figure 1 gives a visual representation of the pipeline of the entire model, from video input to a recognizable face. The combination of the voice encoder and face decoder results are combined to form an image. The variability in facial expressions, head positions and lighting conditions of the face images creates a challenge to both the design and training of the Speech2Face model. It needs a model to figure out many irrelevant variations in the data, and to implicitly extract important internal representations of faces. To avoid this problem the model is trained to first regress to a low dimensional intermediate representation of the face. <br />
<br />
'''Face Decoder''' <br />
The face decoder itself was taken from previous work The VGG-Face model by Cole et al [3] (a face recognition model that is pretrained on a largescale face database [5] is used to extract a 4069-D face feature from the penultimate layer of the network.) and will not be explored in great detail here, but in essence the facenet model is combined with a single multilayer perceptron layer, the result of which is passed through a convolutional neural network to determine the texture of the image, and a multilayer perception to determine the landmark locations. The face decoder kept the VGG-Face model's dimension and weights. The weights were also trained separately and remained fixed during the voice encoder training. <br />
<br />
'''Voice Encoder Architecture''' <br />
<br />
[[File:VoiceEncoderArch.JPG|center]]<br />
<br />
<div style="text-align:center;"> Table 1: '''Voice encoder architecture''' </div><br />
<br />
<br />
<br />
The voice encoder itself is a convolutional neural network, which transforms the input spectrogram into pseudo face features. The exact architecture is given in Table 1. The model alternates between convolution, ReLU, batch normalization layers, and layers of max-pooling. In each max-pooling layer, pooling is only done along the temporal dimension of the data. This is to ensure that the frequency, an important factor in determining vocal characteristics such as tone, is preserved. In the final pooling layer, an average pooling is applied along the temporal dimension. This allows the model to aggregate information over time and allows the model to be used for input speeches of varying lengths. Two fully connected layers at the end are used to return a 4096-dimensional facial feature output.<br />
<br />
'''Training'''<br />
<br />
The AVSpeech dataset, a large-scale audio-visual dataset is used for the training. AVSpeech dataset is comprised of millions of video segments from Youtube with over 100,000 different people. The training data is composed of educational videos and does not provide an accurate representation of the global population, which will clearly affect the model. Also note that facial features that are irrelevant to speech, like hair color, may be predicted by the model. From each video, a 224x224 pixels image of the face was passed through the face decoder to compute a facial feature vector. Combined with a spectrogram of the audio, a training and test set of 1.7 and 0.15 million entries respectively were constructed.<br />
<br />
The voice encoder is trained in a self-supervised manner. A frame that contains the face is extracted from each video and then inputted to the VGG-Face model to extract the feature vector <math>v_f</math>, the 4096-dimensional facial feature vector given by the face decoder on a single frame from the input video. This provides the supervision signal for the voice-encoder. The feature <math>v_s</math>, the 4096 dimensional facial feature vector from the voice encoder, is trained to predict <math>v_f</math>.<br />
<br />
In order to train this model, a proper loss function must be defined. The L1 norm of the difference between <math>v_s</math> and <math>v_f</math>, given by <math>||v_f - v_s||_1</math>, may seem like a suitable loss function, but in actuality results in unstable results and long training times. Figure 2, below, shows the difference in predicted facial features given by <math>||v_f - v_s||_1</math> and the following loss. Based on the work of Castrejon et al. [4], a loss function is used which penalizes the differences in the last layer of the VGG-Face model <math>f_{VGG}</math>: <math> \mathbb{R}^{4096} \to \mathbb{R}^{2622}</math> and the first layer of face decoder <math>f_{dec}</math> : <math> \mathbb{R}^{4096} \to \mathbb{R}^{1000}</math>. The final loss function is given by: $$L_{total} = ||f_{dec}(v_f) - f_{dec}(v_s)|| + \lambda_1||\frac{v_f}{||v_f||} - \frac{v_s}{||v_s||}||^2_2 + \lambda_2 L_{distill}(f_{VGG}(v_f), f_{VGG}(v_s))$$<br />
This loss penalizes on both the normalized Euclidean distance between the 2 facial feature vectors and the knowledge distillation loss, which is given by: $$L_{distill}(a,b) = -\sum_ip_{(i)}(a)\text{log}p_{(i)}(b)$$ $$p_{(i)}(a) = \frac{\text{exp}(a_i/T)}{\sum_j \text{exp}(a_j/T)}$$ Knowledge distillation is used as an alternative to Cross-Entropy. By recommendation of Cole et al [3], <math> T = 2 </math> was used to ensure a smooth activation. <math>\lambda_1 = 0.025</math> and <math>\lambda_2 = 200</math> were chosen so that magnitude of the gradient of each term with respect to <math>v_s</math> are of similar scale at the <math>1000^{th}</math> iteration.<br />
<br />
<center><br />
[[File:L1vsTotalLoss.png | 700px]]<br />
</center><br />
<br />
<div style="text-align:center;"> Figure 2: '''Qualitative results on the AVSpeech test set''' </div><br />
<br />
'''Implementation Details'''<br />
<br />
6 seconds of audio was used to compute the spectogram by taking a Short-time Fourier transform with Hann window of 25mm, hop length of 10ms, and 512 FFT frequenct bands. A CNN-based face detector from Dlib was used to crop the face regions from the frames. The VGG-face features are computed from the resized faces and together with the spectrogram was used for training. There were a total of 1.7 and 0.15 million spectra-feature pairs.<br />
<br />
== Results ==<br />
<br />
'''Confusion Matrix and Dataset statistics'''<br />
<br />
<center><br />
[[File:Confusionmatrix.png| 600px]]<br />
</center><br />
<br />
<div style="text-align:center;"> Figure 3. '''Facial attribute evaluation''' </div><br />
<br />
<br />
<br />
In order to determine the similarity between the generated images and the ground truth, a commercial service known as Face++ which classifies faces for distinct attributes (such as gender, ethnicity, etc) was used. Figure 3 gives a confusion matrix based on gender, ethnicity, and age. By examining these matrices, it is seen that the Speech2Face model performs very well on gender, only misclassifying 6% of the time. Similarly, the model performs fairly well on ethnicities, especially with white or Asian faces. Although the model performs worse on black and Indian faces, that can be attributed to the vastly unbalanced data, where 50% of the data represented a white face, and 80% represented a white or Asian face. <br />
<br />
'''Feature Similarity'''<br />
<br />
<center><br />
[[File:FeatSim.JPG]]<br />
</center><br />
<br />
<div style="text-align:center;"> Table 2. '''Feature similarity''' </div><br />
<br />
<br />
<br />
Another examination of the result is the similarity of features predicted by the Speech2Face model. The cosine, L1, and L2 distance between the facial feature vector produced by the model and the true facial feature vector from the face decoder were computed, and presented, above, in Table 2. A comparison of facial similarity was also done based on the length of audio input. From the table, it is evident that the 6-second audio produced a lower cosine, L1, and L2 distance, resulting in a facial feature vector that is closer to the ground truth. <br />
<br />
'''S2F -> Face retrieval performance'''<br />
<br />
<center><br />
[[File: Retrieval.JPG]]<br />
</center><br />
<br />
<div style="text-align:center;"> Table 3. '''S2F -> Face retrieval performance''' </div><br />
<br />
<br />
<br />
The performance of the model was also examined on how well it could produce the original image. The R@K metric, also known as retrieval performance by recall at K, measures the probability that the K closest images to the model output includes the correct image of the speaker's face. A higher R@K score indicates better performance. From Table 3, above, we see that both the 3-second and 6-second audio showed significant improvement over random chance, with the 6-second audio performing slightly better.<br />
<br />
'''Additional Observations''' <br />
<br />
Ablation studies were carried out to test the effect of audio duration and batch normalization. It was found that the duration of input audio during the training stage had little effect on convergence speed (comparing 3 and 6-second speech segments), while in the test stage longer input speech yields improvement in reconstruction quality. With respect to batch normalization (BN), it was found that without BN reconstructed faces would converge to an average face, while the inclusion of BN led to results which contained much richer facial features.<br />
<br />
== Conclusion ==<br />
The report presented a novel study of face reconstruction from audio recordings of a person speaking. The model was demonstrated to be able to predict plausible face reconstructions with similar facial features to real images of the person speaking. The problem was addressed by learning to align the feature space of speech to that of a pretrained face decoder. The model was trained on millions of videos of people speaking from YouTube. The model was then evaluated by comparing the reconstructed faces with a commercial facial detection service. The authors believe that facial reconstruction allows a more comprehensive view of voice-face correlation compared to predicting individual features, which may lead to new research opportunities and applications.<br />
<br />
== Discussion and Critiques ==<br />
<br />
There is evidence that the results of the model may be heavily influenced by external factors:<br />
<br />
1. Their method of sampling random YouTube videos resulted in an unbalanced sample in terms of ethnicity. Over half of the samples were white. We also saw a large bias in the model's prediction of ethnicity towards white. The bias in the results shows that the model may be overfitting the training data and puts into question what the performance of the model would be when trained and tested on a balanced dataset. Figure (11) highlights this shortcoming: The same man heard speaking in either English or Chinese was predicted to have a "white" appearance or an "asian" appearance respectively.<br />
<br />
2. The model was shown to infer different face features based on language. This puts into question how heavily the model depends on the spoken language. The paper mentioned the quality of face reconstruction may be affected by uncommon languages, where English is the most popular language on Youtube(training set). Testing a more controlled sample where all speech recording was of the same language may help address this concern to determine the model's reliance on spoken language.<br />
<br />
3. The evaluation of the result is also highly dependent on the Face++ classifiers. Since they compare the age, gender, and ethnicity by running the Face++ classifiers on the original images and the reconstructions to evaluate their model, the model that they create can only be as good as the one they are using to evaluate it. Therefore, any limitations of the Face++ classifier may become a limitation of Speech2Face and may result in a compounding effect on the miss-classification rate.<br />
<br />
4. Figure 4.b shows the AVSpeech dataset statistics. However, it doesn't show the statistics about speakers' ethnicity and the language of the video. If we train the model with a more comprehensive dataset that includes enough Asian/Indian English speakers and native language speakers will this increase the accuracy?<br />
<br />
5. One concern about the source of the training data, i.e. the Youtube videos, is that resolution varies a lot since the videos are randomly selected. That may be the reason why the proposed model performs badly on some certain features. For example, it is hard to tell the age when the resolution is bad because the wrinkles on the face are neglected.<br />
<br />
6. The topic of this project is very interesting, but I highly doubt this model will be practical in real-world problems. Because there are many factors to affect a person's sound in a real-world environment. Sounds such as phone clock, TV, car horn and so on. These sounds will decrease the accuracy of the predicted result of the model.<br />
<br />
7. A lot of information can be obtained from someone's voice, this can potentially be useful for detective work and crime scene investigation. In our world of increasing surveillance, public voice recording is quite common and we can reconstruct images of potential suspects based on their voice. In order for this to be achieved, the model has to be thoroughly trained and tested to avoid false positives as it could have a highly destructive outcome for a falsely convicted suspect.<br />
<br />
8. This is a very interesting topic, and this summary has a good structure for readers. Since this model uses Youtube to train model, but I think one problem is that most of the YouTubers are adult, and many additional reasons make this dataset highly unbalanced. What is more, some people may have a baby voice, this also could affect the performance of the model. But overall, this is a meaningful topic, it might help police to locate the suspects. So it might be interesting to apply this to the police.<br />
<br />
9. In addition, it seems very unlikely that any results coming from this model would ever be held in regard even remotely close to being admissible in court to identify a person of interest until the results are improved and the model can be shown to work in real-world applications. Otherwise, there seems to be very little use for such technology and it could have negative impacts on people if they were to be depicted in an unflattering way by the model based on their voice.<br />
<br />
10. Using voice as a factor of constructing the face is a good idea, but it seems like the data they have will have lots of noise and bias. The voice of a video might not come from the person in the video. There are so many YouTubers adjusting their voices before uploading their video and it's really hard to know whether they adjust their voice. Also, most YouTubers are adults so the model cannot have enough training samples about teenagers and kids.<br />
<br />
11. It would be interesting to see how the performance changes with different face encoding sizes (instead of just 4096-D) and also difference face models (encoder/decoders) to see if better performance can be achieved. Also given that the dataset used was unbalanced, was the dataset used to train the face model the same dataset? or was a different dataset used (the model was pretrained). This could affect the performance of the model as well.<br />
<br />
12. The audio input is transformed into a spectrogram before being used for training. They use STFT with a Hann window of 25 mm, a hop length of 10 ms, and 512 FFT frequency bands. They cite this method from a paper that focuses on speech separation, not speech classification. So, it would be interesting to see if there is a better way to do STFT, possibly with different hyperparameters (eg. different windowing, different number of bands), or if another type of transform (eg. wavelet transform) would have better results.<br />
<br />
13. A easy way to get somewhat balanced data is to duplicate the data that are fewer.<br />
<br />
14. This problem is interesting but is hard to generalize. This algorithm didn't account for other genders and mixed-race. In addition, the face recognition software Face++ introduces bias which can carry forward to Speech2Face algorithm. Face recognition algorithms are known to have higher error rates classifying darker-skinned individuals. Thus, it'll be tough to apply it to real-life scenarios like identifying suspects.<br />
<br />
15. This experiment raises a lot of ethical complications when it comes to possible applications in the real world. Even if this model was highly accurate, the implications of being able to discern a person's racial ethnicity, skin tone, etc. based solely on there voice could play in to inherent biases in the application user and this may end up being an issue that needs to be combatted in future research in this area. Another possible issue is that many people will change their intonation or vocal features based on the context (I'll likely have a different voice pattern in a job interview in terms of projection, intonation, etc. than if I was casually chatting/mumbling with a friend while playing video games for example).<br />
<br />
16. Overall a very interesting topic. I want to talk about the technical challenged raised by using the AVSSpeech dataset for training. The paper acknowledges that the AVSSpeech is unbalanced, and 80% of the data are white and Asians. It also says in the results section that "Our model does not perform on other races due to the imbalance in data". There does not seem to be any effort made in balancing the data. I think that there are definitely some data processing techniques that can be used (filtering, data augmentation, etc) to address the class imbalance problem. Not seeing any of these in the paper is a bit disappointing. Another issue I have noticed is that the model aims to predict an average-looking face from certain gender/racial group from voice input, due to ethical considerations. If we cannot reveal the identify of a person, why don't we predict the gender and race directly? Giving an average-looking face does not seem to be the most helpful.<br />
<br />
17. Very interesting research paper to be studied and the main objective was also interesting. This research leads to open question which can be applied to another application such as predicting person's face using voice and can be used in more advanced way. The only risk is how the data is obtained from YouTube where data is not consistent.<br />
<br />
18. The essay uses millions of natural videos of people speaking to find the correlation between face and voice. Since face and voice are commonly used as the identity of a person, there are many possible research opportunities and applications about improving voice and face unlock.<br />
<br />
19. It would be better to have a future work section to discuss the current shortage and explore the possible improvement and applications in the future.<br />
<br />
20. While the idea behind Speech2Face is interesting, ethnic profiling is a huge concern and it can further lead to racial discrimination, racism etc. Developers must put more care and thought into applying Speech2Face in tech before deploying the products.<br />
<br />
21. It would be helpful if the author could explore the different applications of this project in real life. Speech2face can be helpful during criminal investigation and essentially in scenarios when someone's picture is missing and only voice is available. It would also be helpful if the author could state the importance and need of such kind project in the society.<br />
<br />
22. The authors mention that they use the AVSpeech dataset for both training and testing but do not talk about how they split the data. It is possible that the same speakers were used in the training and testing data and so the model is able to recreate a face simply by matching the observed face to the observed audio. This would explain the striking example images shown in the paper.<br />
<br />
23. Another interesting application of this research is automated speech or facial animation at scale or in multiple languages. The cutting-edge automated facial animation solution provided by JALI Research Inc is applied in Cyberpunk 2077.<br />
<br />
24. It would be interesting to know the model can predict a similar face when one is speaking different languages. A person who is speaking multiple languages can have different tones and accents depending on a language that they speak.<br />
<br />
25. The results are actually amazing for the introduction of Speech2Face. As others have mentioned, the researchers might have used a biased dataset of YouTube videos favoring certain ethnicities and their accents and dialects. Thus, it would be nice to also see the data distribution. Additionally it would be nice to see how their model reacts to people who are able to speak multiple languages and see how well Speech2Face generalizes different language pronunciations of one person.<br />
<br />
26. The paper introduces Speech2Face and it definitely is one of the major areas of researches in the future. In the paper, the confusion matrix indicates that the model tends to misclassify based on the age of the speaking person. Specifically, the model tends to misclassify between 40-70. It would be interesting to see if the model could improve on its bottleneck by training on more speeches by the age group 40-70.<br />
<br />
27. An interesting topic, and as others have mentioned, has many ethical considerations and implications. Particularly in regions where call-recording is permitted, there is dangerous potential to for the technology to be misused to identify and target individuals. It would also be interesting to get a more in depth exploration into how the language spoken and accents have a bias. For example, if a person speaks with a strong British accent, are they classified as white? Particularly for Spanish-speakers, they vary greatly with respect to their skin colour and features, how well does the algorithm work on these individuals. A last nit-pick is the labelling used (i.e. Asian, White, Indian, Black) as this is not accurate since Indians, and moreover South Asians, fall under Asian as well.<br />
<br />
28. This topic is quite interesting and it could have great contribution in terms of criminal fight. But as the result, the accuracy is essential. There is still the space for much improvements since to tell a person's face by his/her voice is pretty hard since there are many factors such as oral structure, the language environment and even personality. Great bias could be resulted from these unpredictable factors.<br />
<br />
29. This is an interesting topic and could have great use in terms of finding criminals or people when having their voice recorded. However, the voice recording might be noisy and some might include voices of multiple people. It could consider ways to eliminate those factors that might effect the accuracy of the face generation.<br />
<br />
30. Most contents described in the paper are very useful. However, YouTube might not be a good enough data source since there are fewer labels to classify. Perhaps, after generating the model, the transfer learning could be done based on Facebook's videos in order to solve the imbalanced problem.<br />
<br />
31. This topic is really incredibly interesting and the writers should commend themselves on a job well done. However, Youtube, not only is it an ethnically skewed dataset, but has a non-negligible number of creators who use voice modifiers, auto tune, or a number of other things to change the pitch of their voices, which may lead to the significantly more errors in practical applications. A better dataset to be used could be Skype video calls, or a class room study. Also, judging from the way the model does it's prediction, it seems very prone to overfitting on the dataset, and will not generalize well, since pitch and sound are both incredibly variable across humans.<br />
<br />
32. One thing to notice is that the training data used to train the model is downloaded from Youtube, which may be a good site to retrieve a large amount of data. While it allows the possibility that the voices retrieved does not match with the people who made those sounds, claimed by the video. If that is the case, those records will become dirty data, and needs to be cleaned before training the model. Otherwise, there will be some huge misclassifications because some of the training data is not making sense. One way I can think of to improve this problem is that we may train multiple models on different subsets of the original dataset, and combine the results of all the models by taking weighted average.<br />
<br />
== References ==<br />
[1] R. Arandjelovic and A. Zisserman. Look, listen and learn. In<br />
IEEE International Conference on Computer Vision (ICCV),<br />
2017.<br />
<br />
[2] A. Duarte, F. Roldan, M. Tubau, J. Escur, S. Pascual, A. Salvador, E. Mohedano, K. McGuinness, J. Torres, and X. Giroi-Nieto. Wav2Pix: speech-conditioned face generation using generative adversarial networks. In IEEE International<br />
Conference on Acoustics, Speech and Signal Processing<br />
(ICASSP), 2019.<br />
<br />
[3] F. Cole, D. Belanger, D. Krishnan, A. Sarna, I. Mosseri, and W. T. Freeman. Synthesizing normalized faces from facial identity features. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.<br />
<br />
[4] L. Castrejon, Y. Aytar, C. Vondrick, H. Pirsiavash, and A. Torralba. Learning aligned cross-modal representations from weakly aligned data. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.<br />
<br />
[5] O. M. Parkhi, A. Vedaldi, and A. Zisserman. Deep face recognition. In British Machine Vision Conference (BMVC), 2015.<br />
<br />
[7] “Overview of GAN Structure | Generative Adversarial Networks,” ''Google Developers'', 24-May-2019. [Online]. Available: https://developers.google.com/machine-learning/gan/gan_structure. [Accessed: 02-Dec-2020].</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Research_Papers_Classification_System&diff=49754Research Papers Classification System2020-12-07T05:41:50Z<p>J244yang: /* Introduction */</p>
<hr />
<div>= Presented by =<br />
Jill Wang, Junyi (Jay) Yang, Yu Min (Chris) Wu, Chun Kit (Calvin) Li<br />
<br />
= Introduction =<br />
With the increasing advance of computer science and information technology, an increasingly overwhelming number of papers have been published. Due to the great volume, it has become incredibly hard to find and categorize papers. Typically this is a very time consuming activity. This paper introduces a paper classification system that utilizes the Term Frequency-Inverse Document Frequency (TF-IDF), Latent Dirichlet Allocation (LDA), and K-means clustering. The most important technology the system used to process big data is the Hadoop Distributed File System (HDFS). The system is highly fault-tolerant and can be deployed on low-cost hardware. It can handle quantitatively complex research paper classification problems efficiently and accurately.<br />
<br />
===General Framework===<br />
<br />
The paper classification system classifies research papers based on the abstracts given that the core of most papers is presented in the abstracts. <br />
<br />
[[ File:Systemflow.png |right|image on right| 400px]]<br />
<ol><li>Paper Crawling <br />
<p>Collects abstracts and keywords from research papers published during a given period</p></li><br />
<li>Preprocessing<br />
<p> <ol style="list-style-type:lower-alpha"><li>Removes stop words in the papers crawled, in which only nouns are extracted from the papers</li><br />
<li>generates a keyword dictionary, keeping only the top-N keywords with the highest frequencies</li> </ol><br />
</p></li> <br />
<li>Topic Modelling<br />
<p> Use the LDA to group the keywords into topics</p><br />
</li><br />
<li>Paper Length Calculation<br />
<p> Calculates the total number of occurrences of words to prevent an unbalanced TF values caused by the various length of abstracts using the map-reduce algorithm</p><br />
</li><br />
<li>Word Frequency Calculation<br />
<p> Calculates the Term Frequency (TF) values which represent the frequency of keywords in a research paper</p><br />
</li><br />
<li>Document Frequency Calculation<br />
<p> Calculates the Document Frequency (DF) values which represents the frequency of keywords in a collection of research papers. The higher the DF value, the lower the importance of a keyword.</p><br />
</li><br />
<li>Term frequency-inverse document frequency (TF-IDF) calculation<br />
<p> Calculates the inverse of the DF which represents the importance of a keyword.</p><br />
</li><br />
<li>Paper Classification<br />
<p> Classify papers by topics and similar subjects using the K-means clustering algorithm.</p><br />
</li><br />
</ol><br />
<br />
===Technologies===<br />
<br />
The HDFS with a Hadoop cluster composed of one master node, one sub-node, and four data nodes is what is used to process the massive paper data. Hadoop-2.6.5 version in Java is what is used to perform the TF-IDF calculation. Spark MLlib is what is used to perform the LDA. The Scikit-learn library is what is used to perform the K-means clustering.<br />
<br />
===HDFS===<br />
<br />
Hadoop Distributed File System (HDFS) was used to process big data in this system. HFDS has been shown to process big data rapidly and stably with high scalability which makes it a perfect choice for this problem. What Hadoop does is to break a big collection of data into different partitions and pass each partition to one individual processor. Each processor will only have information about the partition of data it has received.<br />
<br />
'''In this summary, we are going to focus on introducing the main algorithms of what this system uses, namely LDA, TF-IDF, and K-Means.'''<br />
<br />
=Data Preprocessing=<br />
===Crawling of Abstract Data===<br />
<br />
Under the assumption that audiences tend to first read the abstract of a paper to gain an overall understanding of the material, it is reasonable to assume the abstract section includes “core words” that can be used to effectively classify a paper's subject.<br />
<br />
An abstract is crawled to have its stop words removed. Stop words are words that are usually ignored by search engines, such as “the”, “a”, and etc. Afterward, nouns are extracted, as a more condensed representation for efficient analysis.<br />
<br />
This is managed on HDFS. The TF-IDF value of each paper is calculated through map-reduce, an easy-to-use programming model and implementation for processing and generating large data sets. The user must specify (i) a map procedure, that filters and sorts the input data to produce a set of intermediate key/value pairs and (ii) a reduce function, which performs a summary operation on the intermediate values with the same key and returns a smaller set of output key/value pairs. The MapReduce interface enables this process by grouping the intermediate values with the same key and passing them as input to the reduce function. For example, one could count the number of times various words appear in a large number of documents by setting your map procedure to count the number of occurrences of each word in a single document, and your reduce function to sum all counts of a given word [[https://dl.acm.org/doi/pdf/10.1145/1327452.1327492?casa_token=_Zg_DWxQzKEAAAAA:EHII0CaP36_ojGMT8huqTGLNMSEc-CKzZAoXBxSXe6pr2WB0DCQvEKa30CFQW0NSbB2-CVo8GcBcJAg 1]].<br />
<br />
===Managing Paper Data===<br />
<br />
To construct an effective keyword dictionary using abstract data and keywords data in all of the crawled papers, the authors categorized keywords with similar meanings using a single representative keyword. The approach is called stemming, which is common in cleaning data, where words are reduced to their word stem. An example is "running" and "ran" would be reduced to "run". 1394 keyword categories are extracted, which is still too much to compute. Hence, only the top 30 keyword categories are used.<br />
<br />
<div align="center">[[File:table_1_kswf.JPG|700px]]</div><br />
<br />
=Topic Modeling Using LDA=<br />
<br />
Latent Dirichlet allocation (LDA) is a generative probabilistic model that views documents as random mixtures over latent topics. Each topic is a distribution over words, and the goal is to extract these topics from documents.<br />
<br />
LDA estimates the topic-word distribution <math>P\left(t | z\right)</math> (probability of word "z" having topic "t") and the document-topic distribution <math>P\left(z | d\right)</math> (probability of finding word "z" within a given document "d") using Dirichlet priors for the distributions with a fixed number of topics. For each document, obtain a feature vector:<br />
<br />
\[F = \left( P\left(z_1 | d\right), P\left(z_2 | d\right), \cdots, P\left(z_k | d\right) \right)\]<br />
<br />
In the paper, authors extract topics from preprocessed paper to generate three kinds of topic sets, each with 10, 20, and 30 topics respectively. The following is a table of the 10 topic sets of highest frequency keywords.<br />
<br />
<div align="center">[[File:table_2_tswtebls.JPG|700px]]</div><br />
<br />
<br />
===LDA Intuition===<br />
<br />
LDA uses the Dirichlet priors of the Dirichlet distribution, which allows the algorithm to model a probability distribution ''over prior probability distributions of words and topics''. The following picture illustrates 2-simplex Dirichlet distributions with different alpha values, one for each corner of the triangles. <br />
<br />
<div align="center">[[File:dirichlet_dist.png|700px]]</div><br />
<br />
Simplex is a generalization of the notion of a triangle in k-1 dimension where k is the number of classes. For example, if you wish to classify essays into three groups, English, History and Math then the simplex would be a 2 dimension triangle, if you add philosophy as one of your potential class, then we would need a tetrahedron in 3 deminsion. In Dirichlet distribution, each parameter will be represented by a corner in simplex, so adding additional parameters implies increasing the dimensions of simplex. As illustrated, when alphas are smaller than 1 the distribution is dense at the corners. When the alphas are greater than 1 the distribution is dense at the centers.<br />
<br />
The following illustration shows an example LDA with 3 topics, 4 words and 7 documents.<br />
<br />
<div align="center">[[File:LDA_example.png|800px]]</div><br />
<br />
In the left diagram, there are three topics, hence it is a 2-simplex. In the right diagram there are four words, hence it is a 3-simplex. LDA essentially adjusts parameters in Dirichlet distributions and multinomial distributions (represented by the points), such that, in the left diagram, all the yellow points representing documents and, in the right diagram, all the points representing topics, are as close to a corner as possible. In other words, LDA finds topics for documents and also finds words for topics. At the end topic-word distribution <math>P\left(t | z\right)</math> and the document-topic distribution <math>P\left(z | d\right)</math> are produced.<br />
<br />
=Term Frequency Inverse Document Frequency (TF-IDF) Calculation=<br />
<br />
TF-IDF is widely used to evaluate the importance of a set of words in the fields of information retrieval and text mining. It is a combination of term frequency (TF) and inverse document frequency (IDF). The idea behind this combination is<br />
* It evaluates the importance of a word within a document<br />
* It evaluates the importance of the word among the collection of all documents<br />
<br />
The inverse of the document frequency accounts for the fact that term frequency will naturally increase as document frequency increases. Thus IDF is needed to counteract a word's TF to give an accurate representation of a word's importance.<br />
<br />
The TF-IDF formula has the following form:<br />
<br />
\[TF-IDF_{i,j} = TF_{i,j} \times IDF_{i}\]<br />
<br />
where i stands for the <math>i^{th}</math> word and j stands for the <math>j^{th}</math> document.<br />
<br />
===Term Frequency (TF)===<br />
<br />
TF evaluates the percentage of a given word in a document. Thus, TF value indicates the importance of a word. The TF has a positive relation with the importance.<br />
<br />
In this paper, we only calculate TF for words in the keyword dictionary obtained. For a given keyword i, <math>TF_{i,j}</math> is the number of times word i appears in document j divided by the total number of words in document j.<br />
<br />
The formula for TF has the following form:<br />
<br />
\[TF_{i,j} = \frac{n_{i,j} }{\sum_k n_{k,j} }\]<br />
<br />
where i stands for the <math>i^{th}</math> word, j stands for the <math>j^{th}</math> document, <math>n_{i,j}</math> stands for the number of times words <math>t_i</math> appear in document <math>d_j</math> and <math>\sum_k n_{k,j} </math> stands for total number of occurence of words in document <math>d_j</math>.<br />
<br />
Note that the denominator is the total number of words remaining in document j after crawling.<br />
<br />
===Document Frequency (DF)===<br />
<br />
DF evaluates the percentage of documents that contain a given word over the entire collection of documents. Thus, the higher DF value is, the less important the word is.<br />
<br />
<math>DF_{i}</math> is the number of documents in the collection with word i divided by the total number of documents in the collection. The formula for DF has the following form:<br />
<br />
\[DF_{i} = \frac{|d_k \in D: n_{i,k} > 0|}{|D|}\]<br />
<br />
where <math>n_{i,k}</math> is the number of times word i appears in document k, |D| is the total number of documents in the collection.<br />
<br />
Since DF and the importance of the word have an inverse relation, we use inverse document frequency (IDF) instead of DF.<br />
<br />
===Inverse Document Frequency (IDF)===<br />
<br />
In this paper, IDF is calculated in a log scale. Since we will receive a large number of documents, i.e, we will have a large |D|<br />
<br />
The formula for IDF has the following form:<br />
<br />
\[IDF_{i} = log\left(\frac{|D|}{|\{d_k \in D: n_{i,k} > 0\}|}\right)\]<br />
<br />
As mentioned before, we will use HDFS. The actual formula applied is:<br />
<br />
\[IDF_{i} = log\left(\frac{|D|+1}{|\{d_k \in D: n_{i,k} > 0\}|+1}\right)\]<br />
<br />
The inverse document frequency gives a measure of how rare a certain term is in a given document corpus.<br />
<br />
=Paper Classification Using K-means Clustering=<br />
<br />
K-means clustering is an unsupervised classification algorithm that groups similar data into the same class. It is an efficient and simple method that can be applied to different types of data attributes. It is also flexible enough to handle various kinds of noise and outliers.<br />
<br><br />
<br />
Given a set of <math>d</math> by <math>n</math> dataset <math>\mathbf{X} = \left[ \mathbf{x}_1 \cdots \mathbf{x}_n \right]</math>, the algorithm will assign each <math>\mathbf{x}_j</math> into <math>k</math> different clusters based on the characteristics of <math>\mathbf{x}_j</math> itself.<br />
<br><br />
<br />
Moreover, when assigning data into a cluster, the algorithm will also try to minimise the distances between the data and the centre of the cluster which the data belongs to. That is, k-means clustering will minimize the sum of square error:<br />
<br />
\begin{align*}<br />
min \sum_{i=1}^{k} \sum_{j \in C_i} ||x_j - \mu_i||^2<br />
\end{align*}<br />
<br />
where<br />
<ul><br />
<li><math>k</math>: the number of clusters</li><br />
<li><math>C_i</math>: the <math>i^th</math> cluster</li><br />
<li><math>x_j</math>: the <math>j^th</math> data in the <math>C_i</math></li><br />
<li><math>mu_i</math>: the centroid of <math>C_i</math></li><br />
<li><math>||x_j - \mu_i||^2</math>: the Euclidean distance between <math>x_j</math> and <math>\mu_i</math></li><br />
</ul><br />
<br><br />
<br />
K-means Clustering algorithm, an unsupervised algorithm, is chosen because of its advantages to deal with different types of attributes, to run with minimal requirement of domain knowledge, to deal with noise and outliers, to realize clusters with similarities. <br />
<br />
<br />
Since the goal for this paper is to classify research papers and group papers with similar topics based on keywords, the paper uses the K-means clustering algorithm. The algorithm first computes the cluster centroid for each group of papers with a specific topic. Then, it will assign a paper into a cluster based on the Euclidean distance between the cluster centroid and the paper’s TF-IDF value.<br />
<br><br />
<br />
However, different values of <math>k</math> (the number of clusters) will return different clustering results. Therefore, it is important to define the number of clusters before clustering. For example, in this paper, the authors choose to use the Elbow scheme to determine the value of <math>k</math>. The Elbow scheme is a somewhat subjective way of choosing an optimal <math>k</math> that involves plotting the average of the squared distances from the cluster centers of the respective clusters (distortion) as a function of <math>k</math> and choosing a <math>k</math> at which point the decrease in distortion is outweighed by the increase in complexity. Also, to measure the performance of clustering, the authors decide to use the Silhouette scheme. The Silhouette scheme is a measure of how well the objects lie within each cluster. Silhouette scores lie from -1 to 1. A positive score indicates that the object is well-matched with its own cluster, while a negative score indicates the opposite (Kaufman & Rousseeuw, 2005). The results of clustering are validated if the Silhouette scheme returns a value greater than <math>0.5</math>.<br />
<br />
=System Testing Results=<br />
<br />
In this paper, the dataset has 3264 research papers from the Future Generation Computer System (FGCS) journal between 1984 and 2017. For constructing keyword dictionaries for each paper, the authors have introduced three methods as shown below:<br />
<br />
<div align="center">[[File:table_3_tmtckd.JPG|700px]]</div><br />
<br />
<br />
Then, the authors use the Elbow scheme to define the number of clusters for each method with different numbers of keywords before running the K-means clustering algorithm. The results are shown below:<br />
<br />
<div align="center">[[File:table_4_nocobes.JPG|700px]]</div><br />
<br />
According to Table 4, there is a positive correlation between the number of keywords and the number of clusters. In addition, method 3 combines the advantages for both method 1 and method 2; thus, method 3 requires the least clusters in total. On the other hand, the wrong keywords might be presented in papers; hence, it might not be possible to group papers with similar subjects correctly by using method 1 and so method 1 needs the most number of clusters in total.<br />
<br />
<br />
Next, the Silhouette scheme had been used for measuring the performance for clustering. The average of the Silhouette values for each method with different numbers of keywords are shown below:<br />
<br />
<div align="center">[[File:table_5_asv.JPG|700px]]</div><br />
<br />
Since the clustering is validated if the Silhouette’s value is greater than 0.5, for methods with 10 and 30 keywords, the K-means clustering algorithm produces good results.<br />
<br />
<br />
To evaluate the accuracy of the classification system in this paper, the authors use the F-Score. The authors execute 5 times of experiment and use 500 randomly selected research papers for each trial. The following histogram shows the average value of F-Score for the three methods and different numbers of keywords:<br />
<br />
<div align="center">[[File:fig_16_fsvotm.JPG|700px]]</div><br />
<br />
Note that “TFIDF” means method 1, “LDA” means method 2, and “TFIDF-LDA” means method 3. The number 10, 20, and 30 after each method is the number of keywords the method has used.<br />
According to the histogram above, method 3 has the highest F-Score values than the other two methods with different numbers of keywords. Therefore, the classification system is most accurate when using method 3 as it combines the advantages for both method 1 and method 2.<br />
<br />
=Conclusion=<br />
<br />
This paper introduces a classification system that classifies research papers into different topics by using TF-IDF and LDA scheme with K-means clustering algorithm. The experimental results showed that the proposed system can classify the papers with similar subjects according to the keywords extracted from the abstracts of papers. In particular, when a keyword dictionary with both of the keywords extracted from the abstracts and the topics extracted by LDA scheme is used, the classification system has a better clustering performance and higher F-Score values. The authors emphasized that the system can be implemented efficiently on high performance computing infrastructure, using industry-standard technologies. This system allows users to search the papers they want quickly and with the most productivity.<br />
<br />
Furthermore, this classification system might be also used in different types of texts (e.g. documents, tweets, etc.) instead of only classifying research papers.<br />
<br />
=Critique=<br />
<br />
In this paper, DF values are calculated within each partition. This results that for each partition, DF value for a given word will vary and may have an inconsistent result for different partition methods. As mentioned above, there might be a divide by zero problem since some partitions do not have documents containing a given word, but this can be solved by introducing a dummy document as the authors did. Another method that might be better at solving inconsistent results and the divide by zero problems is to have all partitions to communicate with their DF value. Then pass the merged DF value to all partitions to do the final IDF and TF-IDF value. Having all partitions to communicate with the DF value will guarantee a consistent DF value across all partitions and helps avoid a divide by zero problem as words in the keyword dictionary must appear in some documents in the whole collection.<br />
<br />
This paper treated the words in the different parts of a document equivalently, it might perform better if it gives different weights to the same word in different parts. For example, if a word appears in the title of the document, it usually shows it's a main topic of this document so we can put more weight on it to categorize.<br />
<br />
When discussing the potential processing advantages of this classification system for other types of text samples, has the effect of processing mixed samples (text and image or text and video) taken into consideration? IF not, in terms of text classification only, does it have an overwhelming advantage over traditional classification models?<br />
<br />
The preprocessing should also include <math>n</math>-gram tokenization for topic modelling because some topics are inherently two words, such as machine learning where if it is seen separately, it implies different topics.<br />
<br />
This system is very compute-intensive due to the large volumes of dictionaries that can be generated by processing large volumes of data. It would be nice to see how much data HDFS had to process and similarly how much time was saved by using Hadoop for data processing as opposed to centralized approach.<br />
<br />
This system can be improved further in terms of computation times by utilizing other big data framework MapReduce, that can also use HDFS, by parallelizing their computation across multiple nodes for K-means clustering as discussed in (Jin, et al) [5].<br />
<br />
It's not exactly clear what method 3 (TFIDF-LDA) is doing, how is it performing TF-IDF on the topics? Also it seems like the preprocessing step only keeps 10/20/30 top words? This seems like an extremely low number especially in comparison with the LDA which has 10/20/30 topics - what is the reason for so strongly limiting the number of words? It would also be interesting to see if both key words and topics are necessary - an ablation study showing the significance of both would be interesting.<br />
<br />
It is better if the paper has an example with some topics on some research papers. Also it is better if we can visualize the distance between each research paper and the topic names<br />
<br />
I am interested in the first step of the general framework, which is the Paper Crawling step. Many conferences actually require the authors to indicate several key words that best describe a paper. For example, a database paper may have keywords such as "large-scale database management", "information retrieval", and "relational table mining". So in addition to crawling text from abstract, it may be more effective to crawl these keywords directly. Not only does this require less time, these keywords may also lead to better performance than the nouns extracted from the abstract section. I am also slightly concerned about the claim made in the paper that "Our methodologies can be applied to text outside of research papers". Research papers are usually carefully revised and well-structured. Extending the algorithm described in the paper to any kind of free-text could be difficult in practice.<br />
<br />
The paper has very meaningful motivation, since the association of research topics and finding all the relevant previous work is indeed a challenging task at the initials stage of the research. It is often easy to miss a relevant paper published years ago which might be crucial to your own work. However, the classification task that the author tested in this work is almost useless, as the classification is too high-level. The overall scheme of classifying paper between categories like "cloud bigdata" or "IoT privacy" is too general to be meaningful. It is simply classifying the primary field computer science into its direct subfield, while most researchers only work on a niche much narrower than the subfield. Most online paper database, including arxiv, takes care of the subfield and even subsubfield classifcation during the stage of submission, which leaves the author's system with limited applicabilty. What we truly need is an algorithm able to classify and cluster papers based on detailed research topics and methodology. <br />
<br />
It would be better if the author could provide some application or example of the research algorithm in the real world. It would be helpful for the readers to understand the algorithm.<br />
<br />
The summary clearly goes through the model framework well, starting from data-preprocessing, prediction, and testing. It can be enhanced by applying this model to other similar use-cases and how well the prediction goes.<br />
<br />
It will be better if their is a comparison on the BM25 algorithm v.s. TF-IDF, which is usually get compared in IR papers<br />
<br />
The paper misses the details on subjects of research papers used to perform classifications. If the majority of research papers were about one subject, it could potentially produce biased results.<br />
<br />
The paper omits the details of the reason why Method 3 for constructing the Keyword dictionaries requires the least number of k-clusters as method 3 is a combination of methods 1 and 2. It would be of interest to investigate why Method 3 uses so little clusters (in comparison) as it seemed to be the most accurate of the 3 methods. (Also the graph comparing the results could be improved by using a variety of different hues of colours as it is difficult to distinguish some scores such as TFIDF_30 and TFIDF-LDA_30)<br />
<br />
The TF-IDF is interesting as it provides a normalized method to extract the most frequent term contained in the paper, while this method still has spaces of improvements. For example, in some machine learning papers, where special operations have to be done on the datasets, the name of dataset may appear multiple times within the paper. In fact, the main theme of the paper is on the novel machine learning algorithm, which may only be mentioned once. In that case, mis-predictions may occur, and a possible improvement here is to add weights to keywords appearing in each section. i.e the most frequent word in Abstract will have more weights than the most frequent word in Introduction.<br />
<br />
In my opinion, the paper glosses over a few technicalities. First, how does the proposed algorithm deal with subgroups and nested groups. The paper is assuming only one level of sorting, which may work for a sufficiently unique set of paper, but since the problem is meant to be generalized, many papers will have to have multi-level sorts. For example, the category 'machine learning' can be further divided into 'supervised' and 'unsupervised'. Is the algorithm able to handle this or would it create 2 groups (i.e. ML-supervised and ML-unsupervised)? Second, a popular LDA model is available through the gensim package which utilizes relevancy and saliency metrics - how does that factor into the quality of the topics? Third, what is the motivation in using TF-IDF scores for clustering? In my experience, using Word2Vec and BERT has been the industry standard for obtaining vectors to perform clustering on text.<br />
<br />
When working with a larger data set, Spark might be more efficient than Hadoop. Working with natural language, the preprocessing is very important which might significantly determine the accuracy of the results. Therefore, different preprocessing techniques should be used to have a comparison. Lastly, PCA T-SNE might be a good way to visualize the result data.<br />
<br />
=References=<br />
<br />
[1] Blei DM, el. (2003). Latent Dirichlet allocation. J Mach Learn Res 3:993–1022<br />
<br />
[2] Gil, JM, Kim, SW. (2019). Research paper classification systems based on TF-IDF and LDA schemes. ''Human-centric Computing and Information Sciences'', 9, 30. https://doi.org/10.1186/s13673-019-0192-7<br />
<br />
[3] Liu, S. (2019, January 11). Dirichlet distribution Motivating LDA. Retrieved November 2020, from https://towardsdatascience.com/dirichlet-distribution-a82ab942a879<br />
<br />
[4] Serrano, L. (Director). (2020, March 18). Latent Dirichlet Allocation (Part 1 of 2) [Video file]. Retrieved 2020, from https://www.youtube.com/watch?v=T05t-SqKArY<br />
<br />
[5] Jin, Cui, Yu. (2016). A New Parallelization Method for K-means. https://arxiv.org/ftp/arxiv/papers/1608/1608.06347.pdf<br />
<br />
[6] Kaufman, L., & Rousseeuw, P. J. (2005). Graphical Output Concerning Each Clustering. In Finding groups in data : An introduction to cluster analysis (pp. 84-85). Hoboken, New Jersey: John Wiley & Sons. doi:10.1002/9780470316801</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Improving_neural_networks_by_preventing_co-adaption_of_feature_detectors&diff=49752Improving neural networks by preventing co-adaption of feature detectors2020-12-07T05:35:51Z<p>J244yang: /* Pre-training and Training */</p>
<hr />
<div>== Presented by ==<br />
Stan Lee, Seokho Lim, Kyle Jung, Dae Hyun Kim<br />
<br />
= Improvement Intro =<br />
'''Drop Out Model'''<br />
<br />
In this paper, Hinton et al. introduce a novel way to improve neural networks’ performance, particularly in the case that a large feedforward neural network is trained on a small training set, which causes poor performance and leads to an “overfitting” problem. This problem can be reduced by randomly omitting half of the feature detectors on each training case. In fact, By omitting neurons in hidden layers with a probability of 0.5, each hidden unit is prevented from relying on other hidden units being present during training. Hence there are fewer co-adaptations among them on the training data. Called “dropout,” this process is also an efficient alternative to train many separate networks and average their predictions on the test set. <br />
<br />
The intuition for dropout is that if neurons are randomly dropped during training, they can no longer rely on their neighbours, thus allowing each neuron to become more robust. Another interpretation is that dropout is similar to training an ensemble of models since each epoch with randomly dropped neurons can be viewed as its own model. <br />
<br />
They used the standard, stochastic gradient descent algorithm and separated training data into mini-batches. An upper bound was set on the L2 norm of incoming weight vector for each hidden neuron, which was normalized if its size exceeds the bound. They found that using a constraint, instead of a penalty, forced the model to do a more thorough search of the weight-space, when coupled with the very large learning rate that decays during training.<br />
<br />
'''Mean Network'''<br />
<br />
Their dropout models included all of the hidden neurons, and their outgoing weights were halved to account for the chances of omission. This is called a 'Mean Network'. This is similar to taking the geometric mean of the probability distribution predicted by all <math>2^N</math> networks. Due to this cumulative addition, the correct answers will have a higher log probability than an individual dropout network, which also leads to a lower squared error of the network. <br />
<br />
<br />
The models were shown to result in lower test error rates on several datasets: MNIST; TIMIT; Reuters Corpus Volume; CIFAR-10; and ImageNet.<br />
<br />
= MNIST =<br />
The MNIST dataset contains 70,000 digit images of size 28 x 28. To see the impact of dropout, they used 4 different neural networks (784-800-800-10, 784-1200-1200-10, 784-2000-2000-10, 784-1200-1200-1200-10), with the same dropout rates, 50%, for hidden neurons and 20% for visible neurons. Stochastic gradient descent was used with mini-batches of size 100 and a cross-entropy objective function as the loss function. Weights were updated after each minibatch, and training was done for 3000 epochs. An exponentially decaying learning rate <math>\epsilon</math> was used, with the initial value set as 10.0, and it was multiplied by the decaying factor <math>f</math> = 0.998 at the end of each epoch. At each hidden layer, the incoming weight vector for each hidden neuron was set an upper bound of its length, <math>l</math>, and they found from cross-validation that the results were the best when <math>l</math> = 15. Initial weights values were pooled from a normal distribution with mean 0 and standard deviation of 0.01. To update weights, an additional variable, ''p'', called momentum, was used to accelerate learning. The initial value of <math>p</math> was 0.5, and it increased linearly to the final value 0.99 during the first 500 epochs, remaining unchanged after. Also, when updating weights, the learning rate was multiplied by <math>1 – p</math>. <math>L</math> denotes the gradient of loss function.<br />
<br />
[[File:weights_mnist2.png|center|400px]]<br />
<br />
The best-published result for a standard feedforward neural network was 160 errors. This was reduced to about 130 errors with 0.5 dropout and different L2 constraints for each hidden unit input weight. By omitting a random 20% of the input pixels in addition to the aforementioned changes, the number of errors was further reduced to 110. The following figure visualizes the result.<br />
[[File:mnist_figure.png|center|500px]]<br />
A publicly available pre-trained deep belief net resulted in 118 errors, and it was reduced to 92 errors when the model was fine-tuned with dropout. Another publicly available model was a deep Boltzmann machine, and it resulted in 103, 97, 94, 93 and 88 when the model was fine-tuned using standard backpropagation and was unrolled. They were reduced to 83, 79, 78, 78, and 77 when the model was fine-tuned with dropout – the mean of 79 errors was a record for models that do not use prior knowledge or enhanced training sets.<br />
<br />
= TIMIT = <br />
<br />
TIMIT dataset includes voice samples of 630 American English speakers varying across 8 different dialects. It is often used to evaluate the performance of automatic speech recognition systems. Using Kaldi, the dataset was pre-processed to extract input features in the form of log filter bank responses.<br />
<br />
=== Pre-training and Training ===<br />
<br />
For pretraining, they pre-trained their neural network with a deep belief network and the first layer was built using Restricted Boltzmann Machine (RBM) which is a generative stochastic artificial neural network that can learn a probability distribution over its set of inputs. Initializing visible biases with zero, weights were sampled from random numbers that followed normal distribution <math>N(0, 0.01)</math>. Each visible neuron’s variance was set to 1.0 and remained unchanged.<br />
<br />
Minimizing Contrastive Divergence (CD) was used to facilitate learning. Since momentum is used to speed up learning, it was initially set to 0.5 and increased linearly to 0.9 over 20 epochs. The average gradient had 0.001 of a learning rate which was then multiplied by <math>(1-momentum)</math> and L2 weight decay was set to 0.001. After setting up the hyperparameters, the model was done training after 100 epochs. Binary RBMs were used for training all subsequent layers with a learning rate of 0.01. Then, <math>p</math> was set as the mean activation of a neuron in the data set and the visible bias of each neuron was initialized to <math>log(p/(1 − p))</math>. Training each layer with 50 epochs, all remaining hyper-parameters were the same as those for the Gaussian RBM.<br />
<br />
=== Dropout tuning ===<br />
<br />
The initial weights were set in a neural network from the pre-trained RBMs. To finetune the network with dropout-backpropagation, momentum was initially set to 0.5 and increased linearly up to 0.9 over 10 epochs. The model had a small constant learning rate of 1.0 and it was used to apply to the average gradient on a minibatch. The model also retained all other hyperparameters the same as the model from MNIST dropout finetuning. The model required approximately 200 epochs to converge. For comparison purposes, they also finetuned the same network with standard backpropagation with a learning rate of 0.1 with the same hyperparameters.<br />
<br />
=== Classification Test and Performance ===<br />
<br />
A Neural network was constructed to output the classification error rate on the test set of TIMIT dataset. They have built the neural network with four fully-connected hidden layers with 4000 neurons per layer. The output layer distinguishes distinct classes from 185 softmax output neurons that are merged into 39 classes. After constructing the neural network, 21 adjacent frames with an advance of 10ms per frame was given as an input.<br />
<br />
Comparing the performance of dropout with standard backpropagation on several network architectures and input representations, dropout consistently achieved lower error and cross-entropy. Results showed that it significantly controls overfitting, making the method robust to choices of network architecture. It also allowed much larger nets to be trained and removed the need for early stopping. Thus, neural network architectures with dropout are not very sensitive to the choice of learning rate and momentum.<br />
<br />
= Reuters Corpus Volume =<br />
Reuters Corpus Volume I archives 804,414 news documents that belong to 103 topics. Under four major themes - corporate/industrial, economics, government/social, and markets – they belonged to 63 classes. After removing 11 classes with no data and one class with insufficient data, they are left with 50 classes and 402,738 documents. The documents were divided into training and test sets equally and randomly, with each document representing the 2000 most frequent words in the dataset, excluding stopwords.<br />
<br />
They trained two neural networks, with size 2000-2000-1000-50, one using dropout and backpropagation, and the other using standard backpropagation. The training hyperparameters are the same as that in MNIST, but training was done for 500 epochs.<br />
<br />
In the following figure, we see the significant improvements by the model with dropout in the test set error. On the right side, we see that learning with dropout also proceeds smoother. <br />
<br />
[[File:reuters_figure.png|700px|center]]<br />
<br />
= CNN =<br />
<br />
Feed-forward neural networks consist of several layers of neurons where each neuron in a layer applies a linear filter to the input image data and is passed on to the neurons in the next layer. When calculating the neuron’s output, scalar bias a.k.a weights are applied to the filter with nonlinear activation function as parameters of the network that are learned by training data. [[File:cnnbigpicture.jpeg|thumb|upright=2|center|alt=text|Figure: Overview of Convolutional Neural Network]] There are several differences between Convolutional Neural networks and ordinary neural networks. The figure above gives a visual representation of a Convolutional Neural Network. First, CNN’s neurons are organized topographically into a bank and laid out on a 2D grid, so it reflects the organization of dimensions of the input data. Secondly, neurons in CNN apply filters which are local, and which are centered at the neuron’s location in the topographic organization. Meaning that useful metrics or clues to identify the object in an input image can be found by examining local neighborhoods of the image. Next, all neurons in a bank apply the same filter at different locations in the input image. When looking at the image example, green is input to one neuron bank, yellow is a filter bank, and pink is the output of one neuron bank (convolved feature). A bank of neurons in a CNN applies a convolution operation, aka filters, to its input where a single layer in a CNN typically has multiple banks of neurons, each performing a convolution with a different filter. The resulting neuron banks become distinct input channels into the next layer. The whole process reduces the net’s representational capacity but also reduces the capacity to overfit.<br />
[[File:bankofneurons.gif|thumb|upright=3|center|alt=text|Figure: Bank of neurons]]<br />
<br />
=== Pooling ===<br />
<br />
Pooling layer summarizes the activities of local patches of neurons in the convolutional layer by subsampling the output of a convolutional layer. Pooling is useful for extracting dominant features, to decrease the computational power required to process the data through dimensionality reduction. The procedure of pooling goes on like this; output from convolutional layers is divided into sections called pooling units and they are laid out topographically, connected to a local neighborhood of other pooling units from the same convolutional output. Then, each pooling unit is computed with some function which could be maximum and average. Maximum pooling returns the maximum value from the section of the image covered by the pooling unit while average pooling returns the average of all the values inside the pooling unit (see example). In the result, there are fewer total pooling units than convolutional unit outputs from the previous layer, this is due to the larger spacing between pixels on pooling layers. Using the max-pooling function reduces the effect of outliers and improves generalization. Other than that, overlapping pooling makes this spacing between pixels smaller than the size of the neighborhood that the pooling units summarize (This spacing is usually referred to as the stride between pooling units). With this variant, pooling layer can produce a coarse coding of the outputs which helps generalization. <br />
[[File:maxandavgpooling.jpeg|thumb|upright=2|center|alt=text|Figure: Max pooling and Average pooling]]<br />
<br />
=== Local Response Normalization === <br />
<br />
This network includes local response normalization layers which are implemented in lateral form and used on neurons with unbounded activations and permit the detection of high-frequency features with a big neuron response. This regularizer encourages competition among neurons belonging to different banks. Normalization is done by dividing the activity of a neuron in bank <math>i</math> at position <math>(x,y)</math> by the equation:<br />
[[File:local response norm.png|upright=2|center|]] where the sum runs over <math>N</math> ‘adjacent’ banks of neurons at the same position as in the topographic organization of neuron bank. The constants, <math>N</math>, <math>alpha</math> and <math>betas</math> are hyper-parameters whose values are determined using a validation set. This technique is replaced by better techniques such as the combination of dropout and regularization methods (<math>L1</math> and <math>L2</math>)<br />
<br />
=== Neuron nonlinearities ===<br />
<br />
All of the neurons for this model use the max-with-zero nonlinearity where output within a neuron is computed as <math> a^{i}_{x,y} = max(0, z^i_{x,y})</math> where <math> z^i_{x,y} </math> is the total input to the neuron. The reason they use nonlinearity is that it has several advantages over traditional saturating neuron models, such as a significant reduction in training time required to reach a certain error rate. Another advantage is that nonlinearity reduces the need for contrast-normalization and data pre-processing since neurons do not saturate- meaning activities simply scale up little by little with usually large input values. For this model’s only pre-processing step, they subtract the mean activity from each pixel and the result is a centered data.<br />
<br />
=== Objective function ===<br />
<br />
The objective function of their network maximizes the multinomial logistic regression objective which is the same as minimizing the average cross-entropy across training cases between the true label and the model’s predicted label.<br />
<br />
=== Weight Initialization === <br />
<br />
It’s important to note that if a neuron always receives a negative value during training, it will not learn because its output is uniformly zero under the max-with-zero nonlinearity. Hence, the weights in their model were sampled from a zero-mean normal distribution with a high enough variance. High variance in weights will set a certain number of neurons with positive values for learning to happen, and in practice, it’s necessary to try out several candidates for variances until a working initialization is found. In their experiment, setting a positive constant, or 1, as biases of the neurons in the hidden layers was helpful in finding it.<br />
<br />
=== Training ===<br />
<br />
In this model, a batch size of 128 samples and momentum of 0.9, we train our model using stochastic gradient descent. The update rule for weight <math>w</math> is $$ v_{i+1} = 0.9v_i + \epsilon <\frac{dE}{dw_i}> i$$ $$w_{i+1} = w_i + v_{i+1} $$ where <math>i</math> is the iteration index, <math>v</math> is a momentum variable, <math>\epsilon</math> is the learning rate and <math>\frac{dE}{dw}</math> is the average over the <math>i</math>th batch of the derivative of the objective with respect to <math>w_i</math>. The whole training process on CIFAR-10 takes roughly 90 minutes and ImageNet takes 4 days with dropout and two days without.<br />
<br />
=== Learning ===<br />
To determine the learning rate for the network, it is a must to start with an equal learning rate for each layer which produces the largest reduction in the objective function with the power of ten. Usually, it is in the order of <math>10^{-2}</math> or <math>10^{-3}</math>. In this case, they reduce the learning rate twice by a factor of ten before the termination of training.<br />
<br />
= CIFAR-10 =<br />
<br />
=== CIFAR-10 Dataset ===<br />
<br />
Removing incorrect labels, The CIFAR-10 dataset is a subset of the Tiny Images dataset with 10 classes. It contains 5000 training images and 1000 testing images for each class. The dataset has 32 x 32 color images searched from the web and the images are labeled with the noun used to search the image.<br />
<br />
[[File:CIFAR-10.png|thumb|upright=2|center|alt=text|Figure 4: CIFAR-10 Sample Dataset]]<br />
<br />
=== Models for CIFAR-10 ===<br />
<br />
Two models, one with dropout and one without dropout, were built to test the performance of dropout on CIFAR-10. All models have CNN with three convolutional layers each with a pooling layer. All of the pooling payers use a stride=2 and summarize a 3*3 neighborhood. The max-pooling method is performed by the pooling layer which follows the first convolutional layer, and the average-pooling method is performed by the remaining 2 pooling layers. The first and second pooling layers with <math>N = 9, α = 0.001</math>, and <math>β = 0.75</math> are followed by response normalization layers. A ten-unit softmax layer, which is used to output a probability distribution over class labels, is connected with the upper-most pooling layer. Using a filter size of 5×5, all convolutional layers have 64 filter banks.<br />
<br />
Additional changes were made with the model with dropout. The model with dropout enables us to use more parameters because dropout forces a strong regularization on the network. Thus, a fourth weight layer is added to take the input from the previous pooling layer. This fourth weight layer is locally connected, but not convolutional, and contains 16 banks of filters of size 3 × 3 with 50% dropout. Lastly, the softmax layer takes its input from this fourth weight layer.<br />
<br />
Thus, with a neural network with 3 convolutional hidden layers with 3 max-pooling layers, the classification error achieved 16.6% to beat 18.5% from the best-published error rate without using transformed data. The model with one additional locally-connected layer and dropout at the last hidden layer produced an error rate of 15.6%.<br />
<br />
= ImageNet =<br />
<br />
===ImageNet Dataset===<br />
<br />
ImageNet is a dataset of millions of high-resolution images, and they are labeled among 1000 different categories. The data were collected from the web and manually labeled using MTerk tool, which is a crowd-sourcing tool provided by Amazon.<br />
Because this dataset has millions of labeled images in thousands of categories, it is very difficult to have perfect accuracy on this dataset even for humans because the ImageNet images may contain multiple objects and there are a large number of object classes. ImageNet and CIFAR-10 are very similar, but the scale of ImageNet is about 20 times bigger (1,300,000 vs 60,000). The size of ImageNet is about 1.3 million training images, 50,000 validation images, and 150,000 testing images. They used resized images of 256 x 256 pixels for their experiments.<br />
<br />
'''An ambiguous example to classify:'''<br />
<br />
[[File:imagenet1.png|200px|center]]<br />
<br />
When this paper was written, the best score on this dataset was the error rate of 45.7% by High-dimensional signature compression for large-scale image classification (J. Sanchez, F. Perronnin, CVPR11 (2011)). The authors of this paper could achieve a comparable performance of 48.6% error rate using a single neural network with five convolutional hidden layers with a max-pooling layer in between, followed by two globally connected layers and a final 1000-way softmax layer. When applying 50% dropout to the 6th layer, the error rate was brought down to 42.4%.<br />
<br />
'''ImageNet Dataset:'''<br />
<br />
[[File:imagenet2.png|400px|center]]<br />
<br />
===Models for ImageNet===<br />
<br />
They mostly focused on the model with dropout because the one without dropout had a similar approach, but there was a serious issue with overfitting. They used a convolutional neural network trained by 224×224 patches randomly extracted from the 256 × 256 images. This could reduce the network’s capacity to overfit the training data and helped generalization as a form of data augmentation. The method of averaging the prediction of the net on ten 224 × 224 patches of the 256 × 256 input image was used for testing their model patched at the center, four corners, and their horizontal reflections. To maximize the performance on the validation set, this complicated network architecture was used and it was found that dropout was very effective. Also, it was demonstrated that using non-convolutional higher layers with the number of parameters worked well with dropout, but it had a negative impact on the performance without dropout.<br />
<br />
The network contains seven weight layers. The first five are convolutional, and the last two are globally-connected. Max-pooling layers follow the layer number 1,2, and 5. And then, the output of the last globally-connected layer was fed to a 1000-way softmax output layer. Using this architecture, the authors achieved an error rate of 48.6%. When applying 50% dropout to the 6th layer, the error rate was brought down to 42.4%.<br />
<br />
<br />
[[File:modelh2.png|700px|center]] <br />
<br />
[[File:layer2.png|600px|center]]<br />
<br />
Like the previous datasets, such as the MNIST, TIMIT, Reuters, and CIFAR-10, we also see a significant improvement for the ImageNet dataset. Including complicated architectures like this one, introducing dropout generalizes models better and gives lower test error rates.<br />
<br />
= Conclusion =<br />
<br />
The authors have shown a consistent improvement by the models trained with dropout in classifying objects in the following datasets: MNIST; TIMIT; Reuters Corpus Volume I; CIFAR-10; and ImageNet.<br />
<br />
The authors comment on a theory that sexual reproduction limits biological function to a small number of coadapted genes. The idea is that a given organism is unlikely to receive many coordinated genes from a parent, so will likely die if it relies on many genes to perform a given task. This limits the number of genes required to perform a function, which is like a built-in evolutionary dropout.<br />
<br />
= Critiques =<br />
It is a very brilliant idea to dropout half of the neurons to reduce co-adaptations. It is mentioned that for fully connected layers, dropout in all hidden layers works better than dropout in only one hidden layer. There is another paper Dropout: A Simple Way to Prevent Neural Networks from<br />
Overfitting[https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf] gives a more detailed explanation.<br />
<br />
It will be interesting to see how this paper could be used to prevent the overfitting of LSTMs.<br />
<br />
This paper focused more on CV tasks, it will be interesting to have some discussion on NLP tasks<br />
<br />
Firstly, it is a very interesting topic of classification by the "dropout" CNN method(omitting neurons in hidden layers). If the author can briefly explain the advantages of this method in processing image data in theory, it will be easier for readers to understand. Also, how to deal with the overfitting issue would be valuable.<br />
<br />
The authors mention that they tried various dropout probabilities and that the majority of them improved the model's generalization performance, but that more extreme probabilities tended to be worse which is why a dropout rate of 50% was used in the paper. The authors further develop this point to mention that the method can be improved by adapting individual dropout probabilities of each hidden or input unit using validation tests. This would be an interesting area to further develop and explore, as using a hardcoded 50% dropout for all layers might not be the optimal choice for all CNN applications. It would have been interesting to see the results of their investigations of differing dropout rates.<br />
<br />
The authors don't explain that during training, at each layer that we apply dropout, the values must be scaled by 1/p where p is dropout rate - this way the expected value of the layers is the same in both train and test time. They may have considered another solution for this discrepancy at the time (it is an old paper) but it doesn't seem like any solution was presented here. <br />
<br />
Despite the advantages of using dropout to prevent overfitting and reducing errors in testing, the authors did not discuss much the effects on the length of training time. In another [https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf paper] published a few years later by the same authors, there was more discussion about this. It appears that dropout increases training time by 2-3 times compared to a standard NN with the same architecture, which is a drawback that might be worth mentioning.<br />
<br />
Dropout layers prevent overfitting by random dropout of a fraction of the neurons specified in each layer. In fact, the neurons to be dropped out in each layer are randomly selected. Therefore, it might be the case that some important features in the dropout layer are discarded, which leads to a sudden drop in performance. Although this barely happens, and CNN with dropout rates roughly 50% in each layer will lead to generally good performance, some future improvements are still possible if we are able to select dropout neurons cleverly.<br />
<br />
The article does a good job of analyzing the benefit of using the standard dropout method, but I think it would be beneficial to take a look at other dropout variants. For example, the paper may have benefited from looking at DropConnect which was introduced y L. Wan et al and is similar to dropout layers but it does not apply a dropout directly o the neurons but on the weights and the bias linking the neurons. Others that they also could have looked at were Standout, Pooling Drop and MaxDrop. Comparing various dropout methods I think would greatly add to the paper.<br />
<br />
The author analyzed the dropout method for addressing overfitting problems. The key idea is to randomly drop units from the neural network during training. This prevents units from co-adapting too much. In addition, it also fastens the speed of training models since there are fewer neurons, which is a good idea. <br />
<br />
Random dropping was indeed quite effective in the MNIST fashion classification challenge, however, it may pose a question if the problem has very few features to begin with.<br />
<br />
The authors mentioned that they used Momentum to speed up the training but didn't show the alternative and the speed of the alternative. This [https://link.springer.com/article/10.1007/s11042-019-08453-9 paper]conducts an empirical study of Dropout vs Batch Normalization as well as compares different optimizers (like SGD which uses momentum) for each technique. It is found that optimizers with momentum outperform adaptive optimizers but at a cost of significantly longer training times.<br />
<br />
Dropout is a very popular technique to improve accuracy by avoiding overfitting. It might be interesting to see how it compares to other techniques and how the combination of techniques works.<br />
<br />
Dropout is really popular, but its usefulness is oftentimes inversely proportional to the amount of data in the training data, making it less useful for many modern applications. This paper could talk a little more about alternate methods, such as data augmentation, or L1/L2 regularization, and present them as viable alternatives.<br />
<br />
== Other Work ==<br />
<br />
In modern training, dropout is not advised for convolutional neural networks because it does not have the effect, interpretation, impact on spatial feature maps as dense features. This is because features in CNNs are spatially correlated. There is an interesting paper on DropBlock [2], a dropout method that drops entire contiguous regions of features, which has been shown to be much more effective for CNNs.<br />
<br />
== Reference ==<br />
[1] N. Srivastave, "Dropout: a simple way to prevent neural networks from overfitting", The Journal of Machine Learning Research, Jan 2014.<br />
<br />
[2] Ghiasi, Golnaz and Lin, Tsung-Yi and Le, Quoc V. "DropBlock: A regularization method for convolutional networks". NeurIPS, 2018.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Point-of-Interest_Recommendation:_Exploiting_Self-Attentive_Autoencoders_with_Neighbor-Aware_Influence&diff=48304Point-of-Interest Recommendation: Exploiting Self-Attentive Autoencoders with Neighbor-Aware Influence2020-11-30T04:51:28Z<p>J244yang: /* Previous Work */</p>
<hr />
<div>== Presented by == <br />
Guanting(Tony) Pan, Zaiwei(Zara) Zhang, Haocheng(Beren) Chang<br />
<br />
== Introduction == <br />
With the development of mobile devices and location-acquisition technologies, accessing real-time location information is becoming easier and more efficient. Precisely because of this development, Location-based Social Networks (LBSNs) like Yelp and Foursquare have become an important part of human life. People can share their experiences in locations, such as restaurants and parks, on the Internet. These locations can be seen as a Point-of-Interest (POI) in software such as Maps on our phone. These large amounts of user-POI interaction data can be used to provide a service, which is called personalized POI recommendation, to give recommendations to users of a location they might be interested in. These large amounts of data can be used to train a model through Machine Learning methods(i.e., Classification, Clustering, etc.) to predict a POI that users might be interested in. The POI recommendation system still faces some challenging issues: (1) the difficulty of modeling complex user-POI interactions from sparse implicit feedback; (2) the difficulty of incorporating geographic background information. In order to meet these challenges, this paper will introduce a novel autoencoder-based model to learn non-linear user-POI relations, which is called SAE-NAD. SAE stands for the self-attentive encoder, while NAD stands for the neighbor-aware decoder. An autoencoder is an unsupervised learning technique that we implement in the neural network model for representation learning, meaning that our neural network will contain a "bottleneck" layer that produces a compressed knowledge representation of the original input. This method will utilize machine learning knowledge that we learned in this course.<br />
<br />
== Previous Work == <br />
<br />
In the previous works, the method is just equally treating users checked in POIs. The drawback of equally treating users checked in POIs is that valuable information about the similarity between users is not utilized, thus reducing the power of such recommenders. However, the SAE adaptively differentiates the user preference degrees in multiple aspects.<br />
<br />
Previous methods mainly used a process called collaborative filtering which can be divided into memory based methods and model based methods. Memory based methods predict a users preference based on a weighted average of similar users or POIs. Model based methods use user-POI data to build a model for generating recommendations. Both methods typically model user preferences linearly, which may be an oversimplification.<br />
<br />
There are some other personalized POI recommendation methods that can be used. Some famous software (e.g., Netflix) uses model-based methods that are built on matrix factorization (MF). For example, ranked based Geographical Factorization Method in [1] adopted weighted regularized MF to serve people on POI. Machine learning is popular in this area. POI recommendation is an important topic in the domain of recommender systems [4]. This paper also described related work in Personalized location recommendation and attention mechanism in the recommendation. The recent studies on location recommendation methods using historical data (check-ins, comments, etc.)<br />
<br />
== Motivation == <br />
This paper reviews encoder and decoder. A single hidden-layer autoencoder is an unsupervised neural network, which consists of two parts: an encoder and a decoder. The encoder has one activation function that maps the input data to the latent space. The decoder also has one activation function mapping the representations in the latent space to the reconstruction space. And here is the formula:<br />
<br />
[[File: formula.png|center]](Note: a is the activation function)<br />
<br />
The proposed method uses a two-layer neural network to compute the score matrix in the architecture of the SAE. The NAD adopts the RBF kernel to make checked-in POIs exert more influence on nearby unvisited POIs. To train this model, Network training is required.<br />
<br />
This paper will use the datasets in the real world, which are from Gowalla[2], Foursquare [3], and Yelp[3]. These datasets would be used to train by using the method introduced in this paper and compare the performance of SAE-NAD with other POI recommendation methods. Three groups of methods are used to compare with the proposed method, which are traditional MF methods for implicit feedback, Classical POI recommendation methods, and Deep learning-based methods. Specifically, the Deep learning-based methods contain a DeepAE which is a three-hidden-layer autoencoder with a weighted loss function, we can connect this to the material in this course.<br />
<br />
Autoencoders (AE), due to their ability to represent complex data, have become very useful in recommendation systems. The primary reason it is used is because with deep neural network and with non-linear activation function it effectively captures the non-linear and non-trivial relationships between users and POI's.<br />
<br />
== Methodology == <br />
<br />
=== Notations ===<br />
<br />
Here are the notations used in this paper. It will be helpful when trying to understand the structure and equations in the algorithm.<br />
[[File:notations.JPG|500px|x300px|center]]<br />
<br />
=== Structure ===<br />
<br />
The structure of the network in this paper includes a self-attentive encoder as the input layer(yellow), and a neighbor-aware decoder as the output layer(green).<br />
<br />
[[File:1.JPG|1200px|x600px]]<br />
<br />
=== Self-Attentive Encoder ===<br />
<br />
The self-attentive encoder is the input layer. It transfers the preference vector <math>x_u</math> to hidden representation <math>A_u</math> using weight matrix <math>W^1</math> and the activation function <math>softmax</math> and <math>tanh</math>. The 0's and 1's in <math>x_u</math> indicates whether the user has been to a certain POI. The weight matrix <math>W_a</math> assigns different weights on various features of POIs. <math>A_u</math> is the importance score matrix, where each column is a POI, and each row is the importance level of the <math>n</math> checked in POIs in one aspect.<br />
<br />
[[File:encoder.JPG|center]]<br />
<br />
<math>\mathbf{Z}_u^{(1)} = \mathbf{A}_u \cdot (\mathbf{W}^{(1)}[L_u])^\top</math> is the multiplication of the importance score matrix and the POI embeddings, and represents the user from <math>d_a</math> aspects. <math>\mathbf{Z}_u^{(1)}</math> is a <math>d_a \times H_1</math> matrix. The aggregation layer then combines multiple aspects that represent the user into one, so that it fits into the Neighbor-Aware decoder: <math>\mathbf{z}_u^{(1)} = a_t(\mathbf{Z}_u^{(1)\top}\mathbf{w}_t + \mathbf{b}_t)</math>.<br />
<br />
=== Neighbor-Aware Decoder ===<br />
<br />
POI recommendation uses the geographical clustering phenomenon, which increases the weight of the unvisited POIs that surround the visited POIs. Also, an aggregation layer is added to the network to aggregate users’ representations from different aspects into one aspect. This means that a person who has visited a location is very likely to return to this location again in the future, so the user is recommended POIs surrounding this area. An example would be someone who has been to the UW plaza and bought Lazeez, is very likely to return to the plaza, therefore the person is recommended to try Mr. Panino's Beijing House.<br />
<br />
[[File:decoder.JPG|center]]<br />
<br />
=== Objective Function ===<br />
<br />
By minimizing the objective function, the partial derivatives with respect to all the parameters can be computed by gradient descent with backpropagation. After that, the training is complete.<br />
<br />
[[File:objective_function.JPG|center]]<br />
<br />
<br />
== Comparative analysis ==<br />
<br />
=== Metrics introduction ===<br />
To obtain a comprehensive evaluation of the effectiveness of the model, the authors performed a thorough comparison between the proposed model and the existing major POI recommendation methods. These methods can be further broken down into three categories: traditional matrix factorization methods for implicit feedback, classical POI recommendation methods, and deep learning-based methods. Here, three key evaluation metrics were introduced as Precison@k, Recall@k, and MAP@k. Through comparing all models on three datasets using the above metrics, it is concluded that the proposed model achieved the best performance.<br />
<br />
To better understand the comparison results, it is critical to understand the meanings behind each evaluation metric. Suppose the proposed model generated k recommended POIs for the user. The first metric, Precison@k, measures the percentage of the recommended POIs which the user has visited. Recall@k is also associated with the user’s behavior. However, it will measure the percentage of recommended POIs in all POIs which have been visited by the user. Lastly, MAP@k represents the mean average precision at k, where average precision is the average of precision values at all k ranks, where relevant POIs are found. They are formally defined as follows, <br />
$$ Recall@k=\frac{1}{M} \sum_{i=1}^M \frac{S_i(k) \cap T_i}{|T_i|} \\<br />
Precision@k = \frac{1}{M} \sum_{i=1}^M \frac{S_i(k) \cap T_i}{k} \\<br />
MAP@k = \frac{1}{M} \sum_{i=1}^M \frac{\sum_{j=1}^k p(j) \times rel(j)}{|T_i|} \\$$<br />
<br />
where <math>S_i(k) </math> us a set of top- <math>k </math> unvisited locations recommended to user <math> i </math> excluding those locations in the training, and <math>T_i </math> is a set of locations that are visited by user <math> i</math> in the testing. <math> p(j)</math> is the precision of a cut-off rank list from 1 to <math> j</math>, and <math>rel(j) </math> is an indicator function that equals to 1 if the location is visited in the testing, otherwise equals to 0.<br />
<br />
=== Model Comparison ===<br />
Among all models in the comparison group, RankGeoFM, IRNMF, and PACE produced the best results. Nonetheless, these models are still incomparable to our proposed model. The reasons are explained in details as follows:<br />
<br />
Both RankGeoFM and IRNMF incorporate geographical influence into their ranking models, which is significant for generating POI recommendations. However, they are not capable of capturing non-linear interactions between users and POIs. In comparison, the proposed model, while incorporating geographical influence, adopts a deep neural structure which enables it to measure non-linear and complex interactions. As a result, it outperforms the two methods in the comparison group.<br />
<br />
Moreover, compared to PACE, which is a deep learning-based method, the proposed model offers a more precise measurement of geographical influence. Though PACE is able to capture complex interactions, it models the geographical influence by a context graph, which fails to incorporate user reachability into the modeling process. In contrast, the proposed model is able to capture geographical influence directly through its neighbor-aware decoder, which allows it to achieve better performance than the PACE model.<br />
<br />
[[File:model_comparison.JPG|center]]<br />
<br />
== Conclusion ==<br />
In summary, the proposed model, namely SAE-NAD, clearly showed its advantages compared to many state-of-the-art baseline methods. Its self-attentive encoder effectively discriminates user preferences on check-in POIs, and its neighbor-aware decoder measures geographical influence precisely through differentiating user reachability on unvisited POIs. By leveraging these two components together, it can generate recommendations that are highly relevant to its users.<br />
<br />
== Critiques ==<br />
Besides developing the model and conducting a detailed analysis, the authors also did very well in constructing this paper. The paper is well-written and has a highly logical structure. Definitions, notations, and metrics are introduced and explained clearly, which enables readers to follow through the analysis easily. Last but not least, both the abstract and the conclusion of this paper are strong. The abstract concisely reported the objectives and outcomes of the experiment, whereas the conclusion is succinct and precise.<br />
<br />
This idea would have many applications, such as suggesting new restaurants to customers in the food delivery service app. Would the improvement in accuracy outweigh the increased complexity of the model when it comes to use in industry?<br />
<br />
It would be nice if the authours could describe the extensive experiments on the real-world datasets, with different baseline methods and evaluation metrics, to demonstrate the effectiveness of the proposed model. Moreover, show the comparison result in tables vs other methodologies, both in terms of accuracy and time-efficiency. In addition, the drawbacks of this new methodology are unknown to the readers. In other words, how does this compare to the already established recommendation systems found in large scale applications utilize by companies like Netflix? Why use the proposed method over something simpler such as matrix factorization or collaborative filtering? <br />
<br />
It would also be nice if the authors provided some more ablation on the various components of the proposed method. Even after reading some of their experiments, we do not have a clear understanding of how important each component is to the recommendation quality.<br />
<br />
It is recommended that the author present how the encoder and the decoder help in the process by comparing different models with or without encoder and decoder.<br />
<br />
It would have been better if the author included all figures to explain the sensitivity of parameters more elaborately. In the paper he only included plots showing effects on Gowalla and Foursquare datasets but not other datasets.<br />
<br />
Some additional explanations can be inserted in the Objective Function part. From the paper, we can find <math>\lambda</math> is the regularization parameter and <math>W_a</math> and <math>w_t</math> are the learned parameters in the attention layer and aggregation layer.<br />
<br />
It would be more attractive if there is a section to introduce the applications that based on such algorithm in daily life. For instance, which application we use nowadays is based on this algorithm and what are the advantages of it compared to other similar algorithm?<br />
<br />
It would be useful to the readers if the authors briefly described covariates with which they are using to predict POIs. All that is detailed in this paper is that geographical information is used. Taking note of the characteristics that the data set the proposed method deals with is important, especially as phones become capabable of collecting more and more kinds of data. That is to say, the information available for predicting POI's in the future may be different to the information available today, so it is important to describe the data. (The information could even decrease in the future if privacy laws are enacted).<br />
<br />
== References ==<br />
[1] Defu Lian, Cong Zhao, Xing Xie, Guangzhong Sun, Enhong Chen, and Yong Rui. 2014. GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation. In KDD. ACM, 831–840.<br />
<br />
[2] Eunjoon Cho, Seth A. Myers, and Jure Leskovec. 2011. Friendship and mobility: user movement in location-based social networks. In KDD. ACM, 1082–1090.<br />
<br />
[3] Yiding Liu, Tuan-Anh Pham, Gao Cong, and Quan Yuan. 2017. An Experimental Evaluation of Point-of-interest Recommendation in Location-based Social Networks. PVLDB 10, 10 (2017), 1010–1021.<br />
<br />
[4] Jie Bao, Yu Zheng, David Wilkie, and Mohamed F. Mokbel. 2015. Recommendations in location-based social networks: a survey. GeoInformatica 19, 3 (2015), 525–565.<br />
<br />
[5] Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural Collaborative Filtering. In WWW. ACM, 173–182.<br />
<br />
[6] Yifan Hu, Yehuda Koren, and Chris Volinsky. 2008. Collaborative Filtering for Implicit Feedback Datasets. In ICDM. IEEE Computer Society, 263–272.<br />
<br />
[7] Santosh Kabbur, Xia Ning, and George Karypis. 2013. FISM: factored item similarity models for top-N recommender systems. In KDD. ACM, 659–667. [12] Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. CoRR abs/1412.6980 (2014).<br />
<br />
[8] Yong Liu,WeiWei, Aixin Sun, and Chunyan Miao. 2014. Exploiting Geographical<br />
Neighborhood Characteristics for Location Recommendation. In CIKM. ACM,<br />
739–748<br />
<br />
[9] Xutao Li, Gao Cong, Xiaoli Li, Tuan-Anh Nguyen Pham, and Shonali Krishnaswamy.<br />
2015. Rank-GeoFM: A Ranking based Geographical Factorization<br />
Method for Point of Interest Recommendation. In SIGIR. ACM, 433–442.<br />
<br />
[10] Carl Yang, Lanxiao Bai, Chao Zhang, Quan Yuan, and Jiawei Han. 2017. Bridging<br />
Collaborative Filtering and Semi-Supervised Learning: A Neural Approach for<br />
POI Recommendation. In KDD. ACM, 1245–1254.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Semantic_Relation_Classification%E2%80%94%E2%80%94via_Convolution_Neural_Network&diff=48296Semantic Relation Classification——via Convolution Neural Network2020-11-30T04:42:31Z<p>J244yang: /* Introduction */</p>
<hr />
<div><br />
<br />
<br />
== Presented by ==<br />
Rui Gong, Xinqi Ling, Di Ma,Xuetong Wang<br />
<br />
== Introduction ==<br />
A Semantic Relation can imply a relation between different words and a relation between different sentences or phrases. For example, the pair of words "white" and "snowy" can be synonyms, while "white" and "black" can be opposites. It can be used for recommendation systems like YouTube, and understanding sentiment analysis. The study of semantic analysis involves determining the exact meaning of a text. For example, the word "date", can have different meanings in different contexts, like a calendar "date", a "date" fruit, or a romantic "date". <br />
<br />
One of the emerging trends of natural language technologies is their use for the humanities and sciences (Gbor et al., 2018). SemEval 2018 Task 7 mainly solves the problem of relation extraction and classification of two entities in the same sentence into 6 potential relations. The 6 relations are USAGE, RESULT, MODEL-FEATURE, PART WHOLE, TOPIC, and COMPARE.<br />
<br />
SemEval 2018 Task 7 extracted data from 350 scientific paper abstracts, which has 1228 and 1248 annotated sentences for two tasks, respectively. For each data, an example sentence was chosen with its right and left sentences, as well as an indicator showing whether the relation is reserved, then a prediction is made. <br />
<br />
Three models were used for the prediction: Linear Classifiers, Long Short-Term Memory(LSTM), and Convolutional Neural Networks (CNN). Linear Classifier achieves the goal of classification by making a classification decision based on the value of a linear combination of the characteristics. LSTM is an artificial recurrent neural network (RNN) architecture well suited to classifying, processing and making predictions based on time series data. In the end, the prediction based on the CNN model was ultimately submitted since it performed the best among all models. By using the learned custom word embedding function, the research team added a variant of negative sampling, thereby improving performance and surpassing ordinary CNN.<br />
<br />
== Previous Work ==<br />
SemEval 2010 Task 8 (Hendrickx et al., 2010) explored the classification of natural language relations and studied the 9 relations between word pairs. However, it is not designed for scientific text analysis, and their challenge differs from the challenge of this paper in its generalizability; this paper’s relations are specific to ACL papers (e.g. MODEL-FEATURE), whereas the 2010 relations are more general, and might necessitate more common-sense knowledge than the 2018 relations. Xu et al. (2015a) and Santos et al. (2015) both applied CNN with negative sampling to finish task7. The 2017 SemEval Task 10 also featured relation extraction within scientific publications.<br />
<br />
== Algorithm ==<br />
<br />
[[File:CNN.png|800px|center]]<br />
<br />
This is the architecture of CNN. We first transform a sentence via Feature embeddings. Word representations are encoded by the column vector in the embedding matrix <math> W^{word} \in \mathbb{R}^{d^w \times |V|}</math>, where <math>V</math> is the vocabulary of the dataset. Each colummn is the word embedding vector for the <math>i^{th}</math> word in the vocabulary. This matrix is trainale during the optimization process and initialized by pre-trained emmbedding vectors. Basically, we transform each sentence into continuous word embeddings:<br />
<br />
$$<br />
(e^{w_i})<br />
$$<br />
<br />
And word position embeddings:<br />
$$<br />
(e^{wp_i}): e_i = [e^{w_i}, e^{wp_i}]<br />
$$<br />
<br />
In the word embeddings, we generated a vocabulary <math> V </math>. We will then generate an embedding word matrix based on the position of the word in the vocabulary. This matrix is trainable and needs to be initialized by pre-trained embedding vectors such as through GloVe or Word2Vec.<br />
<br />
In the word position embeddings, we first need to input some words named ‘entities,’ and they are the key for the machine to determine the sentence’s relation. During this process, if we have two entities, we will use the relative position of them in the sentence to make the<br />
embeddings. We will output two vectors, and one of them keeps track of the first entity relative position in the sentence ( we will make the entity recorded as 0, the former word recorded as -1 and the next one 1, etc. ). And the same procedure for the second entity. Finally, we will get two vectors concatenated as the position embedding. For example, in the sentence "the black '''cat''' jumped", the position embedding of "'''cat'''" is -2,-1,0,1.<br />
<br />
<br />
<br />
After the embeddings, the model will transform the embedded sentence into a fix-sized representation of the whole sentence via the convolution layer. Finally, after the max-pooling to reduce the dimension of the output of the layers, we will get a score for each relation class via a linear transformation.<br />
<br />
<br />
After featurizing all words in the sentence. The sentence of length N can be expressed as a vector of length <math> N </math>, which looks like <br />
$$e=[e_{1},e_{2},\ldots,e_{N}]$$<br />
and each entry represents a token of the word. Also, to apply <br />
convolutional neural network, the subsets of features<br />
$$e_{i:i+j}=[e_{i},e_{i+1},\ldots,e_{i+j}]$$<br />
are given to a weight matrix <math> W\in\mathbb{R}^{(d^{w}+2d^{wp})\times k}</math> to <br />
produce a new feature, defiend as <br />
$$c_{i}=\text{tanh}(W\cdot e_{i:i+k-1}+bias)$$<br />
This process is applied to all subsets of features with length <math> k </math> starting <br />
from the first one. Then a mapped feature factor is produced:<br />
$$c=[c_{1},c_{2},\ldots,c_{N-k+1}]$$<br />
<br />
<br />
The max pooling operation is used, the <math> \hat{c}=max\{c\} </math> was picked.<br />
With different weight filter, different mapped feature vectors can be obtained. Finally, the original <br />
sentence <math> e </math> can be converted into a new representation <math> r_{x} </math> with a fixed length. For example, if there are 5 filters,<br />
then there are 5 features (<math> \hat{c} </math>) picked to create <math> r_{x} </math> for each <math> x </math>.<br />
<br />
Then, the score vector <br />
$$s(x)=W^{classes}r_{x}$$<br />
is obtained which represented the score for each class, given <math> x </math>'s entities' relation will be classified as <br />
the one with the highest score. The <math> W^{classes} </math> here is the model being trained.<br />
<br />
To improve the performance, “Negative Sampling" was used. Given the trained data point <br />
<math> \tilde{x} </math>, and its correct class <math> \tilde{y} </math>. Let <math> I=Y\setminus\{\tilde{y}\} </math> represent the <br />
incorrect labels for <math> x </math>. Basically, the distance between the correct score and the positive margin, and the negative <br />
distance (negative margin plus the second largest score) should be minimized. So the loss function is <br />
$$L=\log(1+e^{\gamma(m^{+}-s(x)_{y})})+\log(1+e^{\gamma(m^{-}-\mathtt{max}_{y'\in I}(s(x)_{y'}))})$$<br />
with margins <math> m_{+} </math>, <math> m_{-} </math>, and penalty scale factor <math> \gamma </math>.<br />
The whole training is based on ACL anthology corpus and there are 25,938 papers with 136,772,370 tokens in total, <br />
and 49,600 of them are unique.<br />
<br />
== Results ==<br />
In machine learning, the most important part is to tune the hyper-parameters. Unlike traditional hyper-parameter optimization, there are some<br />
modifications to the model to increase performance on the test set. There are 5 modifications that we can apply:<br />
<br />
'''1.''' Merged Training Sets. It combined two training sets to increase the data set<br />
size and it improves the equality between classes to get better predictions.<br />
<br />
'''2.''' Reversal Indicate Features. It added a binary feature.<br />
<br />
'''3.''' Custom ACL Embeddings. It embedded a word vector to an ACL-specific<br />
corps.<br />
<br />
'''4.''' Context words. Within the sentence, it varies in size on a context window<br />
around the entity-enclosed text.<br />
<br />
'''5.''' Ensembling. It used different early stop and random initializations to improve<br />
the predictions.<br />
<br />
These modifications performances well on the training data and they are shown<br />
in table 3.<br />
<br />
[[File:table3.PNG|center]]<br />
<br />
<br />
<br />
As we can see the best choice for this model is ensembling as the random initialization made the data more natural and avoided the overfit.<br />
During the training process, there are some methods such that they can only<br />
increase the score on the cross-validation test sets but hurt the performance on<br />
the overall macro-F1 score. Thus, these methods were eventually ruled out.<br />
<br />
<br />
[[File:table4.PNG|center]]<br />
<br />
There are six submissions in total. Three for each training set and the result<br />
is shown in figure 2.<br />
<br />
The best submission for the training set 1.1 is the third submission which does not<br />
use a separate cross-validation dataset. Instead, a constant number of<br />
training epochs are run with cross-validation based on the training data.<br />
<br />
This compares to the other submissions in which 10% of the training data are<br />
removed to form the validation set (both with and without stratification).<br />
Predictions for these are made when the model has the highest validation accuracy. <br />
<br />
The best submission for the training set 1.2 is the submission which<br />
extracted 10% of the training data to form the validation dataset. Predictions are<br />
made when maximum accuracy is reached on the validation data.<br />
<br />
All in all, early stopping cannot always be based on the accuracy of the validation set<br />
since it cannot guarantee to get better performance on the real test set. Thus,<br />
we have to try new approaches and combine them to see the prediction<br />
results. Also, doing stratification will certainly improve the performance of<br />
the test data.<br />
<br />
== Conclusions ==<br />
Throughout the process, we have experimented with linear classifiers, sequential random forest, LSTM, and CNN models with various variations applied, such as two models of attention, negative sampling, entity embedding or sentence-only embedding, etc. <br />
<br />
Among all variations, vanilla CNN with negative sampling and ACL-embedding, without attention, has significantly better performance than all others. Attention-based pooling, up-sampling, and data augmentation are also tested, but they barely perform positive increment on the behavior.<br />
<br />
== Critiques == <br />
<br />
- Applying this in news apps might be beneficial to improve readability by highlighting specific important sections.<br />
<br />
- The data set come from 350 scientist papers, this could be more explained by the author on how those paper are selected and why those paper are important to discuss.<br />
<br />
- In the section of previous work, the author mentioned 9 natural language relationships between the word pairs. Among them, 6 potential relationships are USAGE, RESULT, MODEL-FEATURE, PART WHOLE, TOPIC, and COMPARE. It would help the readers to better understand if all 9 relationships are listed in the summary.<br />
<br />
-This topic is interesting and this application might be helpful for some educational websites to improve their website to help readers focus on the important points. I think it will be nice to use Latex to type the equation in the sentence rather than center the equation on the next line. I think it will be interesting to discuss applying this way to other languages such as Chinese, Japanese, etc.<br />
<br />
- It would be a good idea if the authors can provide more details regarding ACL Embeddings and Context words modifications. Scores generated using these two modifications are quite close to the highest Ensembling modification generated score, which makes it a valid consideration to examine these two modifications in detail. <br />
<br />
- This paper is dealing with a similar problem as 'Neural Speed Reading Via Skim-RNN', num 19 paper summary. It will be an interesting approach to compare these two models' performance based on the same dataset.<br />
<br />
- I think it would be highly practical to implement this system as a page-rank system for search engines (such as google, bing, or other platforms like Facebook, Instagram, etc.) by finding the most prevalent information available in a search query and then matching the search to the related text which can be found on webpages. This could also be implemented in search bars on specific websites or locations as well.<br />
<br />
- It would be interesting to see in the future how the model would behave if data not already trained was used. This pre-trained data as mentioned in the paper had noise included. Using cleaner data would give better results maybe.<br />
<br />
- The selection of the training dataset, i.e. the abstracts of scientific papers, is an excellent idea since the abstracts usually contain more information than the body. But it may be also a good idea to train the model with the conclusions. Other than that, the result of applying the model to the body part of the scientific papers may show some interesting features of the model.<br />
<br />
- From Table 4 we find that comparing with using a fixed number of training periods, early stopping based on the accuracy of the validation set does not guarantee better test set performance. The label ratio of the validation set is layered according to the training set, which helps to improve the performance of the test set. Whether it is beneficial to add entity embedding as an additional feature could be an interesting point of discussion.<br />
<br />
- The author mentioned the use of CNNs for contextual understanding. NLP models based on CNNs have sometimes been inadequate for the use of understanding the context of words used in a body of text, being very prone to overfitting the context of the training data. It would help if more evidence was shown as to how the paper deals with this problem.<br />
<br />
== References ==<br />
Diederik P Kingma and Jimmy Ba. 2014. Adam: A<br />
method for stochastic optimization. arXiv preprint<br />
arXiv:1412.6980.<br />
<br />
DragomirR. Radev, Pradeep Muthukrishnan, Vahed<br />
Qazvinian, and Amjad Abu-Jbara. 2013. The ACL<br />
anthology network corpus. Language Resources<br />
and Evaluation, pages 1–26.<br />
<br />
Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey<br />
Dean. 2013a. Efficient estimation of word<br />
representations in vector space. arXiv preprint<br />
arXiv:1301.3781.<br />
<br />
Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado,<br />
and Jeff Dean. 2013b. Distributed representations<br />
of words and phrases and their compositionality.<br />
In Advances in neural information processing<br />
systems, pages 3111–3119.<br />
<br />
Kata Gbor, Davide Buscaldi, Anne-Kathrin Schumann, Behrang QasemiZadeh, Hafa Zargayouna,<br />
and Thierry Charnois. 2018. Semeval-2018 task 7:Semantic relation extraction and classification in scientific papers. <br />
In Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval2018), New Orleans, LA, USA, June 2018.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=stat441F21&diff=48266stat441F212020-11-30T04:11:46Z<p>J244yang: /* Paper presentation */</p>
<hr />
<div><br />
<br />
== [[F20-STAT 441/841 CM 763-Proposal| Project Proposal ]] ==<br />
<br />
<!--[https://goo.gl/forms/apurag4dr9kSR76X2 Your feedback on presentations]--><br />
<br />
= Record your contributions here [https://docs.google.com/spreadsheets/d/10CHiJpAylR6kB9QLqN7lZHN79D9YEEW6CDTH27eAhbQ/edit?usp=sharing]=<br />
<br />
Use the following notations:<br />
<br />
P: You have written a summary/critique of the paper.<br />
<br />
T: You had a technical contribution on a paper (excluding the paper that you present).<br />
<br />
E: You had an editorial contribution on a paper (excluding the paper that you present).<br />
<br />
=Paper presentation=<br />
{| class="wikitable"<br />
<br />
{| border="1" cellpadding="3"<br />
|-<br />
|width="60pt"|Date<br />
|width="250pt"|Name <br />
|width="15pt"|Paper number <br />
|width="700pt"|Title<br />
|width="15pt"|Link to the paper<br />
|width="30pt"|Link to the summary<br />
|width="30pt"|Link to the video<br />
|-<br />
|Sep 15 (example)||Ri Wang || ||Sequence to sequence learning with neural networks.||[http://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Going_Deeper_with_Convolutions Summary] || [https://youtu.be/JWozRg_X-Vg?list=PLehuLRPyt1HzXDemu7K4ETcF0Ld_B5adG&t=539]<br />
|-<br />
|Week of Nov 16 ||Sharman Bharat, Li Dylan,Lu Leonie, Li Mingdao || 1|| Risk prediction in life insurance industry using supervised learning algorithms || [https://rdcu.be/b780J Paper] ||[https://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:Bsharman Summary] ||<br />
[https://www.youtube.com/watch?v=TVLpSFYgF0c&feature=youtu.be]<br />
|-<br />
|Week of Nov 16 || Delaney Smith, Mohammad Assem Mahmoud || 2|| Influenza Forecasting Framework based on Gaussian Processes || [https://proceedings.icml.cc/static/paper_files/icml/2020/1239-Paper.pdf Paper] ||[https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Influenza_Forecasting_Framework_based_on_Gaussian_Processes Summary]|| [https://www.youtube.com/watch?v=HZG9RAHhpXc&feature=youtu.be]<br />
|-<br />
|Week of Nov 16 || Tatianna Krikella, Swaleh Hussain, Grace Tompkins || 3|| Processing of Missing Data by Neural Networks || [http://papers.nips.cc/paper/7537-processing-of-missing-data-by-neural-networks.pdf Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:Gtompkin Summary] || [https://learn.uwaterloo.ca/d2l/ext/rp/577051/lti/framedlaunch/6ec1ebea-5547-46a2-9e4f-e3dc9d79fd54]<br />
|-<br />
|Week of Nov 16 ||Jonathan Chow, Nyle Dharani, Ildar Nasirov ||4 ||Streaming Bayesian Inference for Crowdsourced Classification ||[https://papers.nips.cc/paper/9439-streaming-bayesian-inference-for-crowdsourced-classification.pdf Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Streaming_Bayesian_Inference_for_Crowdsourced_Classification Summary] || [https://www.youtube.com/watch?v=UgVRzi9Ubws]<br />
|-<br />
|Week of Nov 16 || Matthew Hall, Johnathan Chalaturnyk || 5|| Neural Ordinary Differential Equations || [https://papers.nips.cc/paper/7892-neural-ordinary-differential-equations.pdf] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Neural_ODEs Summary]||<br />
|-<br />
|Week of Nov 16 || Luwen Chang, Qingyang Yu, Tao Kong, Tianrong Sun || 6|| Adversarial Attacks on Copyright Detection Systems || Paper [https://proceedings.icml.cc/static/paper_files/icml/2020/1894-Paper.pdf] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Adversarial_Attacks_on_Copyright_Detection_Systems Summary] || [https://www.youtube.com/watch?v=bQI9S6bCo8o]<br />
|-<br />
|Week of Nov 16 || Casey De Vera, Solaiman Jawad || 7|| IPBoost – Non-Convex Boosting via Integer Programming || [https://arxiv.org/pdf/2002.04679.pdf Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=IPBoost Summary] || [https://www.youtube.com/watch?v=4DhJDGC4pyI&feature=youtu.be]<br />
|-<br />
|Week of Nov 16 || Yuxin Wang, Evan Peters, Yifan Mou, Sangeeth Kalaichanthiran || 8|| What Game Are We Playing? End-to-end Learning in Normal and Extensive Form Games || [https://arxiv.org/pdf/1805.02777.pdf] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=what_game_are_we_playing Summary] || [https://www.youtube.com/watch?v=9qJoVxo3hnI&feature=youtu.be]<br />
|-<br />
|Week of Nov 16 || Yuchuan Wu || 9|| || || ||<br />
|-<br />
|Week of Nov 16 || Zhou Zeping, Siqi Li, Yuqin Fang, Fu Rao || 10|| A survey of neural network-based cancer prediction models from microarray data || [https://www.sciencedirect.com/science/article/pii/S0933365717305067 Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:Y93fang Summary] || [https://youtu.be/B8pPUU8ypO0]<br />
|-<br />
|Week of Nov 23 ||Jinjiang Lian, Jiawen Hou, Yisheng Zhu, Mingzhe Huang || 11|| DROCC: Deep Robust One-Class Classification || [https://proceedings.icml.cc/static/paper_files/icml/2020/6556-Paper.pdf paper] ||[https://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:J46hou Summary] || [https://www.youtube.com/watch?v=tvCEvvy54X8&ab_channel=JJLian]<br />
|-<br />
|Week of Nov 23 || Bushra Haque, Hayden Jones, Michael Leung, Cristian Mustatea || 12|| Combine Convolution with Recurrent Networks for Text Classification || [https://arxiv.org/pdf/2006.15795.pdf Paper] ||[https://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:Cvmustat Summary] || [https://www.youtube.com/watch?v=or5RTxDnZDo]<br />
|-<br />
|Week of Nov 23 || Taohao Wang, Zeren Shen, Zihao Guo, Rui Chen || 13|| Large Scale Landmark Recognition via Deep Metric Learning || [https://arxiv.org/pdf/1908.10192.pdf paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:T358wang Summary] || [https://www.youtube.com/watch?v=K9NypDNPLJo Video]<br />
|-<br />
|Week of Nov 23 || Qianlin Song, William Loh, Junyue Bai, Phoebe Choi || 14|| Task Understanding from Confusing Multi-task Data || [https://proceedings.icml.cc/static/paper_files/icml/2020/578-Paper.pdf Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Task_Understanding_from_Confusing_Multi-task_Data Summary] || [https://youtu.be/i_5PQdfuH-Y]<br />
|-<br />
|Week of Nov 23 || Rui Gong, Xuetong Wang, Xinqi Ling, Di Ma || 15|| Semantic Relation Classification via Convolution Neural Network|| [https://www.aclweb.org/anthology/S18-1127.pdf paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Semantic_Relation_Classification——via_Convolution_Neural_Network Summary]|| [https://www.youtube.com/watch?v=m9o3NuMUKkU&ab_channel=DiMa video]<br />
|-<br />
|Week of Nov 23 || Xiaolan Xu, Robin Wen, Yue Weng, Beizhen Chang || 16|| Graph Structure of Neural Networks || [https://proceedings.icml.cc/paper/2020/file/757b505cfd34c64c85ca5b5690ee5293-Paper.pdf Paper] ||[https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Graph_Structure_of_Neural_Networks Summary] || [https://youtu.be/x9eUgEwntcs Video]<br />
|-<br />
|Week of Nov 23 ||Hansa Halim, Sanjana Rajendra Naik, Samka Marfua, Shawrupa Proshasty || 17|| Superhuman AI for multiplayer poker || [https://www.cs.cmu.edu/~noamb/papers/19-Science-Superhuman.pdf Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Superhuman_AI_for_Multiplayer_Poker Summary]|| [https://www.youtube.com/watch?v=kazqcOwbtTI Video]<br />
|-<br />
|Week of Nov 23 ||Guanting Pan, Haocheng Chang, Zaiwei Zhang || 18|| Point-of-Interest Recommendation: Exploiting Self-Attentive Autoencoders with Neighbor-Aware Influence || [https://arxiv.org/pdf/1809.10770.pdf Paper] ||[https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Point-of-Interest_Recommendation:_Exploiting_Self-Attentive_Autoencoders_with_Neighbor-Aware_Influence Summary] || [https://www.youtube.com/watch?v=aAwjaos_Hus Video]<br />
|-<br />
|Week of Nov 23 || Jerry Huang, Daniel Jiang, Minyan Dai || 19|| Neural Speed Reading Via Skim-RNN ||[https://arxiv.org/pdf/1711.02085.pdf?fbclid=IwAR3EeFsKM_b5p9Ox7X9mH-1oI3U3oOKPBy3xUOBN0XvJa7QW2ZeJJ9ypQVo Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Neural_Speed_Reading_via_Skim-RNN Summary]|| [https://youtu.be/vOENmt9jgVE Video]<br />
|-<br />
|Week of Nov 23 ||Ruixian Chin, Yan Kai Tan, Jason Ong, Wen Cheen Chiew || 20|| DivideMix: Learning with Noisy Labels as Semi-supervised Learning || [https://openreview.net/pdf?id=HJgExaVtwr Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:Yktan Summary]|| [https://www.youtube.com/watch?v=48xYZXifjS0&ab_channel=SeakraChin]<br />
|-<br />
|Week of Nov 30 || Banno Dion, Battista Joseph, Kahn Solomon || 21|| Music Recommender System Based on Genre using Convolutional Recurrent Neural Networks || [https://www.sciencedirect.com/science/article/pii/S1877050919310646] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Music_Recommender_System_Based_using_CRNN#Evaluation_of_Music_Recommendation_System: Summary] || [https://youtu.be/eGUV3zwLwqQ]<br />
|-<br />
|Week of Nov 30 || Isaac Ellmen, Dorsa Mohammadrezaei, Emilee Carson || 22|| A universal SNP and small-indel variant caller using deep neural networks||[https://www.nature.com/articles/nbt.4235.epdf?author_access_token=q4ZmzqvvcGBqTuKyKgYrQ9RgN0jAjWel9jnR3ZoTv0NuM3saQzpZk8yexjfPUhdFj4zyaA4Yvq0LWBoCYQ4B9vqPuv8e2HHy4vShDgEs8YxI_hLs9ov6Y1f_4fyS7kGZ Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=A_universal_SNP_and_small-indel_variant_caller_using_deep_neural_networks Summary] ||<br />
|-<br />
|Week of Nov 30 || Daniel Fagan, Cooper Brooke, Maya Perelman || 23|| Efficient kNN Classification With Different Number of Nearest Neighbors || [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7898482 Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:Dfagan Summary]||<br />
|-<br />
|Week of Nov 30 || Karam Abuaisha, Evan Li, Jason Pu, Nicholas Vadivelu || 24|| Being Bayesian about Categorical Probability || [https://proceedings.icml.cc/static/paper_files/icml/2020/3560-Paper.pdf Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Being_Bayesian_about_Categorical_Probability Summary] || [https://drive.google.com/file/d/1I0uYF2xEMuNVtaEhPb_vZ6bxSKMi0gUh/view?usp=sharing]<br />
|-<br />
|Week of Nov 30 || Anas Mahdi Will Thibault Jan Lau Jiwon Yang || 25|| Loss Function Search for Face Recognition<br />
|| [https://proceedings.icml.cc/static/paper_files/icml/2020/245-Paper.pdf] paper || Summary [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Loss_Function_Search_for_Face_Recognition] || [https://youtu.be/i3dXnK9HGSQ]<br />
|-<br />
|Week of Nov 30 ||Zihui (Betty) Qin, Wenqi (Maggie) Zhao, Muyuan Yang, Amartya (Marty) Mukherjee || 26|| Deep Learning for Cardiologist-level Myocardial Infarction Detection in Electrocardiograms || [https://arxiv.org/pdf/1912.07618.pdf?fbclid=IwAR0RwATSn4CiT3qD9LuywYAbJVw8YB3nbex8Kl19OCExIa4jzWaUut3oVB0 Paper] || Summary [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Deep_Learning_for_Cardiologist-level_Myocardial_Infarction_Detection_in_Electrocardiograms&fbclid=IwAR1Tad2DAM7LT6NXXuSYDZtHHBvN0mjZtDdCOiUFFq_XwVcQxG3hU-3XcaE] || [https://www.youtube.com/watch?v=kiYbAmd_3IA]<br />
|-<br />
|Week of Nov 30 || Stan Lee, Seokho Lim, Kyle Jung, Dae Hyun Kim || 27|| Improving neural networks by preventing co-adaption of feature detectors || [https://arxiv.org/pdf/1207.0580.pdf paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Improving_neural_networks_by_preventing_co-adaption_of_feature_detectors Summary] ||<br />
|-<br />
|Week of Nov 30 || Yawen Wang, Danmeng Cui, ZiJie Jiang, Mingkang Jiang, Haotian Ren, Haris Bin Zahid || 28|| A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques || [https://arxiv.org/pdf/1707.02919.pdf Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Describtion_of_Text_Mining Summary] ||<br />
|-<br />
|Week of Nov 30 || Qing Guo, XueGuang Ma, James Ni, Yuanxin Wang || 29|| Mask R-CNN || [https://arxiv.org/pdf/1703.06870.pdf Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Mask_RCNN Summary] || [https://youtu.be/NgcSMXNDNuU]<br />
|-<br />
|Week of Nov 30 || Junyi Yang, Jill Yu Chieh Wang, Yu Min Wu, Calvin Li || 30|| Research paper classifcation systems based on TF‑IDF and LDA schemes || [https://hcis-journal.springeropen.com/articles/10.1186/s13673-019-0192-7?fbclid=IwAR3swO-eFrEbj1BUQfmomJazxxeFR6SPgr6gKayhs38Y7aBG-zX1G3XWYRM Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Research_Papers_Classification_System Summary] || [https://youtu.be/Ug-5H4B5xkQ]<br />
|-<br />
|Week of Nov 30 || Daniel Zhang, Jacky Yao, Scholar Sun, Russell Parco, Ian Cheung || 31 || Speech2Face: Learning the Face Behind a Voice || [https://arxiv.org/pdf/1905.09773.pdf?utm_source=thenewstack&utm_medium=website&utm_campaign=platform Paper] ||[https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Speech2Face:_Learning_the_Face_Behind_a_Voice Summary] || [https://youtu.be/lNQAbMxOj4w]<br />
|-<br />
|Week of Nov 30 || Siyuan Xia, Jiaxiang Liu, Jiabao Dong, Yipeng Du || 32 || Evaluating Machine Accuracy on ImageNet || [https://proceedings.icml.cc/static/paper_files/icml/2020/6173-Paper.pdf] || ||<br />
|-<br />
|Week of Nov 30 || Mushi Wang, Siyuan Qiu, Yan Yu || 33 || Surround Vehicle Motion Prediction Using LSTM-RNN for Motion Planning of Autonomous Vehicles at Multi-Lane Turn Intersections || [https://ieeexplore.ieee.org/abstract/document/8957421 Paper] || [https://wiki.math.uwaterloo.ca/statwiki/index.php?title=Surround_Vehicle_Motion_Prediction Summary] ||</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:T358wang&diff=47634User:T358wang2020-11-29T07:14:49Z<p>J244yang: /* Related Work */</p>
<hr />
<div><br />
== Group ==<br />
Rui Chen, Zeren Shen, Zihao Guo, Taohao Wang<br />
<br />
== Introduction ==<br />
<br />
Landmark recognition is an image retrieval task with its own specific challenges. This paper provides a new and effective method to recognize landmark images, which has been successfully applied to actual images. In this way, statues, buildings, and characteristic objects can be effectively identified.<br />
<br />
There are many difficulties encountered in the development process:<br />
<br />
'''1.''' The concept of landmarks is not strictly defined. Landmarks can take various forms including objects and buildings.<br />
<br />
'''2.''' The same landmark can be photographed from different angles. Certain angles may capture the interior of a building as opposed to its exterior. This could result in vastly different picture characteristics between angles. A good model should accurately identify landmarks regardless of perspective.<br />
<br />
'''3.''' The dataset is unbalanced. The majority of objects fall into the single class of "not landmarks", while relatively few images exist for each class of landmark. Hence, it will be challenging to obtain both a low false positive rate as well as a high recognition accuracy between classes of landmarks.<br />
<br />
There are also three potential problems:<br />
<br />
'''1.''' The processed data set contains a little error content, the image content is not clean and the quantity is huge.<br />
<br />
'''2.''' The algorithm for learning the training set must be fast and scalable.<br />
<br />
'''3.''' While displaying high-quality judgment landmarks, there is no image geographic information mixed.<br />
<br />
The article describes the deep convolutional neural network (CNN) architecture, loss function, training method, and inference aspects. Using this model, similar metrics to the state of the art model in the test were obtained and the inference time was found to be 15 times faster. Further, because of the efficient architecture, the system can serve in an online fashion. The results of quantitative experiments will be displayed through testing and deployment effect analysis to prove the effectiveness of the model.<br />
<br />
== Related Work ==<br />
<br />
Landmark recognition can be regarded as one of the tasks of image retrieval, and a large number of documents concentrate on image retrieval tasks. In the past two decades, the field of image retrieval has made significant progress, and the main methods can be divided into two categories. <br />
The first is a classic retrieval method using local features, a method based on local feature descriptors organized in bag-of-words(A bag of words model is defined as a simplified representation of the text information by retrieving only the significant words in a sentence or paragraph while disregarding its grammar. The bag of words approach is commonly used in classification tasks where the words are used as features in the model-training), spatial verification, Hamming embedding, and query expansion. These methods are dominant in image retrieval. Later, until the rise of deep convolutional neural networks (CNN), CNNs were used to generate global descriptors of input images.<br />
<br />
Vector of Locally Aggregated Descriptors which uses first-order statistics of the local descriptor is one of the main representatives of local features-based methods. Another method is to selectively match the kernel Hamming embedding method extension. With the advent of deep convolutional neural networks, the most effective image retrieval method is based on training CNNs for specific tasks. Deep networks are very powerful for semantic feature representation, which allows us to effectively use them for landmark recognition. This method shows good results but brings additional memory and complexity costs. <br />
The DELF (DEep local feature) by Noh et al. proved promising results. This method combines the classic local feature method with deep learning. This allows us to extract local features from the input image and then use RANSAC for geometric verification. Random Sample Consensus (RANSAC) is a method to smooth data containing a significant percentage of errors, which is ideally suited for applications in automated image analysis where interpretation is based on the data generated by error-prone feature detectors. The goal of the project is to describe a method for accurate and fast large-scale landmark recognition using the advantages of deep convolutional neural networks.<br />
<br />
== Methodology ==<br />
<br />
This section will describe in detail the CNN architecture, loss function, training procedure, and inference implementation of the landmark recognition system. The figure below is an overview of the landmark recognition system.<br />
<br />
[[File:t358wang_landmark_recog_system.png |center|800px]]<br />
<br />
The landmark CNN consists of three parts: the main network, the embedding layer, and the classification layer. To obtain a CNN main network suitable for training landmark recognition model, fine-tuning is applied and several pre-trained backbones (Residual Networks) based on other similar datasets, including ResNet-50, ResNet-200, SE-ResNext-101, and Wide Residual Network (WRN-50-2), are evaluated based on inference quality and efficiency. Based on the evaluation results, WRN-50-2 is selected as the optimal backbone architecture. Fine-tuning is a very efficient technique in various computer vision applications because we can take advantage of everything the model has already learned and applied it to our specific task.<br />
<br />
[[File:t358wang_backbones.png |center|600px]]<br />
<br />
For the embedding layer, as shown in the below figure, the last fully-connected layer after the averaging pool is removed. Instead, a fully-connected 2048 <math>\times</math> 512 layer and a batch normalization are added as the embedding layer. After the batch norm, a fully-connected 512 <math>\times</math> n layer is added as the classification layer. The below figure shows the overview of the CNN architecture of the landmark recognition system.<br />
<br />
[[File:t358wang_network_arch.png |center|800px]]<br />
<br />
To effectively determine the embedding vectors for each landmark class (centroids), the network needs to be trained to have the members of each class to be as close as possible to the centroids. Several suitable loss functions are evaluated including Contrastive Loss, Arcface, and Center loss. The center loss is selected since it achieves the optimal test results and it trains a center of embeddings of each class and penalizes distances between image embeddings as well as their class centers. In addition, the center loss is a simple addition to softmax loss and is trivial to implement.<br />
<br />
When implementing the loss function, a new additional class that includes all non-landmark instances needs to be added and the center loss function needs to be modified as follows: Let n be the number of landmark classes, m be the mini-batch size, <math>x_i \in R^d</math> is the i-th embedding and <math>y_i</math> is the corresponding label where <math>y_i \in</math> {1,...,n,n+1}, n+1 is the label of the non-landmark class. Denote <math>W \in R^{d \times n}</math> as the weights of the classifier layer, <math>W_j</math> as its j-th column. Let <math>c_{y_i}</math> be the <math>y_i</math> th embeddings center from Center loss and <math>\lambda</math> be the balancing parameter of Center loss. Then the final loss function will be: <br />
<br />
[[File:t358wang_loss_function.png |center|600px]]<br />
<br />
In the training procedure, the stochastic gradient descent(SGD) will be used as the optimizer with momentum=0.9 and weight decay = 5e-3. For the center loss function, the parameter <math>\lambda</math> is set to 5e-5. Each image is resized to 256 <math>\times</math> 256 and several data augmentations are applied to the dataset including random resized crop, color jitter, and random flip. The training dataset is divided into four parts based on the geographical affiliation of cities where landmarks are located: Europe/Russia, North America/Australia/Oceania, the Middle East/North Africa, and the Far East Regions. <br />
<br />
The paper introduces curriculum learning for landmark recognition, which is shown in the below figure. The algorithm is trained for 30 epochs and the learning rate <math>\alpha_1, \alpha_2, \alpha_3</math> will be reduced by a factor of 10 at the 12th epoch and 24th epoch.<br />
<br />
[[File:t358wang_algorithm1.png |center|600px]]<br />
<br />
In the inference phase, the paper introduces the term “centroids” which are embedding vectors that are calculated by averaging embeddings and are used to describe landmark classes. The calculation of centroids is significant to effectively determine whether a query image contains a landmark. The paper proposes two approaches to help the inference algorithm to calculate the centroids. First, instead of using the entire training data for each landmark, data cleaning is done to remove most of the redundant and irrelevant elements in the image. For example, if the landmark we are interested in is a palace located on a city square, then images of a similar building on the same square are included in the data which can affect the centroids. Second, since each landmark can have different shooting angles, it is more efficient to calculate a separate centroid for each shooting angle. Hence, a hierarchical agglomerative clustering algorithm is proposed to partition training data into several valid clusters for each landmark and the set of centroids for a landmark L can be represented by <math>\mu_{l_j} = \frac{1}{|C_j|} \sum_{i \in C_j} x_i, j \in 1,...,v</math> where v is the number of valid clusters for landmark L and v=1 if there is no valid clusters for L. <br />
<br />
Once the centroids are calculated for each landmark class, the system can make decisions whether there is any landmark in an image. The query image is passed through the landmark CNN and the resulting embedding vector is compared with all centroids by dot product similarity using approximate k-nearest neighbors (AKNN). To distinguish landmark classes from non-landmark, a threshold <math>\eta</math> is set and it will be compared with the maximum similarity to determine if the image contains any landmarks.<br />
<br />
The full inference algorithm is described in the below figure.<br />
<br />
[[File:t358wang_algorithm2.png |center|600px]]<br />
<br />
We will now look at how the landmark database was created. The collection process was structured by countries, cities and landmarks. They divided the world into several regions: Europe, America, Middle East, Africa, Far East, Australia and Oceania. Within each region, cities were selected that contained a lot of significant landmarks, and some natural landmarks were filtered out as they are difficult to distinguish. Once the cities and landmarks were selected, both images and metadata were collected for each landmark.<br />
<br />
[[File:landmarkcleaning.png | center | 400px]]<br />
<br />
After forming the database, it had to be cleaned before it could be used to train the CNN. First, for each landmark, any redundant images were removed. Then for each landmark, 5 images were picked that had a high probability of containing the landmark and were checked manually. The database was then cleaned by parts using the curriculum learning process. It is further described in the pseudocode above. The final database contained 11381 landmarks in 503 cities and 70 countries. With 2331784 landmark images and 900000 non-landmark images. The number of landmarks that have less than 100 images is called "rare".<br />
<br />
== Experiments and Analysis ==<br />
<br />
'''Offline test'''<br />
<br />
In order to measure the quality of the model, an offline test set was collected and manually labeled. According to the calculations, photos containing landmarks make up 1 − 3% of the total number of photos on average. This distribution was emulated in an offline test, and the geo-information and landmark references weren’t used. <br />
The results of this test are presented in the table below. Two metrics were used to measure the results of experiments: Sensitivity — the accuracy of a model on images with landmarks (also called Recall) and Specificity — the accuracy of a model on images without landmarks. Several types of DELF were evaluated, and the best results in terms of sensitivity and specificity were included in the table below. The table also contains the results of the model trained only with Softmax loss, Softmax, and Center loss. Thus, the table below reflects improvements in our approach with the addition of new elements in it.<br />
<br />
[[File:t358wang_models_eval.png |center|600px]]<br />
<br />
It’s very important to understand how a model works on “rare” landmarks due to the small amount of data for them. Therefore, the behavior of the model was examined separately on “rare” and “frequent” landmarks in the table below. The column “Part from total number” shows what percentage of landmark examples in the offline test has the corresponding type of landmarks. And we find that the sensitivity of “frequent” landmarks is much higher than “rare” landmarks.<br />
<br />
[[File:t358wang_rare_freq.png |center|600px]]<br />
<br />
Analysis of the behavior of the model in different categories of landmarks in the offline test is presented in the table below. These results show that the model can successfully work with various categories of landmarks. Predictably better results (92% of sensitivity and 99.5% of specificity) could also be obtained when the offline test with geo-information was launched on the model.<br />
<br />
[[File:t358wang_landmark_category.png |center|600px]]<br />
<br />
'''Revisited Paris dataset'''<br />
<br />
Revisited Paris dataset (RPar)[2] was also used to measure the quality of the landmark recognition approach. This dataset with Revisited Oxford (ROxf) is standard benchmarks for the comparison of image retrieval algorithms. In recognition, it is important to determine the landmark, which is contained in the query image. Images of the same landmark can have different shooting angles or taken inside/outside the building. Thus, it is reasonable to measure the quality of the model in the standard and adapt it to the task settings. That means not all classes from queries are presented in the landmark dataset. For those images containing correct landmarks but taken from different shooting angles within the building, we transferred them to the “junk” category, which does not influence the final score and makes the test markup closer to our model’s goal. Results on RPar with and without distractors in medium and hard modes are presented in the table below. <br />
<br />
<div style="text-align:center;"> '''Revisited Paris Medium''' </div><br />
[[File:t358wang_methods_eval1.png |center|600px]]<br />
<br />
<br />
<div style="text-align:center;"> '''Revisited Paris Hard''' </div><br />
[[File:t358wang_methods_eval2.png |center|600px]]<br />
<br />
== Comparison ==<br />
<br />
Recent most efficient approaches to landmark recognition are built on fine-tuned CNN. We chose to compare our method to DELF on how well each performs on recognition tasks. A brief summary is given below:<br />
<br />
[[File:t358wang_comparison.png |center|600px]]<br />
<br />
''' Offline test and timing '''<br />
<br />
Both approaches obtained similar results for image retrieval in the offline test (shown in the sensitivity&specificity table), but the proposed approach is much faster on the inference stage and more memory efficient.<br />
<br />
To be more detailed, during the inference stage, DELF needs more forward passes through CNN, has to search the entire database, and performs the RANSAC method for geometric verification. All of them make it much more time-consuming than our proposed approach. Our approach mainly uses centroids, this makes it take less time and needs to store fewer elements.<br />
<br />
== Conclusion ==<br />
<br />
In this paper we were hoping to solve some difficulties that emerge when trying to apply landmark recognition to the production level: there might not be a clean & sufficiently large database for interesting tasks, algorithms should be fast, scalable, and should aim for low FP and high accuracy.<br />
<br />
While aiming for these goals, we presented a way of cleaning landmark data. And most importantly, we introduced the usage of embeddings of deep CNN to make recognition fast and scalable, trained by curriculum learning techniques with modified versions of Center loss. Compared to the state-of-the-art methods, this approach shows similar results but is much faster and suitable for implementation on a large scale.<br />
<br />
== Critique ==<br />
The paper selected 5 images per landmark and checked them manually. That means the training process takes a long time on data cleaning and so the proposed algorithm lacks reusability. Also, since only the landmarks that are the largest and most popular were used to train the CNN, the trained model will probably be most useful in big cities instead of smaller cities with less popular landmarks.<br />
<br />
In addition, researchers often look for reliability and reproducibility. By using a private database and manually labelling it, it lends itself to an array of issues in terms of validity and integrity. Researchers who are looking for such an algorithm will not be able to sufficiently determine if the experiments do actually yield the claimed results. Also, manual labelling by those who are related to the individuals conducting this research also raises the question of conflict of interest. The primary experiment of this paper should be on a public and third-party dataset.<br />
<br />
It might be worth looking into the ability to generalize better. <br />
<br />
This is a very interesting implementation in some specific field. The paper shows a process to analyze the problem and trains the model based on deep CNN implementation. In future work, it would be some practical advice to compare the deep CNN model with other models. By comparison, we might receive a more comprehensive training model for landmark recognization.<br />
<br />
This summary has a good structure and the methodology part is very clear for readers to understand. Using some diagrams for the comparison with other methods is good for visualization for readers. Since the dataset is marked manually, so it is kind of time-consuming for training a model. So it might be interesting to discuss how the famous IT company (i.e. Google etc.) fix this problem.<br />
<br />
It would be beneficial if the authors could provide more explanations regarding the DELF method. Visualization of the differences between DELF and CNN from an algorithm and architecture perspective would be highly significant for the context of this paper.<br />
<br />
One challenge of landmark recognition is large number of classes. It would be good to see the comparison between the proposed model and other models in terms of efficiency.<br />
<br />
The scope of this paper seems to work specifically with some of the most well known landmarks in the world, and many of these landmarks are well known because they are very distinct in how they look. It would be interesting to see how well the model works when classifying different landmarks of similar type (ie, Notre Dame Cathedral vs. St. Paul's Cathedral, etc.). It would also be interesting to see how this model compares with other models in literature, or if this is unique, perhaps the authors could scale this model down to a landmark classification problem (castles, churches, parks, etc.) and compare against other models that way.<br />
<br />
Paper 25 (Loss Function Search in Facial Recognition) also utilizes the softmax loss function in feature discrimination in images. The difference between this paper and paper 25 is that this paper focuses on landmark images, whereas paper 25 is for facial recognition. Despite the slightly different application, both papers prove the importance of using the softmax loss function in feature discrimination, which is pretty neat.<br />
<br />
The paper uses typical representatives of landmarks in various continents during training. It would be interesting to see how different results would be if the average structure of all landmarks present were used.<br />
<br />
The curriculum learning algorithm categories the landmarks into four different geographical locations, i.e (1) Europe, (2) North America, Australia and Oceania; (3) Middle East, North Africa; (4) Far east, because landmarks from same geographical locations are similar to each other than from different geographical locations. Landmarks can also be categorized into archeological landmarks like medieval castles, architectural landmarks like monuments, biological landmarks like some parks or gardens, geological landmarks like caves etc, and it would be interesting to explore what kinds of results the curriculum learning algorithm would produce if the landmarks were categorized in different ways. Also In paper 17, i.e poker AI, uses an approach were similar decision points in the game were grouped together in a process called abstraction. Therefore a similar kind approach of grouping objects is used in the methods described in both papers which indeed helps in reducing the computational time and makes the process more scalable.<br />
<br />
== References ==<br />
[1] Andrei Boiarov and Eduard Tyantov. 2019. Large Scale Landmark Recognition via Deep Metric Learning. In The 28th ACM International Conference on Information and Knowledge Management (CIKM ’19), November 3–7, 2019, Beijing, China. ACM, New York, NY, USA, 10 pages. https://arxiv.org/pdf/1908.10192.pdf 3357384.3357956<br />
<br />
[2] FilipRadenović,AhmetIscen,GiorgosTolias,YannisAvrithis,andOndřejChum.<br />
2018. Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking.<br />
arXiv preprint arXiv:1803.11285 (2018).</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:Cvmustat&diff=47633User:Cvmustat2020-11-29T07:08:47Z<p>J244yang: /* CRNN Results vs Benchmarks */</p>
<hr />
<div><br />
== Combine Convolution with Recurrent Networks for Text Classification == <br />
'''Team Members''': Bushra Haque, Hayden Jones, Michael Leung, Cristian Mustatea<br />
<br />
'''Date''': Week of Nov 23 <br />
<br />
== Introduction ==<br />
<br />
<br />
Text classification is the task of assigning a set of predefined categories to natural language texts. It is a fundamental task in Natural Language Processing (NLP) with various applications such as sentiment analysis, and topic classification. A classic example involving text classification is given a set of News articles, is it possible to classify the genre or subject of each article? Text classification is useful as text data is a rich source of information, but extracting insights from it directly can be difficult and time-consuming as most text data is unstructured.[1] NLP text classification can help automatically structure and analyze text quickly and cost-effectively, allowing for individuals to extract important features from the text easier than before. <br />
<br />
Text classification work mainly focuses on three topics: feature engineering, feature selection, and the use of different types of machine learning algorithms.<br />
1. Feature engineering, the most widely used feature is the bag of words feature. Some more complex functions are also designed, such as part-of-speech tags, noun phrases, and tree kernels.<br />
2. Feature selection aims to remove noisy features and improve classification performance. The most common feature selection method is to delete stop words.<br />
3. Machine learning algorithms usually use classifiers, such as Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM).<br />
<br />
In practice, pre-trained word embeddings and deep neural networks are used together for NLP text classification. Word embeddings are used to map the raw text data to an implicit space where the semantic relationships of the words are preserved; words with similar meaning have a similar representation. One can then feed these embeddings into deep neural networks to learn different features of the text. Convolutional neural networks can be used to determine the semantic composition of the text(the meaning), as it treats texts as a 2D matrix by concatenating the embedding of words together. It uses a 1D convolution operator to perform the feature mapping and then conducts a 1D pooling operation over the time domain for obtaining a fixed-length output feature vector, and it can capture both local and position invariant features of the text.[2] Alternatively, Recurrent Neural Networks can be used to determine the contextual meaning of each word in the text (how each word relates to one another) by treating the text as sequential data and then analyzing each word separately. [3] Previous approaches to attempt to combine these two neural networks to incorporate the advantages of both models involve streamlining the two networks, which might decrease their performance. Besides, most methods incorporating a bi-directional Recurrent Neural Network usually concatenate the forward and backward hidden states at each time step, which results in a vector that does not have the interaction information between the forward and backward hidden states.[4] The hidden state in one direction contains only the contextual meaning in that particular direction, however a word's contextual representation, intuitively, is more accurate when collected and viewed from both directions. This paper argues that the failure to observe the meaning of a word in both directions causes the loss of the true meaning of the word, especially for polysemic words (words with more than one meaning) that are context-sensitive.<br />
<br />
== Paper Key Contributions ==<br />
<br />
This paper suggests an enhanced method of text classification by proposing a new way of combining Convolutional and Recurrent Neural Networks (CRNN) involving the addition of a neural tensor layer. The proposed method maintains each network's respective strengths that are normally lost in previous combination methods. The new suggested architecture is called CRNN, which utilizes both a CNN and RNN that run in parallel on the same input sentence. CNN uses weight matrix learning and produces a 2D matrix that shows the importance of each word based on local and position-invariant features. The bidirectional RNN produces a matrix that learns each word's contextual representation; the words' importance in relation to the rest of the sentence. A neural tensor layer is introduced on top of the RNN to obtain the fusion of bi-directional contextual information surrounding a particular word. This method combines these two matrix representations and classifies the text, providing the important information of each word for prediction, which helps to explain the results. The model also uses dropout and L2 regularization to prevent overfitting.<br />
<br />
== CRNN Results vs Benchmarks ==<br />
<br />
In order to benchmark the performance of the CRNN model, as well as compare it to other previous efforts, multiple datasets and classification problems were used. All of these datasets are publicly available and can be easily downloaded by any user for testing.<br />
<br />
- '''Movie Reviews:''' a sentiment analysis dataset, with two classes (positive and negative).<br />
<br />
- '''Yelp:''' a sentiment analysis dataset, with five classes. For this test, a subset of 120,000 reviews was randomly chosen from each class for a total of 600,000 reviews.<br />
<br />
- '''AG's News:''' a news categorization dataset, using only the 4 largest classes from the dataset. There are 30000 training samples and 1900 test samples.<br />
<br />
- '''20 Newsgroups:''' a news categorization dataset, again using only 4 large classes (comp, politics, rec, and religion) from the dataset.<br />
<br />
- '''Sogou News:''' a Chinese news categorization dataset, using 10 major classes as a multi-class classification and include 6500 samples randomly from each class.<br />
<br />
- '''Yahoo! Answers:''' a topic classification dataset, with 10 classes and each class contains 140000 training samples and 5000 testing samples.<br />
<br />
For the English language datasets, the initial word representations were created using the publicly available ''word2vec'' [https://code.google.com/p/word2vec/] from Google news. For the Chinese language dataset, ''jieba'' [https://github.com/fxsjy/jieba] was used to segment sentences, and then 50-dimensional word vectors were trained on Chinese ''wikipedia'' using ''word2vec''.<br />
<br />
A number of other models are run against the same data after preprocessing. Some of these models include:<br />
<br />
- '''Self-attentive LSTM:''' an LSTM model with multi-hop attention for sentence embedding.<br />
<br />
- '''RCNN:''' the RCNN's recurrent structure allows for increased depth of capture for contextual information. Less noise is introduced on account of the model's holistic structure (compared to local features).<br />
<br />
The following results are obtained:<br />
<br />
[[File:table of results.png|550px|center]]<br />
<br />
The bold results represent the best performing model for a given dataset. These results show that the CRNN model manages to be the best performing in 4 of the 6 datasets, with the Self-attentive LSTM beating the CRNN by 0.03 and 0.12 on the news categorization problems. Considering that the CRNN model has better performance than the Self-attentive LSTM on the other 4 datasets, this suggests that the CRNN model is a better performer overall in the conditions of this benchmark.<br />
<br />
It should be noted that including the neural tensor layer in the CRNN model leads to a significant performance boost compared to the CRNN models without it. The performance boost can be attributed to the fact that the neural tensor layer captures the surrounding contextual information for each word, and brings this information between the forward and backward RNN in a direct method. As seen in the table, this leads to a better classification accuracy across all datasets.<br />
<br />
Another important result was that the CRNN model filter size impacted performance only in the sentiment analysis datasets, as seen in the following:<br />
<br />
[[File:filter_effects.png|550px|center]]<br />
<br />
== CRNN Model Architecture ==<br />
<br />
The CRNN model is a combination of RNN and CNN. It uses CNN to compute the importance of each word in the text and utilizes a neural tensor layer to fuse forward and backward hidden states of bi-directional RNN.<br />
<br />
The input of the network is a text, which is a sequence of words. The output of the network is the text representation that is subsequently used as input of a fully-connected layer to obtain the class prediction.<br />
<br />
'''RNN Pipeline:'''<br />
<br />
The goal of the RNN pipeline is to input each word in a text, and retrieve the contextual information surrounding the word and compute the contextual representation of the word itself. This is accomplished by the use of a bi-directional RNN, such that a Neural Tensor Layer (NTL) can combine the results of the RNN to obtain the final output. RNNs are well-suited to NLP tasks because of their ability to sequentially process data such as ordered text.<br />
<br />
A RNN is similar to a feed-forward neural network, but it relies on the use of hidden states. Hidden states are layers in the neural net that produce two outputs: <math> \hat{y}_{t} </math> and <math> h_t </math>. For a time step <math> t </math>, <math> h_t </math> is fed back into the layer to compute <math> \hat{y}_{t+1} </math> and <math> h_{t+1} </math>. <br />
<br />
The pipeline will actually use a variant of RNN called GRU, short for Gated Recurrent Units. This is done to address the vanishing gradient problem which causes the network to struggle to memorize words that came earlier in the sequence. Traditional RNNs are only able to remember the most recent words in a sequence, which may be problematic since words that came at the beginning of the sequence that is important to the classification problem may be forgotten. A GRU attempts to solve this by controlling the flow of information through the network using update and reset gates. <br />
<br />
Let <math>h_{t-1} \in \mathbb{R}^m, x_t \in \mathbb{R}^d </math> be the inputs, and let <math>\mathbf{W}_z, \mathbf{W}_r, \mathbf{W}_h \in \mathbb{R}^{m \times d}, \mathbf{U}_z, \mathbf{U}_r, \mathbf{U}_h \in \mathbb{R}^{m \times m}</math> be trainable weight matrices. Then the following equations describe the update and reset gates:<br />
<br />
<br />
<math><br />
z_t = \sigma(\mathbf{W}_zx_t + \mathbf{U}_zh_{t-1}) \text{update gate} \\<br />
r_t = \sigma(\mathbf{W}_rx_t + \mathbf{U}_rh_{t-1}) \text{reset gate} \\<br />
\tilde{h}_t = \text{tanh}(\mathbf{W}_hx_t + r_t \circ \mathbf{U}_hh_{t-1}) \text{new memory} \\<br />
h_t = (1-z_t)\circ \tilde{h}_t + z_t\circ h_{t-1}<br />
</math><br />
<br />
<br />
Note that <math> \sigma, \text{tanh}, \circ </math> are all element-wise functions. The above equations do the following:<br />
<br />
<ol><br />
<li> <math>h_{t-1}</math> carries information from the previous iteration and <math>x_t</math> is the current input </li><br />
<li> the update gate <math>z_t</math> controls how much past information should be forwarded to the next hidden state </li><br />
<li> the rest gate <math>r_t</math> controls how much past information is forgotten or reset </li><br />
<li> new memory <math>\tilde{h}_t</math> contains the relevant past memory as instructed by <math>r_t</math> and current information from the input <math>x_t</math> </li><br />
<li> then <math>z_t</math> is used to control what is passed on from <math>h_{t-1}</math> and <math>(1-z_t)</math> controls the new memory that is passed on<br />
</ol><br />
<br />
We treat <math>h_0</math> and <math> h_{n+1} </math> as zero vectors in the method. Thus, each <math>h_t</math> can be computed as above to yield results for the bi-directional RNN. The resulting hidden states <math>\overrightarrow{h_t}</math> and <math>\overleftarrow{h_t}</math> contain contextual information around the <math> t</math>-th word in forward and backward directions respectively. Contrary to convention, instead of concatenating these two vectors, it is argued that the word's contextual representation is more precise when the context information from different directions is collected and fused using a neural tensor layer as it permits greater interactions among each element of hidden states. Using these two vectors as input to the neural tensor layer, <math>V^i </math>, we compute a new representation that aggregates meanings from the forward and backward hidden states more accurately as follows:<br />
<br />
<math> <br />
[\hat{h_t}]_i = tanh(\overrightarrow{h_t}V^i\overleftarrow{h_t} + b_i) <br />
</math><br />
<br />
Where <math>V^i \in \mathbb{R}^{m \times m} </math> is the learned tensor layer, and <math> b_i \in \mathbb{R} </math> is the bias.We repeat this <math> m </math> times with different <math>V^i </math> matrices and <math> b_i </math> vectors. Through the neural tensor layer, each element in <math> [\hat{h_t}]_i </math> can be viewed as a different type of intersection between the forward and backward hidden states. In the model, <math> [\hat{h_t}]_i </math> will have the same size as the forward and backward hidden states. We then concatenate the three hidden states vectors to form a new vector that summarizes the context information :<br />
<math><br />
\overleftrightarrow{h_t} = [\overrightarrow{h_t}^T,\overleftarrow{h_t}^T,\hat{h_t}]^T <br />
</math><br />
<br />
We calculate this vector for every word in the text and then stack them all into matrix <math> H </math> with shape <math>n</math>-by-<math>3m</math>.<br />
<br />
<math><br />
H = [\overleftrightarrow{h_1};...\overleftrightarrow{h_n}]<br />
</math><br />
<br />
This <math>H</math> matrix is then forwarded as the results from the Recurrent Neural Network.<br />
<br />
<br />
'''CNN Pipeline:'''<br />
<br />
The goal of the CNN pipeline is to learn the relative importance of words in an input sequence based on different aspects. The process of this CNN pipeline is summarized as the following steps:<br />
<br />
<ol><br />
<li> Given a sequence of words, each word is converted into a word vector using the word2vec algorithm which gives matrix X. <br />
</li><br />
<br />
<li> Word vectors are then convolved through the temporal dimension with filters of various sizes (ie. different K) with learnable weights to capture various numerical K-gram representations. These K-gram representations are stored in matrix C.<br />
</li><br />
<br />
<ul><br />
<li> The convolution makes this process capture local and position-invariant features. Local means the K words are contiguous. Position-invariant means K contiguous words at any position are detected in this case via convolution.<br />
<br />
<li> Temporal dimension example: convolve words from 1 to K, then convolve words 2 to K+1, etc<br />
</li><br />
</ul><br />
<br />
<li> Since not all K-gram representations are equally meaningful, there is a learnable matrix W which takes the linear combination of K-gram representations to more heavily weigh the more important K-gram representations for the classification task.<br />
</li><br />
<br />
<li> Each linear combination of the K-gram representations gives the relative word importance based on the aspect that the linear combination encodes.<br />
</li><br />
<br />
<li> The relative word importance vs aspect gives rise to an interpretable attention matrix A, where each element says the relative importance of a specific word for a specific aspect.<br />
</li><br />
<br />
</ol><br />
<br />
[[File:Group12_Figure1.png |center]]<br />
<br />
<div align="center">Figure 1: The architecture of CRNN.</div><br />
<br />
== Merging RNN & CNN Pipeline Outputs ==<br />
<br />
The results from both the RNN and CNN pipeline can be merged by simply multiplying the output matrices. That is, we compute <math>S=A^TH</math> which has shape <math>z \times 3m</math> and is essentially a linear combination of the hidden states. The concatenated rows of S results in a vector in <math>\mathbb{R}^{3zm}</math> and can be passed to a fully connected Softmax layer to output a vector of probabilities for our classification task. <br />
<br />
To train the model, we make the following decisions:<br />
<ul><br />
<li> Use cross-entropy loss as the loss function (A cross-entropy loss function usually takes in two distributions, a true distribution p and an estimated distribution q, and measures the average number of bits need to identify an event. This calculation is independent of the kind of layers used in the network as well as the kind of activation being implemented.) </li><br />
<li> Perform dropout on random columns in matrix C in the CNN pipeline </li><br />
<li> Perform L2 regularization on all parameters </li><br />
<li> Use stochastic gradient descent with a learning rate of 0.001 </li><br />
</ul><br />
<br />
== Interpreting Learned CRNN Weights ==<br />
<br />
Recall that attention matrix A essentially stores the relative importance of every word in the input sequence for every aspect chosen. Naturally, this means that A is an n-by-z matrix, with n being the number of words in the input sequence and z being the number of aspects considered in the classification task. <br />
<br />
Furthermore, for any specific aspect, words with higher attention values are more important relative to other words in the same input sequence. likewise, for any specific word, aspects with higher attention values prioritize the specific word more than other aspects.<br />
<br />
For example, in this paper, a sentence is sampled from the Movie Reviews dataset, and the transpose of attention matrix A is visualized. Each word represents an element in matrix A, the intensity of red represents the magnitude of an attention value in A, and each sentence is the relative importance of each word for a specific context. In the first row, the words are weighted in terms of a positive aspect, in the last row, the words are weighted in terms of a negative aspect, and in the middle row, the words are weighted in terms of a positive and negative aspect. Notice how the relative importance of words is a function of the aspect.<br />
<br />
[[File:Interpretation example.png|800px|center]]<br />
<br />
From the above sample, it is interesting that the word "but" is viewed as a negative aspect. From a linguistic perspective, the semantic of "but" is incredibly difficult to capture because of the degree of contextual information it needs. In this case, "but" is in the middle of a transition from a negative to a positive so the first row should also have given the attention to that word. Also, it seems that the model has learned to give very high attention to the two words directly adjacent to the word of high attention: "is" and "and" beside "powerful", and "an" and "cast" beside "unwieldy".<br />
<br />
== Conclusion & Summary ==<br />
<br />
This paper proposed a new architecture, the Convolutional Recurrent Neural Network, for text classification. The Convolutional Neural Network is used to learn the relative importance of each word from their different aspects and stores it this information into a weight matrix. The Recurrent Neural Network learns each word's contextual representation through the combination of the forward and backward context information that is fused using a neural tensor layer and is stored as a matrix. These two matrices are then combined to get the text representation used for classification. Although the specifics of the performed tests are lacking, the experiment's results indicate that the proposed method performed well in comparison to most previous methods. In addition to performing well, the proposed method also provides insight into which words contribute greatly to the classification decision as the learned matrix from the Convolutional Neural Network stores the relative importance of each word. This information can then be used in other applications or analyses. In the future, one can explore the features extracted from the model and use them to potentially learn new methods such as model space. [5]<br />
<br />
== Critiques ==<br />
<br />
In the '''Method''' section of the paper, some explanations used the same notation for multiple different elements of the model. This made the paper harder to follow and understand since they were referring to different elements by identical notation.<br />
<br />
In '''Comparison of Methods''', the authors discuss the range of hyperparameter settings that they search through. While some of the hyperparameters have a large range of search values, three parameters are fixed without much explanation as to why for all experiments, size of the hidden state of GRU, number of layers, and dropout. These parameters have a lot to do with the complexity of the model and this paper could be improved by providing relevant reasoning behind these values, or by providing additional experimental results over different values of these parameters.<br />
<br />
In the '''Results''' section of the paper, they tried to show that the classification results from the CRNN model can be better interpreted than other models. In these explanations, the details were lacking and the authors did not adequately demonstrate how their model is better than others.<br />
<br />
Finally, in the '''Results''' section again, the paper compares the CRNN model to several models which they did not implement and reproduce results with. This can be seen in the chart of results above, where several models do not have entries in the table for all six datasets. Since the authors used a subset of the datasets, these other models which were not reproduced could have different accuracy scores if they had been tested on the same data as the CRNN model. This difference in training and testing data is not mentioned in the paper, and the conclusion that the CRNN model is better in all cases may not be valid.<br />
<br />
- Could this be applied to hieroglyphs to decipher/better understand them?<br />
<br />
It would be interesting to see how the attention matrix is being constructed and how attention values are being determined in each matrix. For instance, does every different subject have its own attention matrix? If so, how will the situation be handled when the same attention matrix is used in different settings?<br />
<br />
-This is an interesting topic. I think it will be better to show more results by using this method. Maybe it will be better to put the result part after the architecture part? Writing a motivation will be better since it will catch readers' "eyes". I think it will be interesting to ask: whether can we apply this to ancient Chinese poetry? Since there are lots of types of ancient Chinese poetry, doing a classification for them will be interesting.<br />
<br />
This is an interesting method, I would be curious to see if this can be combined or compared with Quasi-Recurrent Neural Networks (https://arxiv.org/abs/1611.01576). In my experience, QRNNs perform similarly to LSTMs while running significantly faster using convolutions with a special temporal pooling. This seems compatible with the neural tensor layer proposed in this paper, which may be combined to yield stronger performance with faster runtimes.<br />
<br />
-The paper shows the CRNN model not performing the best with Ag's news and 20newsgroups. It would be interesting to investigate this in detail and see the difference in the way the data is handled in the model compared to the best performing model(self-attentive LSTM in both datasets).<br />
<br />
== References ==<br />
----<br />
<br />
[1] Grimes, Seth. “Unstructured Data and the 80 Percent Rule.” Breakthrough Analysis, 1 Aug. 2008, breakthroughanalysis.com/2008/08/01/unstructured-data-and-the-80-percent-rule/.<br />
<br />
[2] N. Kalchbrenner, E. Grefenstette, and P. Blunsom, “A convolutional neural network for modeling sentences,”<br />
arXiv preprint arXiv:1404.2188, 2014.<br />
<br />
[3] K. Cho, B. V. Merri¨enboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning<br />
phrase representations using RNN encoder-decoder for statistical machine translation,” arXiv preprint<br />
arXiv:1406.1078, 2014.<br />
<br />
[4] S. Lai, L. Xu, K. Liu, and J. Zhao, “Recurrent convolutional neural networks for text classification,” in Proceedings<br />
of AAAI, 2015, pp. 2267–2273.<br />
<br />
[5] H. Chen, P. Tio, A. Rodan, and X. Yao, “Learning in the model space for cognitive fault diagnosis,” IEEE<br />
Transactions on Neural Networks and Learning Systems, vol. 25, no. 1, pp. 124–136, 2014.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=User:J46hou&diff=47631User:J46hou2020-11-29T07:01:57Z<p>J244yang: /* Previous Work */</p>
<hr />
<div>DROCC: Deep Robust One-Class Classification<br />
== Presented by == <br />
Jinjiang Lian, Yisheng Zhu, Jiawen Hou, Mingzhe Huang<br />
== Introduction ==<br />
In this paper, the “one-class” classification, whose goal is to obtain accurate discriminators for a special class, has been studied. Popular uses of this technique include anomaly detection which is widely used in detecting outliers. Anomaly detection is a well-studied area of research; however, the conventional approach of modeling with typical data using a simple function falls short when it comes to complex domains such as vision or speech. Another case where this would be useful is when recognizing “wake-word” while waking up AI systems such as Alexa. <br />
<br />
Deep learning based on anomaly detection methods attempts to learn features automatically but has some limitations. One approach is based on extending the classical data modeling techniques over the learned representations, but in this case, all the points may be mapped to a single point which makes the layer look "perfect". The second approach is based on learning the salient geometric structure of data and training the discriminator to predict applied transformation. The result could be considered anomalous if the discriminator fails to predict the transformation accurately.<br />
<br />
Thus, in this paper, a new approach called Deep Robust One-Class Classification (DROCC) was presented to solve the above concerns. DROCC is based on the assumption that the points from the class of interest lie on a well-sampled, locally linear low dimensional manifold. More specifically, we are presenting DROCC-LF which is an outlier-exposure style extension of DROCC. This extension combines the DROCC's anomaly detection loss with standard classification loss over the negative data and exploits the negative examples to learn a Mahalanobis distance.<br />
<br />
== Previous Work ==<br />
Traditional approaches for one-class problems include one-class SVM (Scholkopf et al., 1999) and Isolation Forest (Liu et al., 2008)[9]. One drawback of these approaches is that they involve careful feature engineering when applied to structured domains like images. The current state of the art methodologies to tackle these kinds of problems are: <br />
<br />
1. Approach based on prediction transformations (Golan & El-Yaniv, 2018; Hendrycks et al.,2019a) [1] This work is based on learning the salient geometric structure of typical data by applying specific transformations to the input data and training the discriminator to preduct applied transformation. This approach has some shortcomings in the sense that it depends heavily on an appropriate domain-specific set of transformations that are in general hard to obtain. <br />
<br />
2. Approach of minimizing a classical one-class loss on the learned final layer representations such as DeepSVDD. (Ruff et al.,2018)[2] This such work has proposed some heuristics to mitigate issues like setting the bias to zero but it is often insufficient in practice. This method suffers from the fundamental drawback of representation collapse where the model is no longer being able to accurately recognize the feature representations.<br />
<br />
3. Approach based on balancing unbalanced training data sets using methods such as SMOTE to synthetically create outlier data to train models on.<br />
<br />
== Motivation ==<br />
Anomaly detection is a well-studied problem with a large body of research (Aggarwal, 2016; Chandola et al., 2009) [3]. The goal is to identify the outliers - the points not following a typical distribution. <br />
[[File:abnormal.jpeg | thumb | center | 1000px | Abnormal Data (Data Driven Investor, 2020)]]<br />
Classical approaches for anomaly detection are based on modeling the typical data using simple functions over the low-dimensional subspace or a tree-structured partition of the input space to detect anomalies (Sch¨olkopf et al., 1999; Liu et al., 2008; Lakhina et al., 2004) [4], such as constructing a minimum-enclosing ball around the typical data points (Tax & Duin, 2004) [5]. They broadly fall into three categories: AD via generative modeling, Deep Once Class SVM, Transformations based methods, and Side-information based AD. While these techniques are well-suited when the input is featured appropriately, they struggle on complex domains like vision and speech, where hand-designing features are difficult.<br />
<br />
'''AD via Generative Modeling:''' involves deep autoencoders and GAN based methods and have been deeply studied. But, this method solves a much harder problem then required and reconstructs the entire input during the decoding step<br />
<br />
'''Deep Once Class SVM:''' was the first method to introduce deep one-class classification for the purpose of anomaly detection, but is impeded by representation collapse.<br />
<br />
'''Transformations based methods:''' Are more recent methods that are based on self-supervised training. The training process of these methods applies transformations to the regular points and training then trains the classifier to identify the transformations used. The model relies on the assumption that a point is normal iff the transformations applied to the point can be identified. Some proposed transformations are as simple as rotations and flips, or can be handcrafted and much more complicated. The various transformations that have been proposed are heavily domain dependent and are hard to design.<br />
<br />
'''Side-information based AD:''' incorporate labelled anomalous data or out-of-distribution samples. DROCC makes no assumptions regarding access to side-information.<br />
<br />
Another related problem is the one-class classification under limited negatives (OCLN). In this case, only a few negative samples are available. The goal is to find a classifier that would not misfire close negatives so that the false positive rate will be low. <br />
<br />
DROCC is robust to representation collapse by involving a discriminative component that is general and empirically accurate on most standard domains like tabular, time-series and vision without requiring any additional side information. DROCC is motivated by the key observation that generally, the typical data lies on a low-dimensional manifold, which is well-sampled in the training data. This is believed to be true even in complex domains such as vision, speech, and natural language (Pless & Souvenir, 2009). [6]<br />
<br />
== Model Explanation ==<br />
[[File:drocc_f1.jpg | center]]<br />
<div align="center">'''Figure 1'''</div><br />
<br />
(a): A normal data manifold with red dots representing generated anomalous points in Ni(r). <br />
<br />
(b): Decision boundary learned by DROCC when applied to the data from (a). Blue represents points classified as normal and red points are classified as abnormal. We observe from here that DROCC is able to capture the manifold accurately; whereas the classical methods OC-SVM and DeepSVDD perform poorly as they both try to learn a minimum enclosing ball for the whole set of positive data points. <br />
<br />
(c), (d): First two dimensions of the decision boundary of DROCC and DROCC–LF, when applied to noisy data (Section 5.2). DROCC–LF is nearly optimal while DROCC’s decision boundary is inaccurate. Yellow color sine wave depicts the train data.<br />
<br />
== DROCC ==<br />
The model is based on the assumption that the true data lies on a manifold. As manifolds resemble Euclidean space locally, our discriminative component is based on classifying a point as anomalous if it is outside the union of small L2 norm balls around the training typical points (See Figure 1a, 1b for an illustration). Importantly, the above definition allows us to synthetically generate anomalous points, and we adaptively generate the most effective anomalous points while training via a gradient ascent phase reminiscent of adversarial training. In other words, DROCC has a gradient ascent phase to adaptively add anomalous points to our training set and a gradient descent phase to minimize the classification loss by learning a representation and a classifier on top of the representations to separate typical points from the generated anomalous points. In this way, DROCC automatically learns an appropriate representation (like DeepSVDD) but is robust to a representation collapse as mapping all points to the same value would lead to poor discrimination between normal points and the generated anomalous points.<br />
<br />
The algorithm that was used to train the model is laid out below in pseudocode.<br />
<center><br />
[[File:DROCCtrain.png]]<br />
</center><br />
<br />
== DROCC-LF ==<br />
To especially tackle problems such as anomaly detection and outlier exposure (Hendrycks et al., 2019a) [7], DROCC–LF, an outlier-exposure style extension of DROCC was proposed. Intuitively, DROCC–LF combines DROCC’s anomaly detection loss (that is over only the positive data points) with standard classification loss over the negative data. In addition, DROCC–LF exploits the negative examples to learn a Mahalanobis distance to compare points over the manifold instead of using the standard Euclidean distance, which can be inaccurate for high-dimensional data with relatively fewer samples. (See Figure 1c, 1d for illustration)<br />
<br />
== Popular Dataset Benchmark Result ==<br />
<br />
[[File:drocc_auc.jpg | center]]<br />
<div align="center">'''Figure 2: AUC result'''</div><br />
<br />
The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. The dataset is divided into five training batches and one test batch, each with 10000 images. The test batch contains exactly 1000 randomly selected images from each class. The training batches contain the remaining images in random order, but some training batches may contain more images from one class than another. Between them, the training batches contain exactly 5000 images from each class. The average AUC (with standard deviation) for one-vs-all anomaly detection on CIFAR-10 is shown in table 1. DROCC outperforms baselines on most classes, with gains as high as 20%, and notably, nearest neighbors (NN) beats all the baselines on 2 classes.<br />
<br />
[[File:drocc_f1score.jpg | center]]<br />
<div align="center">'''Figure 3: F1-Score'''</div><br />
<br />
Figure 3 shows F1-Score (with standard deviation) for one-vs-all anomaly detection on Thyroid, Arrhythmia, and Abalone datasets from the UCI Machine Learning Repository. DROCC outperforms the baselines on all three datasets by a minimum of 0.07 which is about an 11.5% performance increase.<br />
Results on One-class Classification with Limited Negatives (OCLN): <br />
[[File:ocln.jpg | center]]<br />
<div align="center">'''Figure 4: Sample positives, negatives and close negatives for MNIST digit 0 vs 1 experiment (OCLN).'''</div><br />
MNIST 0 vs. 1 Classification: <br />
We consider an experimental setup on the MNIST dataset, where the training data consists of Digit 0, the normal class, and Digit 1 as the anomaly. During the evaluation, in addition to samples from training distribution, we also have half zeros, which act as challenging OOD points (close negatives). These half zeros are generated by randomly masking 50% of the pixels (Figure 2). BCE performs poorly, with a recall of 54% only at a fixed FPR of 3%. DROCC–OE gives a recall value of 98:16% outperforming DeepSAD by a margin of 7%, which gives a recall value of 90:91%. DROCC–LF provides further improvement with a recall of 99:4% at 3% FPR. <br />
<br />
[[File:ocln_2.jpg | center]]<br />
<div align="center">'''Figure 5: OCLN on Audio Commands.'''</div><br />
Wake word Detection: <br />
Finally, we evaluate DROCC–LF on the practical problem of wake word detection with low FPR against arbitrary OOD negatives. To this end, we identify a keyword, say “Marvin” from the audio commands dataset (Warden, 2018) [8] as the positive class, and the remaining 34 keywords are labeled as the negative class. For training, we sample points uniformly at random from the above-mentioned dataset. However, for evaluation, we sample positives from the train distribution, but negatives contain a few challenging OOD points as well. Sampling challenging negatives itself is a hard task and is the key motivating reason for studying the problem. So, we manually list close-by keywords to Marvin such as Mar, Vin, Marvelous, etc. We then generate audio snippets for these keywords via a speech synthesis tool 2 with a variety of accents.<br />
Figure 3 shows that for 3% and 5% FPR settings, DROCC–LF is significantly more accurate than the baselines. For example, with FPR=3%, DROCC–LF is 10% more accurate than the baselines. We repeated the same experiment with the keyword: Seven, and observed a similar trend. In summary, DROCC–LF is able to generalize well against negatives that are “close” to the true positives even when such negatives were not supplied with the training data.<br />
<br />
== Conclusion and Future Work ==<br />
We introduced DROCC method for deep anomaly detection. It models normal data points using a low-dimensional manifold and hence can compare close points via Euclidean distance. Based on this intuition, DROCC’s optimization is formulated as a saddle point problem which is solved via a standard gradient descent-ascent algorithm. We then extended DROCC to OCLN problem where the goal is to generalize well against arbitrary negatives, assuming the positive class is well sampled and a small number of negative points are also available. Both the methods perform significantly better than strong baselines, in their respective problem settings. <br />
<br />
For computational efficiency, we simplified the projection set of both methods which can perhaps slow down the convergence of the two methods. Designing optimization algorithms that can work with the stricter set is an exciting research direction. Further, we would also like to rigorously analyze DROCC, assuming enough samples from a low-curvature manifold. Finally, as OCLN is an exciting problem that routinely comes up in a variety of real-world applications, we would like to apply DROCC–LF to a few high impact scenarios.<br />
<br />
The results of this study showed that DROCC is comparatively better for anomaly detection across many different areas, such as tabular data, images, audio, and time series, when compared to existing state-of-the-art techniques.<br />
<br />
It would be interesting to see how the DROCC method performs in situations where the anomaly is very rare, say detecting signals of volcanic explosion from seismic activity data. Such challenging anomalous situations will be a test of endurance for this method and can even help advance work in this area.<br />
<br />
== References ==<br />
[1]: Golan, I. and El-Yaniv, R. Deep anomaly detection using geometric transformations. In Advances in Neural Information Processing Systems (NeurIPS), 2018.<br />
<br />
[2]: Ruff, L., Vandermeulen, R., Goernitz, N., Deecke, L., Siddiqui, S. A., Binder, A., M¨uller, E., and Kloft, M. Deep one-class classification. In International Conference on Machine Learning (ICML), 2018.<br />
<br />
[3]: Aggarwal, C. C. Outlier Analysis. Springer Publishing Company, Incorporated, 2nd edition, 2016. ISBN 3319475770.<br />
<br />
[4]: Sch¨olkopf, B., Williamson, R., Smola, A., Shawe-Taylor, J., and Platt, J. Support vector method for novelty detection. In Proceedings of the 12th International Conference on Neural Information Processing Systems, 1999.<br />
<br />
[5]: Tax, D. M. and Duin, R. P. Support vector data description. Machine Learning, 54(1), 2004.<br />
<br />
[6]: Pless, R. and Souvenir, R. A survey of manifold learning for images. IPSJ Transactions on Computer Vision and Applications, 1, 2009.<br />
<br />
[7]: Hendrycks, D., Mazeika, M., and Dietterich, T. Deep anomaly detection with outlier exposure. In International Conference on Learning Representations (ICLR), 2019a.<br />
<br />
[8]: Warden, P. Speech commands: A dataset for limited vocabulary speech recognition, 2018. URL https: //arxiv.org/abs/1804.03209.<br />
<br />
[9]: Liu, F. T., Ting, K. M., and Zhou, Z.-H. Isolation forest. In Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, 2008.<br />
<br />
== Critiques/Insights ==<br />
<br />
1. It would be interesting to see this implemented in self-driving cars, for instance, to detect unusual road conditions.<br />
<br />
2. Figure 1 shows a good representation on how this model works. However, how can we know that this model is not prone to overfitting? There are many situations where there are valid points that lie outside of the line, especially new data that the model has never see before. An explanation on how this is avoided would be good.<br />
<br />
3.In the introduction part, it should first explain what is "one class", and then make a detailed application. Moreover, special definition words are used in many places in the text. No detailed explanation was given. In the end, the future application fields of DROCC and the research direction of the group can be explained.<br />
<br />
4. The geometry of this technique (classification based on incidence outside of a ball centred at a known point <math>x</math>) sounds quite similar to K-nearest neighbors. While the authors compared DROCC to single-nearest neighbor classification, choosing a higher K would result in a stronger, more regularized model. It would be interesting to see how DROCC compares to the general KNN classifier<br />
<br />
5. This is a nice summary and the authors introduce clearly on the performance of DROCC. It is nice to use Alexa as an example to catch readers' attention. I think it will be nice to include the algorithm of the DROCC or the architecture of DROCC in this summary to help us know the whole view of this method. Maybe it will be interesting to apply DROCC in biomedical studies? since one-class classification is often used in biomedical studies.<br />
<br />
6. The training method resembles adversarial learning with gradient ascent, however, there is no evaluation of this method on adversarial examples. This is quite unusual considering the paper proposed a method for robust one-class classification, and can be a security threat in real life in critical applications.<br />
<br />
7. The underlying idea behind OCLN is very similar to how neural networks are implemented in recommender systems and trained over positive/negative triplet models. In that case as well, due to the nature of implicit and explicit feedback, positive data tends to dominate the system. It would be interesting to see if insights from that area could be used to further boost the model presented in this paper.<br />
<br />
8. The paper shows the performance of DROCC being evaluated for time series data. It is interesting to see high AUC scores for DROCC against baselines like nearest neighbours and REBMs.Because detecting abnormal data in time series datasets is not common to practise.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Loss_Function_Search_for_Face_Recognition&diff=47489Loss Function Search for Face Recognition2020-11-29T00:18:19Z<p>J244yang: /* Random Search */</p>
<hr />
<div>== Presented by ==<br />
Jan Lau, Anas Mahdi, Will Thibault, Jiwon Yang<br />
<br />
== Introduction ==<br />
Face recognition is a technology that can label a face to a specific identity. The process involves two tasks: 1. Identifying and classifying a face to a certain identity and 2. Verifying if this face and another face map to the same identity. Loss functions are a method of evaluating how well the prediction models the given data. In the application of face recognition, they are used for training convolutional neural networks (CNNs) with discriminative features. Softmax probability is the probability for each class. It contains a vector of values that add up to 1 while ranging between 0 and 1. Cross-entropy loss is the negative log of the probabilities. When softmax probability is combined with cross-entropy loss in the last fully connected layer of the CNN, it yields the softmax loss function:<br />
<br />
<center><math>L_1=-log\frac{e^{w^T_yx}}{e^{w^T_yx} + \sum_{k≠y}^K{e^{w^T_yx}}}</math> [1] </center><br />
<br />
Specifically for face recognition, <math>L_1</math> is modified such that <math>w^T_yx</math> is normalized and <math>s</math> represents the magnitude of <math>w^T_yx</math>:<br />
<br />
<center><math>L_2=-log\frac{e^{s cos{(\theta_{{w_y},x})}}}{e^{s cos{(\theta_{{w_y},x})}} + \sum_{k≠y}^K{e^{s cos{(\theta_{{w_y},x})}}}}</math> [1] </center><br />
<br />
This function is crucial in face recognition because it is used for enhancing feature discrimination. While there are different variations of the softmax loss function, they build upon the same structure as the equation above. Some of these variations will be discussed in detail in the later sections. <br />
<br />
In this paper, the authors first identified that reducing the softmax probability is a key contribution to feature discrimination and designed two design search spaces (random and reward-guided method). They then evaluated their Random-Softmax and Search-Softmax approaches by comparing the results against other face recognition algorithms using nine popular face recognition benchmarks.<br />
<br />
== Previous Work ==<br />
Margin-based (angular, additive, additive angular margins) soft-max loss functions are important in learning discriminative features in face recognition. There have been hand-crafted methods previously developed that require much efforts such as A-softmax, V-softmax, AM-Softmax, and Arc-softmax. Li et al. proposed an AutoML for loss function search method also known as AM-LFS from a hyper-parameter optimization perspective [2]. It automatically determines the search space by leveraging reinforcement learning to the search loss functions during the training process, though the drawback is the complex and unstable search space.<br />
<br />
== Motivation ==<br />
Previous algorithms for facial recognition frequently rely on CNNs that may include metric learning loss functions such as contrastive loss or triplet loss. Without sensitive sample mining strategies, the computational cost for these functions was high. This drawback prompts the redesign of classical softmax loss that cannot discriminate features. Multiple softmax loss functions have since been developed, and including margin-based formulations, they often require fine-tuning of parameters and are susceptible to instability. Therefore, researchers need to put in a lot of effort in creating their method in the large design space. AM-LFS takes an optimization approach for selecting hyperparameters for the margin-based softmax functions, but its aforementioned drawbacks are caused by the lack of direction in designing the search space.<br />
<br />
To solve the issues associated with hand-tuned softmax loss functions and AM-LFS, the authors attempt to reduce the softmax probability to improve feature discrimination when using margin-based softmax loss functions. The development of margin-based softmax loss with only one parameter required and an improved search space using a reward-based method allows the authors to determine the best option for their loss function.<br />
<br />
== Problem Formulation ==<br />
=== Analysis of Margin-based Softmax Loss ===<br />
Based on the softmax probability and the margin-based softmax probability, the following function can be developed [1]:<br />
<br />
<center><math>p_m=\frac{1}{ap+(1-a)}*p</math></center><br />
<center> where <math>a=1-e^{s{cos{(\theta_{w_y},x)}-f{(m,\theta_{w_y},x)}}}</math> and <math>a≤0</math></center><br />
<br />
<math>a</math> is considered as a modulating factor and <math>h{(a,p)}=\frac{1}{ap+(1-a)} \in (0,1]</math> is a modulating function [1]. Therefore, regardless of the margin function (<math>f</math>), the minimization of the softmax probability will ensure success.<br />
<br />
Compared to AM-LFS, this method involves only one parameter (<math>a</math>) that is also constrained, versus AM-LFS which has 2M parameters without constraints that specify the piecewise linear functions the method requires. Also, the piecewise linear functions of AM-LFS (<math>p_m={a_i}p+b_i</math>) may not be discriminative because it could be larger than the softmax probability.<br />
<br />
=== Random Search ===<br />
Unified formulation <math>L_5</math> is generated by inserting a simple modulating function <math>h{(a,p)}=\frac{1}{ap+(1-a)}</math> into the original softmax loss. It can be written as below [1]:<br />
<br />
<center><math>L_5=-log{(h{(a,p)}*p)}</math> where <math>h \in (0,1]</math> and <math>a≤0</math></center><br />
<br />
This encourages the feature margin between different classes and has the capability of feature discrimination. This leads to defining the search space as the choice of <math>h{(a,p)}</math> whose impacts on the training procedure are decided by the modulating factor <math>a</math>. In order to validate the unified formulation, a modulating factor is randomly set at each training epoch. This is noted as Random-Softmax in this paper.<br />
<br />
=== Reward-Guided Search ===<br />
Unlike supervised learning, reinforcement learning (RL) is a behavioral learning model. It does not need to have input/output labelled and it does not need a sub-optimal action to be explicitly corrected. The algorithm receives feedback from the data to achieve the best outcome. The system has an agent that guides the process by taking an action that maximizes the notion of cumulative reward [3]. The process of RL is shown in figure 1. The equation of the cumulative reward function is: <br />
<br />
<center><math>G_t \overset{\Delta}{=} R_t+R_{t+1}+R_{t+2}+⋯+R_T</math></center><br />
<br />
where <math>G_t</math> = cumulative reward, <math>R_t</math> = immediate reward, and <math>R_T</math> = end of episode.<br />
<br />
<math>G_t</math> is the sum of immediate rewards from arbitrary time <math>t</math>. It is a random variable because it depends on the immediate reward which depends on the agent action and the environment reaction to this action.<br />
<br />
<center>[[Image:G25_Figure1.png|300px |link=https://en.wikipedia.org/wiki/Reinforcement_learning#/media/File:Reinforcement_learning_diagram.svg |alt=Alt text|Title text]]</center><br />
<center>Figure 1: Reinforcement Learning scenario [4]</center><br />
<br />
The reward function is what guides the agent to move in a certain direction. As mentioned above, the system receives feedback from the data to achieve the best outcome. This is caused by the reward being edited based on the feedback it receives when a task is completed [5]. <br />
<br />
In this paper, RL is being used to generate a distribution of the hyperparameter <math>\mu</math> for the SoftMax equation using the reward function. <math>\mu</math> updates after each epoch from the reward function. <br />
<br />
<center><math>\mu_{e+1}=\mu_e + \eta \frac{1}{B} \sum_{i=1}^B R{(a_i)}{\nabla_a}log{(g(a_i;\mu,\sigma))}</math></center><br />
<br />
=== Optimization ===<br />
Calculating the reward involves a standard bi-level optimization problem, which involves a hyperparameter ({<math>a_1,a_2,…,a_B</math>}) that can be used for minimizing one objective function while maximizing another objective function simultaneously:<br />
<br />
<center><math>max_a R(a)=r(M_{w^*(a)},S_v)</math></center><br />
<center><math>w^*(a)=_w \sum_{(x,y) \in S_t} L^a (M_w(x),y)</math></center><br />
<br />
In this case, the loss function takes the training set <math>S_t</math> and the reward function takes the validation set <math>S_v</math>. The weights <math>w</math> are trained such that the loss function is minimized while the reward function is maximized. The calculated reward for each model ({<math>M_{we1},M_{we2},…,M_{weB}</math>}) yields the corresponding score, then the algorithm chooses the one with the highest score for model index selection. With the model containing the highest score being used in the next epoch, this process is repeated until the training reaches convergence. In the end, the algorithm takes the model with the highest score without retraining.<br />
<br />
== Results and Discussion ==<br />
=== Results on LFW, SLLFW, CALFW, CPLFW, AgeDB, DFP ===<br />
For LFW, there is not a noticeable difference between the algorithms proposed in this paper and the other algorithms. However, AM-Softmax achieved higher results than Search-Softmax. Random-Softmax achieved the highest results by 0.03%.<br />
<br />
Random-Softmax outperforms baseline Soft-max and is comparable to most of the margin-based softmax. Search-Softmax boost the performance and better most methods specifically when training CASIA-WebFace-R data set, it achieves 0.72% average improvement over AM-Softmax. The reason the model proposed by the paper gives better results is because of their optimization strategy which helps boost the discimination power. Also the sampled candidate from the paper’s proposed search space can well approximate the margin-based loss functions. More tests need to happen to more complicated protocols to test the performance further. Not a lot of improvement has been shown on those test sets, since they are relatively simple and the performance of all the methods on these test sets are near saturation. <br />
<br />
<center>Table 1.Verification performance (%) of different methods on the test sets LFW, SLLFW, CALFW, CPLFW, AgeDB and CFP. The training set is '''CASIA-WebFace-R''' [1].</center><br />
<br />
<center>[[Image:G25_Table1.png|900px |alt=Alt text|Title text]]</center><br />
<br />
=== Results on RFW ===<br />
The RFW dataset measures racial bias which consists of Caucasian, Indian, Asian, and African. Using this as the test set, Random-softmax and Search-softmax performed better than the other methods. Random-softmax outperforms the baseline softmax by a large margin which means reducing the softmax probability will enhance the feature discrimination for face recognition. It is also observed that the reward guided search-softmax method is more likely to enhance the discriminative feature learning resulting in higher performance as shown in Table 2 and Table 3. <br />
<br />
<center>Table 2. Verification performance (%) of different methods on the test set RFW. The training set is '''CASIA-WebFace-R''' [1].</center><br />
<center>[[Image:G25_Table2.png|500px |alt=Alt text|Title text]]</center><br />
<br />
<br />
<center>Table 3. Verification performance (%) of different methods on the test set RFW. The training set is '''MS-Celeb-1M-v1c-R''' [1].</center><br />
<center>[[Image:G25_Table3.png|500px |alt=Alt text|Title text]]</center><br />
<br />
=== Results on MegaFace and Trillion-Pairs ===<br />
The different loss functions are tested again with more complicated protocols. The identification (Id.) Rank-1 and the verification (Veri.) with the true positive rate (TPR) at low false acceptance rate (FAR) at <math>1e-3</math> on MegaFace, the identification TPR@FAR = <math>1e-6</math> and the verification TPR@FAR = <math>1e-9</math> on Trillion-Pairs are reported on Table 4 and 5.<br />
<br />
On the test sets MegaFace and Trillion-Pairs, Search-softmax achieves the best performance over all other alternative methods. On MegaFace, Search-softmax beat the best competitor AM-softmax by a large margin. It also outperformed AM-LFS due to new designed search space. <br />
<br />
<center>Table 4. Performance (%) of different loss functions on the test sets MegaFace and Trillion-Pairs. The training set is '''CASIA-WebFace-R''' [1].</center><br />
<center>[[Image:G25_Table4.png|450px |alt=Alt text|Title text]]</center><br />
<br />
<br />
<center>Table 5. Performance (%) of different loss functions on the test sets MegaFace and Trillion-Pairs. The training set is '''MS-Celeb-1M-v1c-R''' [1].</center><br />
<center>[[Image:G25_Table5.png|450px |alt=Alt text|Title text]]</center><br />
<br />
From the CMC curves and ROC curves in Figure 2, similar trends are observed at other measures. There is a same trend on Trillion-Pairs where Search-softmax loss is found to be superior with 4% improvements with CASIA-WebFace-R and 1% improvements with MS-Celeb-1M-v1c-R at both the identification and verification. Based on these experiments, Search-Softmax loss can perform well, especially with a low false positive rate and it shows a strong generalization ability for face recognition.<br />
<br />
<center>[[Image:G25_Figure2_left.png|450px |alt=Alt text|Title text]] [[Image:G25_Figure2_right.png|450px |alt=Alt text|Title text]]</center><br />
<center>Figure 2. From Left to Right: CMC curves and ROC curves on MegaFace Set with training set CASIA-WebFace-R, CMC curves and ROC curves on MegaFace Set with training set MS-Celeb-1M-v1c-R [1].</center><br />
<br />
== Conclusion ==<br />
In this paper, it is discussed that in order to enhance feature discrimination for face recognition, it is key to know how to reduce the softmax probability. To achieve this goal, unified formulation for the margin-based softmax losses is designed. Two search methods have been developed using a random and a reward-guided loss function and they were validated to be effective over six other methods using nine different test data sets. <br />
<br />
== Critiques ==<br />
* Thorough experimentation and comparison of results to state-of-the-art provided a convincing argument.<br />
* Datasets used did require some preprocessing, which may have improved the results beyond what the method otherwise would.<br />
* AM-LFS was created by the authors for experimentation (the code was not made public) so the comparison may not be accurate.<br />
* The test data set they used to test Search-Softmax and Random-Softmax are simple and they saturate in other methods. So the results of their methods didn’t show much advantage since they produce very similar results. More complicated data set needs to be tested to prove the method's reliability.<br />
<br />
== References ==<br />
[1] X. Wang, S. Wang, C. Chi, S. Zhang and T. Mei, "Loss Function Search for Face Recognition", in International Conference on Machine Learning, 2020, pp. 1-10.<br />
<br />
[2] Li, C., Yuan, X., Lin, C., Guo, M., Wu, W., Yan, J., and Ouyang, W. Am-lfs: Automl for loss function search. In Proceedings of the IEEE International Conference on Computer Vision, pp. 8410–8419, 2019.<br />
2020].<br />
<br />
[3] S. L. AI, “Reinforcement Learning algorithms - an intuitive overview,” Medium, 18-Feb-2019. [Online]. Available: https://medium.com/@SmartLabAI/reinforcement-learning-algorithms-an-intuitive-overview-904e2dff5bbc. [Accessed: 25-Nov-2020]. <br />
<br />
[4] “Reinforcement learning,” Wikipedia, 17-Nov-2020. [Online]. Available: https://en.wikipedia.org/wiki/Reinforcement_learning. [Accessed: 24-Nov-2020].<br />
<br />
[5] B. Osiński, “What is reinforcement learning? The complete guide,” deepsense.ai, 23-Jul-2020. [Online]. Available: https://deepsense.ai/what-is-reinforcement-learning-the-complete-guide/. [Accessed: 25-Nov-2020].</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Loss_Function_Search_for_Face_Recognition&diff=47487Loss Function Search for Face Recognition2020-11-29T00:17:57Z<p>J244yang: /* Random Search */</p>
<hr />
<div>== Presented by ==<br />
Jan Lau, Anas Mahdi, Will Thibault, Jiwon Yang<br />
<br />
== Introduction ==<br />
Face recognition is a technology that can label a face to a specific identity. The process involves two tasks: 1. Identifying and classifying a face to a certain identity and 2. Verifying if this face and another face map to the same identity. Loss functions are a method of evaluating how well the prediction models the given data. In the application of face recognition, they are used for training convolutional neural networks (CNNs) with discriminative features. Softmax probability is the probability for each class. It contains a vector of values that add up to 1 while ranging between 0 and 1. Cross-entropy loss is the negative log of the probabilities. When softmax probability is combined with cross-entropy loss in the last fully connected layer of the CNN, it yields the softmax loss function:<br />
<br />
<center><math>L_1=-log\frac{e^{w^T_yx}}{e^{w^T_yx} + \sum_{k≠y}^K{e^{w^T_yx}}}</math> [1] </center><br />
<br />
Specifically for face recognition, <math>L_1</math> is modified such that <math>w^T_yx</math> is normalized and <math>s</math> represents the magnitude of <math>w^T_yx</math>:<br />
<br />
<center><math>L_2=-log\frac{e^{s cos{(\theta_{{w_y},x})}}}{e^{s cos{(\theta_{{w_y},x})}} + \sum_{k≠y}^K{e^{s cos{(\theta_{{w_y},x})}}}}</math> [1] </center><br />
<br />
This function is crucial in face recognition because it is used for enhancing feature discrimination. While there are different variations of the softmax loss function, they build upon the same structure as the equation above. Some of these variations will be discussed in detail in the later sections. <br />
<br />
In this paper, the authors first identified that reducing the softmax probability is a key contribution to feature discrimination and designed two design search spaces (random and reward-guided method). They then evaluated their Random-Softmax and Search-Softmax approaches by comparing the results against other face recognition algorithms using nine popular face recognition benchmarks.<br />
<br />
== Previous Work ==<br />
Margin-based (angular, additive, additive angular margins) soft-max loss functions are important in learning discriminative features in face recognition. There have been hand-crafted methods previously developed that require much efforts such as A-softmax, V-softmax, AM-Softmax, and Arc-softmax. Li et al. proposed an AutoML for loss function search method also known as AM-LFS from a hyper-parameter optimization perspective [2]. It automatically determines the search space by leveraging reinforcement learning to the search loss functions during the training process, though the drawback is the complex and unstable search space.<br />
<br />
== Motivation ==<br />
Previous algorithms for facial recognition frequently rely on CNNs that may include metric learning loss functions such as contrastive loss or triplet loss. Without sensitive sample mining strategies, the computational cost for these functions was high. This drawback prompts the redesign of classical softmax loss that cannot discriminate features. Multiple softmax loss functions have since been developed, and including margin-based formulations, they often require fine-tuning of parameters and are susceptible to instability. Therefore, researchers need to put in a lot of effort in creating their method in the large design space. AM-LFS takes an optimization approach for selecting hyperparameters for the margin-based softmax functions, but its aforementioned drawbacks are caused by the lack of direction in designing the search space.<br />
<br />
To solve the issues associated with hand-tuned softmax loss functions and AM-LFS, the authors attempt to reduce the softmax probability to improve feature discrimination when using margin-based softmax loss functions. The development of margin-based softmax loss with only one parameter required and an improved search space using a reward-based method allows the authors to determine the best option for their loss function.<br />
<br />
== Problem Formulation ==<br />
=== Analysis of Margin-based Softmax Loss ===<br />
Based on the softmax probability and the margin-based softmax probability, the following function can be developed [1]:<br />
<br />
<center><math>p_m=\frac{1}{ap+(1-a)}*p</math></center><br />
<center> where <math>a=1-e^{s{cos{(\theta_{w_y},x)}-f{(m,\theta_{w_y},x)}}}</math> and <math>a≤0</math></center><br />
<br />
<math>a</math> is considered as a modulating factor and <math>h{(a,p)}=\frac{1}{ap+(1-a)} \in (0,1]</math> is a modulating function [1]. Therefore, regardless of the margin function (<math>f</math>), the minimization of the softmax probability will ensure success.<br />
<br />
Compared to AM-LFS, this method involves only one parameter (<math>a</math>) that is also constrained, versus AM-LFS which has 2M parameters without constraints that specify the piecewise linear functions the method requires. Also, the piecewise linear functions of AM-LFS (<math>p_m={a_i}p+b_i</math>) may not be discriminative because it could be larger than the softmax probability.<br />
<br />
=== Random Search ===<br />
Unified formulation <math>L_5</math> is generated by inserting a simple modulating function <math>h{(a,p)}=\frac{1}{ap+(1-a)}</math> into the original softmax loss. It can be written as below [1]:<br />
<br />
<center><math>L_5=-log{(h{(a,p)}*p)}</math> where <math>h \in (0,1]</math> and <math>a≤0</math></center><br />
<br />
This encourages the feature margin between different classes and has the capability of feature discrimination. This leads to defining the search space as the choice of <math>h{(a,p)}</math> whose impacts on the training procedure are decided by the modulating factor a. In order to validate the unified formulation, a modulating factor is randomly set at each training epoch. This is noted as Random-Softmax in this paper.<br />
<br />
=== Reward-Guided Search ===<br />
Unlike supervised learning, reinforcement learning (RL) is a behavioral learning model. It does not need to have input/output labelled and it does not need a sub-optimal action to be explicitly corrected. The algorithm receives feedback from the data to achieve the best outcome. The system has an agent that guides the process by taking an action that maximizes the notion of cumulative reward [3]. The process of RL is shown in figure 1. The equation of the cumulative reward function is: <br />
<br />
<center><math>G_t \overset{\Delta}{=} R_t+R_{t+1}+R_{t+2}+⋯+R_T</math></center><br />
<br />
where <math>G_t</math> = cumulative reward, <math>R_t</math> = immediate reward, and <math>R_T</math> = end of episode.<br />
<br />
<math>G_t</math> is the sum of immediate rewards from arbitrary time <math>t</math>. It is a random variable because it depends on the immediate reward which depends on the agent action and the environment reaction to this action.<br />
<br />
<center>[[Image:G25_Figure1.png|300px |link=https://en.wikipedia.org/wiki/Reinforcement_learning#/media/File:Reinforcement_learning_diagram.svg |alt=Alt text|Title text]]</center><br />
<center>Figure 1: Reinforcement Learning scenario [4]</center><br />
<br />
The reward function is what guides the agent to move in a certain direction. As mentioned above, the system receives feedback from the data to achieve the best outcome. This is caused by the reward being edited based on the feedback it receives when a task is completed [5]. <br />
<br />
In this paper, RL is being used to generate a distribution of the hyperparameter <math>\mu</math> for the SoftMax equation using the reward function. <math>\mu</math> updates after each epoch from the reward function. <br />
<br />
<center><math>\mu_{e+1}=\mu_e + \eta \frac{1}{B} \sum_{i=1}^B R{(a_i)}{\nabla_a}log{(g(a_i;\mu,\sigma))}</math></center><br />
<br />
=== Optimization ===<br />
Calculating the reward involves a standard bi-level optimization problem, which involves a hyperparameter ({<math>a_1,a_2,…,a_B</math>}) that can be used for minimizing one objective function while maximizing another objective function simultaneously:<br />
<br />
<center><math>max_a R(a)=r(M_{w^*(a)},S_v)</math></center><br />
<center><math>w^*(a)=_w \sum_{(x,y) \in S_t} L^a (M_w(x),y)</math></center><br />
<br />
In this case, the loss function takes the training set <math>S_t</math> and the reward function takes the validation set <math>S_v</math>. The weights <math>w</math> are trained such that the loss function is minimized while the reward function is maximized. The calculated reward for each model ({<math>M_{we1},M_{we2},…,M_{weB}</math>}) yields the corresponding score, then the algorithm chooses the one with the highest score for model index selection. With the model containing the highest score being used in the next epoch, this process is repeated until the training reaches convergence. In the end, the algorithm takes the model with the highest score without retraining.<br />
<br />
== Results and Discussion ==<br />
=== Results on LFW, SLLFW, CALFW, CPLFW, AgeDB, DFP ===<br />
For LFW, there is not a noticeable difference between the algorithms proposed in this paper and the other algorithms. However, AM-Softmax achieved higher results than Search-Softmax. Random-Softmax achieved the highest results by 0.03%.<br />
<br />
Random-Softmax outperforms baseline Soft-max and is comparable to most of the margin-based softmax. Search-Softmax boost the performance and better most methods specifically when training CASIA-WebFace-R data set, it achieves 0.72% average improvement over AM-Softmax. The reason the model proposed by the paper gives better results is because of their optimization strategy which helps boost the discimination power. Also the sampled candidate from the paper’s proposed search space can well approximate the margin-based loss functions. More tests need to happen to more complicated protocols to test the performance further. Not a lot of improvement has been shown on those test sets, since they are relatively simple and the performance of all the methods on these test sets are near saturation. <br />
<br />
<center>Table 1.Verification performance (%) of different methods on the test sets LFW, SLLFW, CALFW, CPLFW, AgeDB and CFP. The training set is '''CASIA-WebFace-R''' [1].</center><br />
<br />
<center>[[Image:G25_Table1.png|900px |alt=Alt text|Title text]]</center><br />
<br />
=== Results on RFW ===<br />
The RFW dataset measures racial bias which consists of Caucasian, Indian, Asian, and African. Using this as the test set, Random-softmax and Search-softmax performed better than the other methods. Random-softmax outperforms the baseline softmax by a large margin which means reducing the softmax probability will enhance the feature discrimination for face recognition. It is also observed that the reward guided search-softmax method is more likely to enhance the discriminative feature learning resulting in higher performance as shown in Table 2 and Table 3. <br />
<br />
<center>Table 2. Verification performance (%) of different methods on the test set RFW. The training set is '''CASIA-WebFace-R''' [1].</center><br />
<center>[[Image:G25_Table2.png|500px |alt=Alt text|Title text]]</center><br />
<br />
<br />
<center>Table 3. Verification performance (%) of different methods on the test set RFW. The training set is '''MS-Celeb-1M-v1c-R''' [1].</center><br />
<center>[[Image:G25_Table3.png|500px |alt=Alt text|Title text]]</center><br />
<br />
=== Results on MegaFace and Trillion-Pairs ===<br />
The different loss functions are tested again with more complicated protocols. The identification (Id.) Rank-1 and the verification (Veri.) with the true positive rate (TPR) at low false acceptance rate (FAR) at <math>1e-3</math> on MegaFace, the identification TPR@FAR = <math>1e-6</math> and the verification TPR@FAR = <math>1e-9</math> on Trillion-Pairs are reported on Table 4 and 5.<br />
<br />
On the test sets MegaFace and Trillion-Pairs, Search-softmax achieves the best performance over all other alternative methods. On MegaFace, Search-softmax beat the best competitor AM-softmax by a large margin. It also outperformed AM-LFS due to new designed search space. <br />
<br />
<center>Table 4. Performance (%) of different loss functions on the test sets MegaFace and Trillion-Pairs. The training set is '''CASIA-WebFace-R''' [1].</center><br />
<center>[[Image:G25_Table4.png|450px |alt=Alt text|Title text]]</center><br />
<br />
<br />
<center>Table 5. Performance (%) of different loss functions on the test sets MegaFace and Trillion-Pairs. The training set is '''MS-Celeb-1M-v1c-R''' [1].</center><br />
<center>[[Image:G25_Table5.png|450px |alt=Alt text|Title text]]</center><br />
<br />
From the CMC curves and ROC curves in Figure 2, similar trends are observed at other measures. There is a same trend on Trillion-Pairs where Search-softmax loss is found to be superior with 4% improvements with CASIA-WebFace-R and 1% improvements with MS-Celeb-1M-v1c-R at both the identification and verification. Based on these experiments, Search-Softmax loss can perform well, especially with a low false positive rate and it shows a strong generalization ability for face recognition.<br />
<br />
<center>[[Image:G25_Figure2_left.png|450px |alt=Alt text|Title text]] [[Image:G25_Figure2_right.png|450px |alt=Alt text|Title text]]</center><br />
<center>Figure 2. From Left to Right: CMC curves and ROC curves on MegaFace Set with training set CASIA-WebFace-R, CMC curves and ROC curves on MegaFace Set with training set MS-Celeb-1M-v1c-R [1].</center><br />
<br />
== Conclusion ==<br />
In this paper, it is discussed that in order to enhance feature discrimination for face recognition, it is key to know how to reduce the softmax probability. To achieve this goal, unified formulation for the margin-based softmax losses is designed. Two search methods have been developed using a random and a reward-guided loss function and they were validated to be effective over six other methods using nine different test data sets. <br />
<br />
== Critiques ==<br />
* Thorough experimentation and comparison of results to state-of-the-art provided a convincing argument.<br />
* Datasets used did require some preprocessing, which may have improved the results beyond what the method otherwise would.<br />
* AM-LFS was created by the authors for experimentation (the code was not made public) so the comparison may not be accurate.<br />
* The test data set they used to test Search-Softmax and Random-Softmax are simple and they saturate in other methods. So the results of their methods didn’t show much advantage since they produce very similar results. More complicated data set needs to be tested to prove the method's reliability.<br />
<br />
== References ==<br />
[1] X. Wang, S. Wang, C. Chi, S. Zhang and T. Mei, "Loss Function Search for Face Recognition", in International Conference on Machine Learning, 2020, pp. 1-10.<br />
<br />
[2] Li, C., Yuan, X., Lin, C., Guo, M., Wu, W., Yan, J., and Ouyang, W. Am-lfs: Automl for loss function search. In Proceedings of the IEEE International Conference on Computer Vision, pp. 8410–8419, 2019.<br />
2020].<br />
<br />
[3] S. L. AI, “Reinforcement Learning algorithms - an intuitive overview,” Medium, 18-Feb-2019. [Online]. Available: https://medium.com/@SmartLabAI/reinforcement-learning-algorithms-an-intuitive-overview-904e2dff5bbc. [Accessed: 25-Nov-2020]. <br />
<br />
[4] “Reinforcement learning,” Wikipedia, 17-Nov-2020. [Online]. Available: https://en.wikipedia.org/wiki/Reinforcement_learning. [Accessed: 24-Nov-2020].<br />
<br />
[5] B. Osiński, “What is reinforcement learning? The complete guide,” deepsense.ai, 23-Jul-2020. [Online]. Available: https://deepsense.ai/what-is-reinforcement-learning-the-complete-guide/. [Accessed: 25-Nov-2020].</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Loss_Function_Search_for_Face_Recognition&diff=47486Loss Function Search for Face Recognition2020-11-29T00:17:36Z<p>J244yang: /* Problem Formulation */</p>
<hr />
<div>== Presented by ==<br />
Jan Lau, Anas Mahdi, Will Thibault, Jiwon Yang<br />
<br />
== Introduction ==<br />
Face recognition is a technology that can label a face to a specific identity. The process involves two tasks: 1. Identifying and classifying a face to a certain identity and 2. Verifying if this face and another face map to the same identity. Loss functions are a method of evaluating how well the prediction models the given data. In the application of face recognition, they are used for training convolutional neural networks (CNNs) with discriminative features. Softmax probability is the probability for each class. It contains a vector of values that add up to 1 while ranging between 0 and 1. Cross-entropy loss is the negative log of the probabilities. When softmax probability is combined with cross-entropy loss in the last fully connected layer of the CNN, it yields the softmax loss function:<br />
<br />
<center><math>L_1=-log\frac{e^{w^T_yx}}{e^{w^T_yx} + \sum_{k≠y}^K{e^{w^T_yx}}}</math> [1] </center><br />
<br />
Specifically for face recognition, <math>L_1</math> is modified such that <math>w^T_yx</math> is normalized and <math>s</math> represents the magnitude of <math>w^T_yx</math>:<br />
<br />
<center><math>L_2=-log\frac{e^{s cos{(\theta_{{w_y},x})}}}{e^{s cos{(\theta_{{w_y},x})}} + \sum_{k≠y}^K{e^{s cos{(\theta_{{w_y},x})}}}}</math> [1] </center><br />
<br />
This function is crucial in face recognition because it is used for enhancing feature discrimination. While there are different variations of the softmax loss function, they build upon the same structure as the equation above. Some of these variations will be discussed in detail in the later sections. <br />
<br />
In this paper, the authors first identified that reducing the softmax probability is a key contribution to feature discrimination and designed two design search spaces (random and reward-guided method). They then evaluated their Random-Softmax and Search-Softmax approaches by comparing the results against other face recognition algorithms using nine popular face recognition benchmarks.<br />
<br />
== Previous Work ==<br />
Margin-based (angular, additive, additive angular margins) soft-max loss functions are important in learning discriminative features in face recognition. There have been hand-crafted methods previously developed that require much efforts such as A-softmax, V-softmax, AM-Softmax, and Arc-softmax. Li et al. proposed an AutoML for loss function search method also known as AM-LFS from a hyper-parameter optimization perspective [2]. It automatically determines the search space by leveraging reinforcement learning to the search loss functions during the training process, though the drawback is the complex and unstable search space.<br />
<br />
== Motivation ==<br />
Previous algorithms for facial recognition frequently rely on CNNs that may include metric learning loss functions such as contrastive loss or triplet loss. Without sensitive sample mining strategies, the computational cost for these functions was high. This drawback prompts the redesign of classical softmax loss that cannot discriminate features. Multiple softmax loss functions have since been developed, and including margin-based formulations, they often require fine-tuning of parameters and are susceptible to instability. Therefore, researchers need to put in a lot of effort in creating their method in the large design space. AM-LFS takes an optimization approach for selecting hyperparameters for the margin-based softmax functions, but its aforementioned drawbacks are caused by the lack of direction in designing the search space.<br />
<br />
To solve the issues associated with hand-tuned softmax loss functions and AM-LFS, the authors attempt to reduce the softmax probability to improve feature discrimination when using margin-based softmax loss functions. The development of margin-based softmax loss with only one parameter required and an improved search space using a reward-based method allows the authors to determine the best option for their loss function.<br />
<br />
== Problem Formulation ==<br />
=== Analysis of Margin-based Softmax Loss ===<br />
Based on the softmax probability and the margin-based softmax probability, the following function can be developed [1]:<br />
<br />
<center><math>p_m=\frac{1}{ap+(1-a)}*p</math></center><br />
<center> where <math>a=1-e^{s{cos{(\theta_{w_y},x)}-f{(m,\theta_{w_y},x)}}}</math> and <math>a≤0</math></center><br />
<br />
<math>a</math> is considered as a modulating factor and <math>h{(a,p)}=\frac{1}{ap+(1-a)} \in (0,1]</math> is a modulating function [1]. Therefore, regardless of the margin function (<math>f</math>), the minimization of the softmax probability will ensure success.<br />
<br />
Compared to AM-LFS, this method involves only one parameter (<math>a</math>) that is also constrained, versus AM-LFS which has 2M parameters without constraints that specify the piecewise linear functions the method requires. Also, the piecewise linear functions of AM-LFS (<math>p_m={a_i}p+b_i</math>) may not be discriminative because it could be larger than the softmax probability.<br />
<br />
=== Random Search ===<br />
Unified formulation <math>L_5</math> is generated by inserting a simple modulating function <math>h{(a,p)}=\frac{1}{ap+(1-a)}</math> into the original softmax loss. It can be written as below [1]:<br />
<br />
<center><math>L_5=-log{(h{(a,p)}*p)}</math> where <math>h \in (0,1]</math> and <math>a≤0</math></center><br />
<br />
This encourages the feature margin between different classes and has the capability of feature discrimination. This leads to defining the search space as the choice of <math>{(a,p)}</math> whose impacts on the training procedure are decided by the modulating factor a. In order to validate the unified formulation, a modulating factor is randomly set at each training epoch. This is noted as Random-Softmax in this paper.<br />
<br />
=== Reward-Guided Search ===<br />
Unlike supervised learning, reinforcement learning (RL) is a behavioral learning model. It does not need to have input/output labelled and it does not need a sub-optimal action to be explicitly corrected. The algorithm receives feedback from the data to achieve the best outcome. The system has an agent that guides the process by taking an action that maximizes the notion of cumulative reward [3]. The process of RL is shown in figure 1. The equation of the cumulative reward function is: <br />
<br />
<center><math>G_t \overset{\Delta}{=} R_t+R_{t+1}+R_{t+2}+⋯+R_T</math></center><br />
<br />
where <math>G_t</math> = cumulative reward, <math>R_t</math> = immediate reward, and <math>R_T</math> = end of episode.<br />
<br />
<math>G_t</math> is the sum of immediate rewards from arbitrary time <math>t</math>. It is a random variable because it depends on the immediate reward which depends on the agent action and the environment reaction to this action.<br />
<br />
<center>[[Image:G25_Figure1.png|300px |link=https://en.wikipedia.org/wiki/Reinforcement_learning#/media/File:Reinforcement_learning_diagram.svg |alt=Alt text|Title text]]</center><br />
<center>Figure 1: Reinforcement Learning scenario [4]</center><br />
<br />
The reward function is what guides the agent to move in a certain direction. As mentioned above, the system receives feedback from the data to achieve the best outcome. This is caused by the reward being edited based on the feedback it receives when a task is completed [5]. <br />
<br />
In this paper, RL is being used to generate a distribution of the hyperparameter <math>\mu</math> for the SoftMax equation using the reward function. <math>\mu</math> updates after each epoch from the reward function. <br />
<br />
<center><math>\mu_{e+1}=\mu_e + \eta \frac{1}{B} \sum_{i=1}^B R{(a_i)}{\nabla_a}log{(g(a_i;\mu,\sigma))}</math></center><br />
<br />
=== Optimization ===<br />
Calculating the reward involves a standard bi-level optimization problem, which involves a hyperparameter ({<math>a_1,a_2,…,a_B</math>}) that can be used for minimizing one objective function while maximizing another objective function simultaneously:<br />
<br />
<center><math>max_a R(a)=r(M_{w^*(a)},S_v)</math></center><br />
<center><math>w^*(a)=_w \sum_{(x,y) \in S_t} L^a (M_w(x),y)</math></center><br />
<br />
In this case, the loss function takes the training set <math>S_t</math> and the reward function takes the validation set <math>S_v</math>. The weights <math>w</math> are trained such that the loss function is minimized while the reward function is maximized. The calculated reward for each model ({<math>M_{we1},M_{we2},…,M_{weB}</math>}) yields the corresponding score, then the algorithm chooses the one with the highest score for model index selection. With the model containing the highest score being used in the next epoch, this process is repeated until the training reaches convergence. In the end, the algorithm takes the model with the highest score without retraining.<br />
<br />
== Results and Discussion ==<br />
=== Results on LFW, SLLFW, CALFW, CPLFW, AgeDB, DFP ===<br />
For LFW, there is not a noticeable difference between the algorithms proposed in this paper and the other algorithms. However, AM-Softmax achieved higher results than Search-Softmax. Random-Softmax achieved the highest results by 0.03%.<br />
<br />
Random-Softmax outperforms baseline Soft-max and is comparable to most of the margin-based softmax. Search-Softmax boost the performance and better most methods specifically when training CASIA-WebFace-R data set, it achieves 0.72% average improvement over AM-Softmax. The reason the model proposed by the paper gives better results is because of their optimization strategy which helps boost the discimination power. Also the sampled candidate from the paper’s proposed search space can well approximate the margin-based loss functions. More tests need to happen to more complicated protocols to test the performance further. Not a lot of improvement has been shown on those test sets, since they are relatively simple and the performance of all the methods on these test sets are near saturation. <br />
<br />
<center>Table 1.Verification performance (%) of different methods on the test sets LFW, SLLFW, CALFW, CPLFW, AgeDB and CFP. The training set is '''CASIA-WebFace-R''' [1].</center><br />
<br />
<center>[[Image:G25_Table1.png|900px |alt=Alt text|Title text]]</center><br />
<br />
=== Results on RFW ===<br />
The RFW dataset measures racial bias which consists of Caucasian, Indian, Asian, and African. Using this as the test set, Random-softmax and Search-softmax performed better than the other methods. Random-softmax outperforms the baseline softmax by a large margin which means reducing the softmax probability will enhance the feature discrimination for face recognition. It is also observed that the reward guided search-softmax method is more likely to enhance the discriminative feature learning resulting in higher performance as shown in Table 2 and Table 3. <br />
<br />
<center>Table 2. Verification performance (%) of different methods on the test set RFW. The training set is '''CASIA-WebFace-R''' [1].</center><br />
<center>[[Image:G25_Table2.png|500px |alt=Alt text|Title text]]</center><br />
<br />
<br />
<center>Table 3. Verification performance (%) of different methods on the test set RFW. The training set is '''MS-Celeb-1M-v1c-R''' [1].</center><br />
<center>[[Image:G25_Table3.png|500px |alt=Alt text|Title text]]</center><br />
<br />
=== Results on MegaFace and Trillion-Pairs ===<br />
The different loss functions are tested again with more complicated protocols. The identification (Id.) Rank-1 and the verification (Veri.) with the true positive rate (TPR) at low false acceptance rate (FAR) at <math>1e-3</math> on MegaFace, the identification TPR@FAR = <math>1e-6</math> and the verification TPR@FAR = <math>1e-9</math> on Trillion-Pairs are reported on Table 4 and 5.<br />
<br />
On the test sets MegaFace and Trillion-Pairs, Search-softmax achieves the best performance over all other alternative methods. On MegaFace, Search-softmax beat the best competitor AM-softmax by a large margin. It also outperformed AM-LFS due to new designed search space. <br />
<br />
<center>Table 4. Performance (%) of different loss functions on the test sets MegaFace and Trillion-Pairs. The training set is '''CASIA-WebFace-R''' [1].</center><br />
<center>[[Image:G25_Table4.png|450px |alt=Alt text|Title text]]</center><br />
<br />
<br />
<center>Table 5. Performance (%) of different loss functions on the test sets MegaFace and Trillion-Pairs. The training set is '''MS-Celeb-1M-v1c-R''' [1].</center><br />
<center>[[Image:G25_Table5.png|450px |alt=Alt text|Title text]]</center><br />
<br />
From the CMC curves and ROC curves in Figure 2, similar trends are observed at other measures. There is a same trend on Trillion-Pairs where Search-softmax loss is found to be superior with 4% improvements with CASIA-WebFace-R and 1% improvements with MS-Celeb-1M-v1c-R at both the identification and verification. Based on these experiments, Search-Softmax loss can perform well, especially with a low false positive rate and it shows a strong generalization ability for face recognition.<br />
<br />
<center>[[Image:G25_Figure2_left.png|450px |alt=Alt text|Title text]] [[Image:G25_Figure2_right.png|450px |alt=Alt text|Title text]]</center><br />
<center>Figure 2. From Left to Right: CMC curves and ROC curves on MegaFace Set with training set CASIA-WebFace-R, CMC curves and ROC curves on MegaFace Set with training set MS-Celeb-1M-v1c-R [1].</center><br />
<br />
== Conclusion ==<br />
In this paper, it is discussed that in order to enhance feature discrimination for face recognition, it is key to know how to reduce the softmax probability. To achieve this goal, unified formulation for the margin-based softmax losses is designed. Two search methods have been developed using a random and a reward-guided loss function and they were validated to be effective over six other methods using nine different test data sets. <br />
<br />
== Critiques ==<br />
* Thorough experimentation and comparison of results to state-of-the-art provided a convincing argument.<br />
* Datasets used did require some preprocessing, which may have improved the results beyond what the method otherwise would.<br />
* AM-LFS was created by the authors for experimentation (the code was not made public) so the comparison may not be accurate.<br />
* The test data set they used to test Search-Softmax and Random-Softmax are simple and they saturate in other methods. So the results of their methods didn’t show much advantage since they produce very similar results. More complicated data set needs to be tested to prove the method's reliability.<br />
<br />
== References ==<br />
[1] X. Wang, S. Wang, C. Chi, S. Zhang and T. Mei, "Loss Function Search for Face Recognition", in International Conference on Machine Learning, 2020, pp. 1-10.<br />
<br />
[2] Li, C., Yuan, X., Lin, C., Guo, M., Wu, W., Yan, J., and Ouyang, W. Am-lfs: Automl for loss function search. In Proceedings of the IEEE International Conference on Computer Vision, pp. 8410–8419, 2019.<br />
2020].<br />
<br />
[3] S. L. AI, “Reinforcement Learning algorithms - an intuitive overview,” Medium, 18-Feb-2019. [Online]. Available: https://medium.com/@SmartLabAI/reinforcement-learning-algorithms-an-intuitive-overview-904e2dff5bbc. [Accessed: 25-Nov-2020]. <br />
<br />
[4] “Reinforcement learning,” Wikipedia, 17-Nov-2020. [Online]. Available: https://en.wikipedia.org/wiki/Reinforcement_learning. [Accessed: 24-Nov-2020].<br />
<br />
[5] B. Osiński, “What is reinforcement learning? The complete guide,” deepsense.ai, 23-Jul-2020. [Online]. Available: https://deepsense.ai/what-is-reinforcement-learning-the-complete-guide/. [Accessed: 25-Nov-2020].</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Summary_for_survey_of_neural_networked-based_cancer_prediction_models_from_microarray_data&diff=46002Summary for survey of neural networked-based cancer prediction models from microarray data2020-11-23T03:27:34Z<p>J244yang: /* Background */</p>
<hr />
<div>== Presented by == <br />
Rao Fu, Siqi Li, Yuqin Fang, Zeping Zhou<br />
<br />
== Introduction == <br />
Microarray technology is widely used in analyzing genetic diseases as it can help researchers rapidly detect genetic information. To study cancer, researchers use this technology to compare normal and abnormal cancerous tissues to gain insights into pathology of cancer. However, the high dimensionality of the gene expressions can affect the accuracy and computation time of this cancer model. To cope with this problem, we need to use the feature selection method or feature creation method. The former (feature selection methods), reduce the dimensionality of the data-set by selecting only a subset of the key discerning features as inputs to the model. In contrast, the latter (feature creation methods), create an entirely new set of lower dimensional features, meant to represent the original (higher-dimensional) features. <br />
One of the most powerful methods in machine learning is neural networks. In this paper, we will review the latest neural network-based cancer prediction models by presenting the methodology of preprocessing, filtering, prediction, and clustering gene expressions.<br />
<br />
== Background == <br />
<br />
'''Neural Network''' <br><br />
Neural networks are often used to solve non-linear complex problems. It is an operational model consisting of a large number of neurons connected to each other by different weights. In this network structure, each neuron is related to an activation function such as sigmoid or rectified linear activation functions. To train the network, the inputs are fed forward and the activation function value is calculated at every neuron. The difference between the output of the neural network and the actual value is what we call an error.<br />
The backpropagation mechanism is one of the most commonly used algorithms in solving neural network problems. By using this algorithm, we optimize the objective function by propagating back the generated error through the network to adjust the weights.<br />
In the next sections, we will use the above algorithm but with different network architectures and a different number of neurons to review the neural network-based cancer prediction models for learning the gene expression features.<br />
<br />
'''Cancer prediction models'''<br><br />
Cancer prediction models often contain more than 1 method to achieve high prediction accuracy with a more accurate prognosis and it also aims to reduce the cost of patients.<br />
<br />
High dimensionality and spatial structure are the two main factors that can affect the accuracy of the cancer prediction models. They add irrelevant noisy features to our selected models. We have 3 ways to determine the accuracy of a model.<br />
<br />
The first is called ROC curve. ROC curves, receiver operating characteristic curves, are graphs that show the true positive rate against the false positive rate [4]. It reflects the sensitivity of the response to the same signal stimulus under different criteria. To test its validity, we need to consider it with the confidence interval. Usually, a model is considered acceptable when its ROC is greater than 0.7. <br />
<br />
A different machine learning problem is predicting the survival time. The performance of a model that predicts survival time can be measured using two metrics. The problem of predicting survival time can be seen as a ranking problem, where survival times of different subjects are ranked against each other. CI (Concordance Index) is a measure of how good a model ranks survival times and explains the concordance probability of the predicted and observed survival. The closer its value to 0.7, the better the model is. We can express the ordering of survival times in an order graph <math display="inline">G = (V, E)</math> where the vertices <math display="inline">V</math> are the individual survival times, and the edges <math display="inline">E_{ij}</math> from individual <math display="inline">i</math> to <math display="inline">j</math> indicate that <math display="inline">T_i < T_j</math>, where <math display="inline">T_i, T_j</math> are the survival times for individuals <math display="inline">i,j</math> respectively. Then we can write <math display="inline">CI = \frac{1}{|E|}\sum_{i,j}I(f(i) < f(j))</math> where <math display="inline">|E|</math> is the number of edges in the order graph (ie. the total number of comparable pairs), and <math display="inline">I(f(i) < f(j)) = 1</math> if the predictor <math display="inline">f</math> correctly ranks <math display="inline">T_i < T_j</math> [3].<br />
<br />
Another metric is the Brier score, which measures the average difference between the observed and the estimated survival rate in a given period of time. It ranges from 0 to 1, and a lower score indicates higher accuracy. It is defined as <math display="inline">\frac{1}{n}\sum_{i=1}^n(f_i - o_i)^2</math> where <math display="inline">f_i</math> is the predicted survival rate, and <math display="inline">o_i</math> is the observed survival rate [2].<br />
<br />
== Neural network-based cancer prediction models ==<br />
By performing an extensive search relevant to neural network-based cancer prediction using Google scholar and other electronic databases namely PubMed and Scopus with keywords such as “Neural Networks AND Cancer Prediction” and “gene expression clustering”, the chosen papers covered cancer classification, discovery, survivability prediction and the statistical analysis models. The following figure 1 shows a graph representing the number of citations including filtering, predictive and clustering for chosen papers. [[File:f1.png]]<br />
<br />
'''Datasets and preprocessing''' <br><br />
Most studies investigating automatic cancer prediction and clustering used datasets such as the TCGA, UCI, NCBI Gene Expression Omnibus and Kentridge biomedical databases. There are a few of techniques used in processing dataset including removing the genes that have zero expression across all samples, Normalization, filtering with p value > <math>10^{-05}</math> to remove some unwanted technical variation and <math>\log_2</math> transformations. Statistical methods, neural network, were applied to reduce the dimensionality of the gene expressions by selecting a subset of genes. Principle Component Analysis (PCA) can also be used as an initial preprocessing step to extract the datasets features. The PCA method linearly transforms the dataset features into lower dimensional space without capturing the complex relationships between the features. However, simply removing the genes that were not measured by the other datasets could not overcame the class imbalance problem. In that case, one research used Synthetic Minority Class Over Sampling method to generate synthetic minority class samples, which may lead to sparse matrix problem. Clustering was also applied in some studies for labeling data by grouping the samples into high-risk, low-risk groups and so on. <br />
<br />
The following table presents the dataset used by considered reference, the applied normalization technique, the cancer type and the dimensionality of the datasets.<br />
[[File:Datasets and preprocessing.png]]<br />
<br />
'''Neural network architecture''' <br><br />
Most recent studies reveal that neural network methods are used for filtering, predicting and clustering in cancer prediction. <br />
<br />
*''filtering'': Filter the gene expressions to eliminate noise or reduce dimensionality. Then use the resulted features with statistical methods or machine learning classification and clustering tools as figure 2 indicates.<br />
<br />
*''predicting'': Extract features and improve the accuracy of prediction (classification).<br />
<br />
*''clustering'': Divide the gene expressions or samples based on similarity.<br />
<br />
[[File:filtering gane.png]]<br />
<br />
All the neurons in the neural network work together as feature detectors to learn the features from the input. In order to categorize a neural network as a filtering, predicting, or clustering method, we looked at the overall role that network provided within the framework of cancer prediction. Filtering methods are trained to remove the input’s noise and to extract the most representative features that best describe the unlabeled gene expressions. Predicting methods are trained to extract the features that are significant to prediction, therefore its objective functions measure how accurately the network is able to predict the class of an input. Clustering methods are trained to divide unlabeled samples into groups based on their similarities.<br />
<br />
'''Building neural networks-based approaches for gene expression prediction''' <br><br />
According to our survey, the representative codes are generated by filtering methods with dimensionality M smaller or equal to N, where N is the dimensionality of the input. Some other machine learning algorithm such as naïve Bayes or k-means can be used together with the filtering.<br />
Predictive neural networks are supervised, which find the best classification accuracy; meanwhile, clustering methods are unsupervised, which group similar samples or genes together. <br />
The goal of training prediction is to enhance the classification capability, and the goal of training classification is to find the optimal group to a new test set with unknown labels.<br />
<br />
'''Neural network filters for cancer prediction''' <br><br />
In the preprocessing step to classification, clustering and statistical analysis, the autoencoders are more and more commonly-used, to extract generic genomic features. An autoencoder is composed of the encoder part and the decoder part. The encoder part is to learn the mapping between high-dimensional unlabeled input I(x) and the low-dimensional representations in the middle layer(s), and the decoder part is to learn the mapping from the middle layer’s representation to the high-dimensional output O(x). The reconstruction of the input can take the Root Mean Squared Error (RMSE) or the Logloss function as the objective function. <br />
<br />
$$ RMSE = \sqrt{ \frac{\sum{(I(x)-O(x))^2}}{n} } $$<br />
<br />
$$ Logloss = \sum{(I(x)\log(O(x)) + (1 - I(x))\log(1 - O(x)))} $$<br />
<br />
There are several types of autoencoders, such as stacked denoising autoencoders, contractive autoencoders, sparse autoencoders, regularized autoencoders and variational autoencoders. The architecture of the networks varies in many parameters, such as depth and loss function. Each example of an autoencoder mentioned above has different number of hidden layers, different activation functions (e.g. sigmoid function, exponential linear unit function), and different optimization algorithms (e.g. stochastic gradient decent optimization, Adam optimizer).<br />
<br />
Overfitting is a major problem that most autoencoders need to deal with to achieve high efficiency of the extracted features. Regularization, dropout, and sparsity are common solutions.<br />
<br />
The neural network filtering methods were used by different statistical methods and classifiers. The conventional methods include Cox regression model analysis, Support Vector Machine (SVM), K-means clustering, t-SNE and so on. The classifiers could be SVM or AdaBoost or others.<br />
<br />
By using neural network filtering methods, the model can be trained to learn low-dimensional representations, remove noises from the input, and gain better generalization performance by re-training the classifier with the newest output layer.<br />
<br />
'''Neural network prediction methods for cancer''' <br><br />
The prediction based on neural networks can build a network that maps the input features to an output with a number of neurons, which could be one or two for binary classification, or more for multi-class classification. It can also build several independent binary neural networks for the multi-class classification, where the technique called “one-hot encoding” is applied.<br />
<br />
The codeword is a binary string C’k of length k whose j’th position is set to 1 for the j’th class, while other positions remain 0. The process of the neural networks is to map the input to the codeword iteratively, whose objective function is minimized in each iteration.<br />
<br />
Such cancer classifiers were applied on identify cancerous/non-cancerous samples, a specific cancer type, or the survivability risk. MLP models were used to predict the survival risk of lung cancer patients with several gene expressions as input. The deep generative model DeepCancer, the RBM-SVM and RBM-logistic regression models, the convolutional feedforward model DeepGene, Extreme Learning Machines (ELM), the one-dimensional convolutional framework model SE1DCNN, and GA-ANN model are all used for solving cancer issues mentioned above. This paper indicates that the performance of neural networks with MLP architecture as classifier are better than those of SVM, logistic regression, naïve Bayes, classification trees and KNN.<br />
<br />
'''Neural network clustering methods in cancer prediction''' <br><br />
Neural network clustering belongs to unsupervised learning. The input data are divided into different groups according to their feature similarity.<br />
The single-layered neural network SOM, which is unsupervised and without backpropagation mechanism, is one of the traditional model-based techniques to be applied on gene expression data. The measurement of its accuracy could be Rand Index (RI), which can be improved to Adjusted Random Index (ARI) and Normalized Mutation Information (NMI).<br />
<br />
$$ RI=\frac{TP+TN}{TP+TN+FP+FN}$$<br />
<br />
In general, gene expression clustering considers either the relevance of samples-to-cluster assignment or that of gene-to-cluster assignment, or both. To solve the high dimensionality problem, there are two methods: clustering ensembles by running a single clustering algorithm for several times, each of which has different initialization or number of parameters; and projective clustering by only considering a subset of the original features.<br />
<br />
SOM was applied on discriminating future tumor behavior using molecular alterations, whose results were not easy to be obtained by classic statistical models. Then this paper introduces two ensemble clustering frameworks: Random Double Clustering-based Cluster Ensembles (RDCCE) and Random Double Clustering-based Fuzzy Cluster Ensembles (RDCFCE). Their accuracies are high, but they have not taken gene-to-cluster assignment into consideration.<br />
<br />
Also, the paper provides double SOM based Clustering Ensemble Approach (SOM2CE) and double NG-based Clustering Ensemble Approach (NG2CE), which are robust to noisy genes. Moreover, Projective Clustering Ensemble (PCE) combines the advantages of both projective clustering and ensemble clustering, which is better than SOM and RDCFCE when there are irrelevant genes.<br />
<br />
== Summary ==<br />
<br />
Cancer is a disease with a very high fatality rate that spreads worldwide, and it’s essential to analyze gene expression for discovering gene abnormalities and increasing survivability as a consequence. The previous analysis in the paper reveals that neural networks are essentially used for filtering the gene expressions, predicting their class, or clustering them.<br />
<br />
Neural network filtering methods are used to reduce the dimensionality of the gene expressions and remove their noise. In the article, the authors recommended deep architectures more than shallow architectures for best practice as they combine many nonlinearities. <br />
<br />
Neural network prediction methods can be used for both binary and multi-class problems. In binary cases, the network architecture has only one or two output neurons that diagnose a given sample as cancerous or non-cancerous, while the number of the output neurons in multi-class problems is equal to the number of classes. The authors suggested that the deep architecture with convolution layers which was the most recently used model proved efficient capability and in predicting cancer subtypes as it captures the spatial correlations between gene expressions.<br />
Clustering is another analysis tool that is used to divide the gene expressions into groups. The authors indicated that a hybrid approach combining both the ensembling clustering and projective clustering is more accurate than using single-point clustering algorithms such as SOM since those methods do not have the capability to distinguish the noisy genes.<br />
<br />
==Discussion==<br />
There are some technical problems that can be considered and improved for building new models. <br><br />
<br />
1. Overfitting: Since gene expression datasets are high dimensional and have a relatively small number of samples, it would be likely to properly fits the training data but not accurate for test samples due to the lack of generalization capability. The ways to avoid overfitting can be: (1). adding weight penalties using regularization; (2). using the average predictions from many models trained on different datasets; (3). dropout. (4) Augmentation of the dataset to produce more "observations".<br><br />
<br />
2. Model configuration and training: In order to reduce both the computational and memory expenses but also with high prediction accuracy, it’s crucial to properly set the network parameters. The possible ways can be: (1). proper initialization; (2). pruning the unimportant connections by removing the zero-valued neurons; (3). using ensemble learning framework by training different models using different parameter settings or using different parts of the dataset for each base model; (4). Using SMOTE for dealing with class imbalance on the high dimensional level. <br><br />
<br />
3. Model evaluation: In Braga-Neto and Dougherty's research, they have investigated several model evaluation methods: cross-validation, substitution and bootstrap methods. The cross-validation was found to be unreliable for small size data since it displayed excessive variance. The bootstrap method proved more accurate predictability.<br><br />
<br />
4. Study producibility: A study needs to be reproducible to enhance research reliability so that others can replicate the results using the same algorithms, data and methodology.<br />
<br />
==Conclusion==<br />
This paper reviewed the most recent neural network-based cancer prediction models and gene expression analysis tools. The analysis indicates that the neural network methods are able to serve as filters, predictors, and clustering methods, and also showed that the role of the neural network determines its general architecture. The authors showed that Neural Network filtering methods are a way of reducing the dimensionality of the gene expressions, as well as removing their noise for better model fitting. To give suggestions for future neural network-based approaches, the authors highlighted some critical points that have to be considered such as overfitting and class imbalance, and suggest choosing different network parameters or combining two or more of the presented approaches. One of the biggest challenges for cancer prediction modelers is deciding on the network architecture (i.e. the number of hidden layers and neurons), as there are currently no guidelines to follow to obtain high prediction accuracy. The authors discovered that there is no algorithm available to concretely determine an optimal number of hidden layers or nodes and found that many papers simply implemented a trial and error method to reduce loss in the model.<br />
<br />
==Critiques==<br />
<br />
While results indicate that the functionality of the neural network determines its general architecture, the decision on the number of hidden layers, neurons, hypermeters and learning algorithm is made using trial-and-error techniques. Therefore improvements in this area of the model might need to be explored in order to obtain better results and in order to make more convincing statements.<br />
<br />
An issue that one must be mindful of is the underlying distribution of data. Cancer is an extremely complex genetic disease and the predictions would depend on so many variables, a number of which will not even be present in the dataset as they might have been collected. So there is a need for extensive validation when it comes to applying deep learning methods to cancer related data.<br />
<br />
In the field of medical sciences and molecular biology, interpretability of result is imperative as often experts seek not just to solve the issue at hand but to understand the causal relationships. Having a high ROC value may not necessarily convince other experts on the validity of the finding because the underlying details of cancer symptoms have been abstracted in a complex neural network as a black box. However, the neural network clustering method suggested in this paper do offer a good compromise because it enables us humans to visual low-level features but still give experts the control on making various predictions using well-studied traditional techniques.<br />
<br />
With high dimensionality features, kernel SVM is another option for cancer prediction. Jiang et. al. developed a Hadamard Kernel for predicting breast cancer using gene expression data, and it utilizes the Kernel trick to avoid high computational efforts (link: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5763304/). Compared against linear, quadratic, RBF and correlation kernels, Hadamard Kernel performs best with the highest averaged area under the ROC curve (AUC) value. It may be interesting to compare the performance and accuracy between the Hadamard Kernel and cancer prediction models with various number of hidden layers and neurons.<br />
<br />
Although authors presented technical details about data processing, training approaches, evaluation metric, and addressed many practical issues that can be considered for cancer prediction, no novel methods or models are proposed. It's more like a proof-of-concept about the feasibility of different models on cancer prediction.<br />
<br />
==Reference==<br />
[1] Daoud, M., & Mayo, M. (2019). A survey of neural network-based cancer prediction models from microarray data. Artificial Intelligence in Medicine, 97, 204–214.<br />
<br />
[2] Brier GW. 1950. Verification of forecasts expressed in terms of probabilities. Monthly Weather Review 78: 1–3<br />
<br />
[3] Harald Steck, Balaji Krishnapuram, Cary Dehing-oberije, Philippe Lambin, Vikas C. Raykar. On ranking in survival analysis: Bounds on the concordance index. In Advances in Neural Information Processing Systems (2008), pp. 1209-1216<br />
<br />
[4] Google Developers. (2020 February 10). ''Classification: ROC Curve and AUC.'' Machine Learning Crash Course. https://developers.google.com/machine-learning/crash-course/classification/roc-and-auc</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=what_game_are_we_playing&diff=45999what game are we playing2020-11-23T03:24:53Z<p>J244yang: /* References */</p>
<hr />
<div>== Authors == <br />
Yuxin Wang, Evan Peters, Yifan Mou, Sangeeth Kalaichanthiran <br />
<br />
== Introduction ==<br />
Recently, there have been many different studies of methods using AI to solve large-scale, zero-sum, extensive form problems. However, most of these works operate under the assumption that the parameters of the game are known, and the objective is just finding the optimal strategy for the game. This scenario is unrealistic since most of the time parameters of the game are unknown. This paper proposes a framework for finding an optimal solution using a primal-dual Newton Method and then using back-propagation to analytically compute the gradients of all the relevant game parameters.<br />
<br />
The approach to solving this problem is to consider ''quantal response equilibrium'' (QRE), which is a generalization of Nash equilibrium (NE) where the agents can make suboptimal decisions. It is shown that the solution to the QRE is a differentiable function of the payoff matrix. Consequently, back-propagation can be used to analytically solve for the payoff matrix (or other game parameters). This strategy has many future application areas as it allows for game-solving (both extensive and normal form) to be integrated as a module in a deep neural network.<br />
<br />
An example of architecture is presented below:<br />
<br />
[[File:Framework.png ]]<br />
<br />
Payoff matrix <math> P </math> is parameterized by a domain-dependent low dimensional vector <math> \phi </math>, where <math> \phi </math> depends on a differentiable function <math> M_1(x) </math>. Furthermore, <math> P </math> is applied to QRE to get the equilibrium strategies <math> (u^∗, v^∗) </math>. Lastly, the loss function is calculated after applying any differentiable <math> M_2(u^∗, v^∗) </math>.<br />
<br />
The effectiveness of this model is demonstrated using the games “Rock, Paper, Scissors”, one-card poker, and a security defense game.<br />
<br />
== Learning and Quantal Response in Normal Form Games ==<br />
<br />
The game-solving module provides all elements required in differentiable learning, which maps contextual features to payoff matrices, and computes equilibrium strategies under a set of contextual features. This paper will learn zero-sum games and start with normal form games since they have game solver and learning approach capturing much of intuition and basic methodology.<br />
<br />
=== Zero-Sum Normal Form Games ===<br />
<br />
In two-player zero-sum games there is a '''payoff matrix''' <math>P</math> that describes the rewards for two players employing specific strategies u and v respectively. The optimal strategy mixture may be found with a classic min-max formulation:<br />
$$\min_u \max_v \ u^T P v \\ subject \ to \ 1^T u =1, u \ge 0 \\ 1^T v =1, v \ge 0. \ $$<br />
<br />
Here, we consider the case where <math>P</math> is not known a priori. The solution <math> (u^*, v_0) </math> to this optimization and the solution <math> (u_0,v^*) </math> to the corresponding problem with inverse player order form the Nash equilibrium <math>(u^*,v^*) </math>. At this equilibrium, the players do not have anything to gain by changing their strategy, so this point is a stable state of the system. When the payoff matrix P is not known, we observe samples of actions <math> a^{(i)}, i =1,...,N </math> from one or both players, which depends on some external content <math> x </math>, sampled from the equilibrium strategies <math>(u^*,v^*) </math>, to recover the true underlying payoff matrix P or a function form P(x) depending on the current context.<br />
<br />
=== Quantal Response Equilibria ===<br />
<br />
However, NE is poorly suited because NEs are overly strict, discontinuous with respect to P, and may not be unique. To address these issues, model the players' actions with the '''quantal response equilibria''' (QRE), where noise is added to the payoff matric. Specifically, consider the ''logit'' equilibrium for zero-sum games that obeys the fixed point:<br />
$$<br />
u^* _i = \frac {exp(-Pv)_i}{\sum_{q \in [n]} exp (-Pv)_q}, \ v^* _j= \frac {exp(P^T u)_j}{\sum_{q \in [m]} exp (P^T u)_q} .\qquad \ (1)<br />
$$<br />
For a fixed opponent strategy, the logit equilibrium corresponding to a strategy is strictly convex, and thus the regularized best response is unique.<br />
<br />
=== End-to-End Learning ===<br />
<br />
Then to integrate zero-sum solver, [1] introduced a method to solve the QRE and to differentiate through its solution.<br />
<br />
'''QRE solver''':<br />
To find the fixed point in (1), it is equivalent to solve the regularized min-max game:<br />
$$<br />
\min_{u \in \mathbb{R}^n} \max_{v \in \mathbb{R}^m} \ u^T P v -H(v) + H(u) \\<br />
\text{subject to } 1^T u =1, \ 1^T v =1, <br />
$$<br />
where H(y) is the Gibbs entropy <math> \sum_i y_i log y_i</math>.<br />
Entropy regularization guarantees the non-negative condition and makes the equilibrium continuous with respect to P, which means players are encouraged to play more randomly, and all actions have non-zero probability. Moreover, this problem has a unique saddle point corresponding to <math> (u^*, v^*) </math>.<br />
<br />
Using a primal-dual Newton Method to solve the QRE for two-player zero-sum games, the KKT conditions for the problem are:<br />
$$ <br />
Pv + \log(u) + 1 +\mu 1 = 0 \\<br />
P^T v -\log(v) -1 +\nu 1 = 0 \\<br />
1^T u = 1, \ 1^T v = 1, <br />
$$<br />
where <math> (\mu, \nu) </math> are Lagrange multipliers for the equality constraints on u, v respectively. Then applying Newton's method gives the the update rule:<br />
$$<br />
Q \begin{bmatrix} \Delta u \\ \Delta v \\ \Delta \mu \\ \Delta \nu \\ \end{bmatrix} = - \begin{bmatrix} P v + \log u + 1 + \mu 1 \\ P^T u - \log v - 1 + \nu 1 \\ 1^T u - 1 \\ 1^T v - 1 \\ \end{bmatrix}, \qquad (2)<br />
$$<br />
where Q is the Hessian of the Lagrangian, given by <br />
$$ <br />
Q = \begin{bmatrix} <br />
diag(\frac{1}{u}) & P & 1 & 0 \\ <br />
P^T & -diag(\frac{1}{v}) & 0 & 1\\<br />
1^T & 0 & 0 & 0 \\<br />
0 & 1^T & 0 & 0 \\<br />
\end{bmatrix}. <br />
$$<br />
<br />
'''Differentiating Through QRE Solutions''':<br />
The QRE solver provides a method to compute the necessary Jacobian-vector products. Specifically, we compute the gradient of the loss given the solution <math> (u^*,v^*) </math> to the QRE, and some loss function <math> L(u^*,v^*) </math>: <br />
<br />
1. Take differentials of the KKT conditions: <br />
<math><br />
Q \begin{bmatrix} <br />
du & dv & d\mu & d\nu \\ <br />
\end{bmatrix} ^T = \begin{bmatrix} <br />
-dPv & -dP^Tu & 0 & 0 \\ <br />
\end{bmatrix}^T. \ <br />
</math><br />
<br />
2. For small changes du, dv, <br />
<math><br />
dL = \begin{bmatrix} <br />
v^TdP^T & u^TdP & 0 & 0 \\ <br />
\end{bmatrix} Q^{-1} \begin{bmatrix} <br />
-\nabla_u L & -\nabla_v L & 0 & 0 \\ <br />
\end{bmatrix}^T.<br />
</math><br />
<br />
3. Apply this to P, and take limits as dP is small:<br />
<math><br />
\nabla_P L = y_u v^T + u y_v^T, \qquad (3)<br />
</math> where <br />
<math><br />
\begin{bmatrix} <br />
y_u & y_v & y_{\mu} & y_{\nu}\\ <br />
\end{bmatrix}=Q^{-1}\begin{bmatrix} <br />
-\nabla_u L & -\nabla_v L & 0 & 0 \\ <br />
\end{bmatrix}^T.<br />
</math><br />
<br />
Hence, the forward pass is given by using the expression in (2) to solve for the logit equilibrium given P, and the backward pass is given by using <math> \nabla_u L </math> and <math> \nabla_v L </math> to obtain <math> \nabla_P L </math> using (3). There does not always exist a unique P which generates <math> u^*, v^* </math> under the logit QRE, and we cannot expect to recover P when under-constrained.<br />
<br />
== Learning Extensive form games ==<br />
<br />
The normal form representation for games where players have many choices quickly becomes intractable. For example, consider a chess game: One the first turn, player 1 has 20 possible moves and then player 2 has 20 possible responses. If in the following number of turns each player is estimated to have ~30 possible moves and if a typical game is 40 moves per player, the total number of strategies is roughly <math>10^{120} </math> per player (this is known as the Shannon number for game-tree complexity of chess) and so the payoff matrix for a typical game of chess must therefore have <math> O(10^{240}) </math> entries.<br />
<br />
Instead, it is much more useful to represent the game graphically as an "'''Extensive form game'''" (EFG). We'll also need to consider types of games where there is '''imperfect information''' - players do not necessarily have access to the full state of the game. An example of this is one-card poker: (1) Each player draws a single card from a 13-card deck (ignore suits) (2) Player 1 decides whether to bet/hold (3) Player 2 decides whether to call/raise (4) Player 1 must either call/fold if Player 2 raised. From this description, player 1 has <math> 2^{13} </math> possible first moves (all combinations of (card, raise/hold)) and has <math> 2^{13} </math> possible second moves (whenever player 1 gets a second move) for a total of <math> 2^{26} </math> possible strategies. In addition, Player 1 never knows what cards player 2 has and vice versa. So instead of representing the game with a huge payoff matrix we can instead represent it as a simple decision tree (for a ''single'' drawn card of player 1):<br />
<br />
<br />
<center> [[File:1cardpoker.PNG]] </center><br />
<br />
where player 1 is represented by "1", a node that has two branches corresponding to the allowed moves of player 1. However there must also be a notion of information available to either player: While this tree might correspond to say, player 1 holding a "9", it contains no information on what card player 2 is holding (and is much simpler because of this). This leads to the definition of an '''information set''': the set of all nodes belonging to a single player for which the other player cannot distinguish which node has been reached. The information set may therefore be treated as a node itself, for which actions stemming from the node must be chosen in ignorance to what the other player did immediately before arriving at the node. In the poker example, the full game tree consists of a much more complex version of the tree shown above (containing repetitions of the given tree for every possible combination of cards dealt) and the and an example of an information set for player 1 is the set of all of nodes owned by player 2 that immediately follow player 1's decision to hold. In other words, if player 1 holds there are 13 possible nodes describing the responses of player 2 (raise/hold for player 2 having card = ace, 1, ... King) and all 13 of these nodes are indistinguishable to player 1, and so form an information set for player 1.<br />
<br />
The following is a review of important concepts for extensive form games first formalized in [2]. Let <math> \mathcal{I}_i </math> be the set of all information sets for player i, and for each <math> t \in \mathcal{I}_i </math> let <math> \sigma_t </math> be the actions taken by player i to arrive at <math> t </math> and <math> C_t </math> be the actions that player i can take from <math> u </math>. Then the set of all possible sequences that can be taken by player i is given by<br />
<br />
$$<br />
S_i = \{\emptyset \} \cup \{ \sigma_t c | u\in \mathcal{I}_i, c \in C_t \}<br />
$$<br />
<br />
So for the one-card poker we would have <math>S_1 = \{\emptyset, \text{raise}, \text{hold}, \text{hold-call}, \text{hold-fold\} }</math>. From the possible sequences follows two important concepts:<br />
<ol><br />
<li>The EFG '''payoff matrix''' <math> P </math> of size <math>|S_1| \times |S_2| </math> (this is all possible actions available to either player), is populated with rewards from each leaf of the tree (or "zero" for each <math> (s_1, s_2) </math> that is an invalid pair), and the expected payoff for realization plans <math> (u, v) </math> is given by <math> u^T P v </math> </li><br />
<li> A '''realization plan''' <math> u \in \mathbb{R}^{|S_1|} </math> for player 1 (<math> v \in \mathbb{R}^{|S_2|} </math> for player 2 ) will describe probabilities for players to carry out each possible sequence, and each realization plan must be constrained by (i) compatibility of sequences (e.g. "raise" is not compatible with "hold-call") and (ii) information sets available to the player. These constraints are linear:<br />
<br />
$$<br />
Eu = e \\<br />
Fv = f<br />
$$<br />
<br />
where <math> e = f = (1, 0, ..., 0)^T </math> and <math> E, F</math> contain entries in <math> {-1, 0, 1} </math> describing compatibility and information sets. </li><br />
<br />
</ol> <br />
<br />
<br />
The paper's main contribution is to develop a minmax problem for extensive form games:<br />
<br />
<br />
$$<br />
\min_u \max_v u^T P v + \sum_{t\in \mathcal{I}_1} \sum_{c \in C_t} u_c \log \frac{u_c}{u_{p_t}} - \sum_{t\in \mathcal{I}_2} \sum_{c \in C_t} v_c \log \frac{v_c}{v_{p_t}}<br />
$$<br />
<br />
where <math> p_t </math> is the action immediately preceding information set <math> t </math>. Intuitively, each sum resembles a cross entropy over the distribution of probabilities in the realization plan comparing each probability to proceed from an information set to the probability to arrive at that information set. Importantly, these entropies are strictly convex or concave (for player 1 and player 2 respectively) [3] so that the minmax problem will have a unique solution and ''the objective function is continuous and continuously differentiable'' - this means there is a way to optimize the function. As noted in Theorem 1 of [1], the solution to this problem is equivalently a solution for the QRE of the game in reduced normal form.<br />
<br />
Minmax can also be seen from an algorithmic perspective. Referring to the above figure containing a tree, it contains a sequence of states and action which alternates between two or more competing players. The above formulation of the minmax problem essentially measures how well a decision rule is from the perspective of a single player. To describe it in terms of the tree, if it is player 1's turn, then it is a mutual recursion of player 1 choosing to maximize its payoff and player 2 choosing to minimize player 1's payoff.<br />
<br />
Having decided on a cost function, the method of Lagrange multipliers may be used to construct the Lagrangian that encodes the known constraints (<math> Eu = e \,, Fv = f </math>, and <math> u, v \geq 0</math>), and then optimize the Lagrangian using Newton's method (identically to the previous section). Accounting for the constraints, the Lagrangian becomes <br />
<br />
<br />
$$<br />
\mathcal{L} = g(u, v) + \sum_i \mu_i(Eu - e)_i + \sum_i \nu_i (Fv - f)_i<br />
$$<br />
<br />
where <math>g</math> is the argument from the minmax statement above and <math>u, v \geq 0</math> become KKT conditions. The general update rule for Newton's method may be written in terms of the derivatives of <math> \mathcal{L} </math> with respect to primal variables <math>u, v </math> and dual variables <math> \mu, \nu</math>, yielding:<br />
<br />
$$<br />
\nabla_{u,v,\mu,\nu}^2 \mathcal{L} \cdot (\Delta u, \Delta v, \Delta \mu, \Delta \nu)^T= - \nabla_{u,v,\mu,\nu} \mathcal{L}<br />
$$<br />
where <math>\nabla_{u,v,\mu,\nu}^2 \mathcal{L} </math> is the Hessian of the Lagrangian and <math>\nabla_{u,v,\mu,\nu} \mathcal{L} </math> is simply a column vector of the KKT stationarity conditions. Combined with the previous section, this completes the goal of the paper: To construct a differentiable problem for learning normal form and extensive form games.<br />
<br />
== Experiments ==<br />
<br />
The authors demonstrated learning on extensive form games in the presence of ''side information'', with ''partial observations'' using three experiments. In all cases, the goal was to maximize the likelihood of realizing an observed sequence from the player, assuming they act in accordance to the QRE. The authors found that the best way to implement the module was to use a medium to large batch size, RMSProp, or Adam optimizers with a learning rate between <math>\left[0.0001,0.01\right].</math> <br />
<br />
=== Rock, Paper, Scissors ===<br />
<br />
Rock, Paper, Scissors is a 2-player zero-sum game. For this game, the best strategy to reach a Nash equilibrium and a Quantal response equilibrium is to uniformly play each hand with equal odds.<br />
The first experiment was to learn a non-symmetric variant of Rock, Paper, Scissors with ''incomplete information'' with the following payoff matrix:<br />
<br />
{| class="wikitable" style="float:center; margin-left:1em; text-align:center;"<br />
|+ align="bottom"|''Payoff matrix of modified Rock-Paper-Scissors''<br />
! <br />
! ''Rock''<br />
! ''Paper''<br />
! ''Scissors''<br />
|-<br />
! ''Rock''<br />
| '''''0'''''<br />
| <math>-b_1</math><br />
| <math>b_2</math><br />
|-<br />
! ''Paper''<br />
| <math>b_1</math><br />
| '''''0'''''<br />
| <math>-b_3</math><br />
|-<br />
! ''Scissors''<br />
| <math>-b_2</math><br />
| <math>b_3</math><br />
| '''''0'''''<br />
|}<br />
<br />
where each of the <math> b </math> ’s are linear function of some features <math> x \in \mathbb{R}^{2} </math> (i.e., <math> b_y = x^Tw_y </math>, <math> y \in </math> {<math>1,2,3</math>} , where <math> w_y </math> are to be learned by the algorithm). Using many trials of random rewards the technique produced the following results for optimal strategies[1]: <br />
<br />
[[File:RPS Results.png|500px ]]<br />
<br />
From the graphs above, we can tell the following: 1) both parameters learned and predicted strategies improve with larger dataset; and 2) with a reasonably sized dataset, >1000 here, convergence is stable and is fairly quick.<br />
<br />
=== One-Card Poker ===<br />
<br />
Next they investigated extensive form games using the one-Card Poker (with ''imperfect information'') introduced in the previous section. In the experimental setup, they used a deck stacked non-uniformly (meaning repeat cards were allowed). Their goal was to learn this distribution of cards from observations of many rounds of the play. Different from the distribution of cards dealt, the method built in the paper is more suited to learn the player’s perceived or believed distribution of cards. It may even be a function of contextual features such as demographics of players. Three experiments were run with <math> n=4 </math>. Each experiment comprised 5 runs of training, with same weights but different training sets. Let <math> d \in \mathbb{R}^{n}, d \ge 0, \sum_{i} d_i = 1 </math> be the weights of the cards. The probability that the players are dealt cards <math> (i,j) </math> is <math> \frac{d_i d_j}{1-d_i} </math>. This distribution is asymmetric between players. Matrix <math> P, E, F </math> for the case <math> n=4 </math> are presented in [1]. With training for 2500 epochs, the mean squared error of learned parameters (card weights, <math> u, v </math> ) are averaged over all runs of and are presented as following [1]: <br />
<br />
<br />
[[File:One-card_Poker_Results.png|500px ]]<br />
<br />
=== Security Resource Allocation Game ===<br />
<br />
<br />
From Security Resource Allocation Game, they demonstrated the ability to learn from ''imperfect observations''. The defender possesses <math> k </math> indistinguishable and indivisible defensive resources which he splits among <math> n </math> targets, { <math> T_1, ……, T_n </math>}. The attacker chooses one target. If the attack succeeds, the attacker gets <math> R_i </math> reward and defender gets <math> -R_i </math>, otherwise zero payoff for both. If there are n defenders guarding <math> T_i </math>, probability of successful attack on <math> T_i </math> is <math> \frac{1}{2^n} </math>. The expected payoff matrix when <math> n = 2, k = 3 </math>, where the attackers are the row players is:<br />
<br />
{| class="wikitable" style="float:center; margin-left:1em; text-align:center;"<br />
|+ align="bottom"|''Payoff matrix when <math> n = 2, k = 3 </math>''<br />
! {#<math>D_1</math>,#<math>D_2</math>}<br />
! {0, 3}<br />
! {1, 2}<br />
! {2, 1}<br />
! {3, 0}<br />
|-<br />
! <math>T_1</math><br />
| <math>-R_1</math><br />
| <math>-\frac{1}{2}R_1</math><br />
| <math>-\frac{1}{4}R_1</math><br />
| <math>-\frac{1}{8}R_1</math><br />
|-<br />
! <math>T_2</math><br />
| <math>-\frac{1}{8}R_2</math><br />
| <math>-\frac{1}{4}R_2</math><br />
| <math>-\frac{1}{2}R_2</math><br />
| <math>-R_2</math><br />
|} <br />
<br />
<br />
For a multi-stage game the attacker can launch <math> t </math> attacks, one in each stage while defender can only stick with stage 1. The attacker may change target if the attack in stage 1 is failed. Three experiments are run with <math> n = 2, k = 5 </math> for games with single attack and double attack, i.e, <math> t = 1 </math> and <math> t = 2 </math>. The results of simulated experiments are shown below [1]:<br />
<br />
[[File:Security Game Results.png|500px ]]<br />
<br />
<br />
They learned <math> R_i </math> only based on observations of the defender’s actions and could still recover the game setting by only observing the defender’s actions. Same as expectation, the larger dataset size improves the learned parameters. Two outliers are 1) Security Game, the green plot for when <math> t = 2 </math>; and 2) RPS, when comparing between training sizes of 2000 and 5000.<br />
<br />
== Conclusion ==<br />
Unsurprisingly, the results of this study show that in general the quality of learned parameters improved as the number of observations increased. The network presented in this paper demonstrated improvement over existing methodology. <br />
<br />
This paper presents an end-to-end framework for implementing a game solver, for both extensive and normal form, as a module in a deep neural network for zero-sum games. This method, unlike many previous works in this area, does not require the parameters of the game to be known to the agent prior to the start of the game. The two-part method analytically computes both the optimal solution and the parameters of the game. Future work involves taking advantage of the KKT matrix structure to increase computation speed, and extensions to the area of learning general-sum games.<br />
<br />
== Critiques ==<br />
The proposed method appears to suffer from two flaws. Firstly, the assumption that players behave in accordance to the QRE severely limits the space of player strategies, and is known to exhibit pathological behaviour even in one-player settings. Second, the solvers are computationally inefficient and are unable to scale. For this setting, they used Newton's method and it is found that the second-order algorithms do not scale to large games as with Nash equilibrium [4]. <br />
<br />
This method of proposing that real players will follow a laid out scheme or playing strategy is almost always a drastic oversimplification of real world scenarios and severely limits the applications. In order to better fit a model to the real players, there almost always has to be some sort of stochastic implementation which accounts for the presence of irrational users in the system.<br />
<br />
== References ==<br />
<br />
[1] Ling, C. K., Fang, F., & Kolter, J. Z. (2018). What game are we playing? end-to-end learning in normal and extensive form games. arXiv preprint arXiv:1805.02777.<br />
<br />
[2] B. von Stengel. Efficient computation of behavior strategies.Games and Economics Behavior,14(0050):220–246, 1996.<br />
<br />
[3] Boyd, S., Boyd, S. P., & Vandenberghe, L. (2004). Convex optimization. Cambridge university press.<br />
<br />
[4] Farina, G., Kroer, C., & Sandholm, T. (2019). Online Convex Optimization for Sequential Decision Processes and Extensive-Form Games. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 1917-1925. https://doi.org/10.1609/aaai.v33i01.33011917</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=what_game_are_we_playing&diff=45998what game are we playing2020-11-23T03:24:18Z<p>J244yang: /* Critiques */</p>
<hr />
<div>== Authors == <br />
Yuxin Wang, Evan Peters, Yifan Mou, Sangeeth Kalaichanthiran <br />
<br />
== Introduction ==<br />
Recently, there have been many different studies of methods using AI to solve large-scale, zero-sum, extensive form problems. However, most of these works operate under the assumption that the parameters of the game are known, and the objective is just finding the optimal strategy for the game. This scenario is unrealistic since most of the time parameters of the game are unknown. This paper proposes a framework for finding an optimal solution using a primal-dual Newton Method and then using back-propagation to analytically compute the gradients of all the relevant game parameters.<br />
<br />
The approach to solving this problem is to consider ''quantal response equilibrium'' (QRE), which is a generalization of Nash equilibrium (NE) where the agents can make suboptimal decisions. It is shown that the solution to the QRE is a differentiable function of the payoff matrix. Consequently, back-propagation can be used to analytically solve for the payoff matrix (or other game parameters). This strategy has many future application areas as it allows for game-solving (both extensive and normal form) to be integrated as a module in a deep neural network.<br />
<br />
An example of architecture is presented below:<br />
<br />
[[File:Framework.png ]]<br />
<br />
Payoff matrix <math> P </math> is parameterized by a domain-dependent low dimensional vector <math> \phi </math>, where <math> \phi </math> depends on a differentiable function <math> M_1(x) </math>. Furthermore, <math> P </math> is applied to QRE to get the equilibrium strategies <math> (u^∗, v^∗) </math>. Lastly, the loss function is calculated after applying any differentiable <math> M_2(u^∗, v^∗) </math>.<br />
<br />
The effectiveness of this model is demonstrated using the games “Rock, Paper, Scissors”, one-card poker, and a security defense game.<br />
<br />
== Learning and Quantal Response in Normal Form Games ==<br />
<br />
The game-solving module provides all elements required in differentiable learning, which maps contextual features to payoff matrices, and computes equilibrium strategies under a set of contextual features. This paper will learn zero-sum games and start with normal form games since they have game solver and learning approach capturing much of intuition and basic methodology.<br />
<br />
=== Zero-Sum Normal Form Games ===<br />
<br />
In two-player zero-sum games there is a '''payoff matrix''' <math>P</math> that describes the rewards for two players employing specific strategies u and v respectively. The optimal strategy mixture may be found with a classic min-max formulation:<br />
$$\min_u \max_v \ u^T P v \\ subject \ to \ 1^T u =1, u \ge 0 \\ 1^T v =1, v \ge 0. \ $$<br />
<br />
Here, we consider the case where <math>P</math> is not known a priori. The solution <math> (u^*, v_0) </math> to this optimization and the solution <math> (u_0,v^*) </math> to the corresponding problem with inverse player order form the Nash equilibrium <math>(u^*,v^*) </math>. At this equilibrium, the players do not have anything to gain by changing their strategy, so this point is a stable state of the system. When the payoff matrix P is not known, we observe samples of actions <math> a^{(i)}, i =1,...,N </math> from one or both players, which depends on some external content <math> x </math>, sampled from the equilibrium strategies <math>(u^*,v^*) </math>, to recover the true underlying payoff matrix P or a function form P(x) depending on the current context.<br />
<br />
=== Quantal Response Equilibria ===<br />
<br />
However, NE is poorly suited because NEs are overly strict, discontinuous with respect to P, and may not be unique. To address these issues, model the players' actions with the '''quantal response equilibria''' (QRE), where noise is added to the payoff matric. Specifically, consider the ''logit'' equilibrium for zero-sum games that obeys the fixed point:<br />
$$<br />
u^* _i = \frac {exp(-Pv)_i}{\sum_{q \in [n]} exp (-Pv)_q}, \ v^* _j= \frac {exp(P^T u)_j}{\sum_{q \in [m]} exp (P^T u)_q} .\qquad \ (1)<br />
$$<br />
For a fixed opponent strategy, the logit equilibrium corresponding to a strategy is strictly convex, and thus the regularized best response is unique.<br />
<br />
=== End-to-End Learning ===<br />
<br />
Then to integrate zero-sum solver, [1] introduced a method to solve the QRE and to differentiate through its solution.<br />
<br />
'''QRE solver''':<br />
To find the fixed point in (1), it is equivalent to solve the regularized min-max game:<br />
$$<br />
\min_{u \in \mathbb{R}^n} \max_{v \in \mathbb{R}^m} \ u^T P v -H(v) + H(u) \\<br />
\text{subject to } 1^T u =1, \ 1^T v =1, <br />
$$<br />
where H(y) is the Gibbs entropy <math> \sum_i y_i log y_i</math>.<br />
Entropy regularization guarantees the non-negative condition and makes the equilibrium continuous with respect to P, which means players are encouraged to play more randomly, and all actions have non-zero probability. Moreover, this problem has a unique saddle point corresponding to <math> (u^*, v^*) </math>.<br />
<br />
Using a primal-dual Newton Method to solve the QRE for two-player zero-sum games, the KKT conditions for the problem are:<br />
$$ <br />
Pv + \log(u) + 1 +\mu 1 = 0 \\<br />
P^T v -\log(v) -1 +\nu 1 = 0 \\<br />
1^T u = 1, \ 1^T v = 1, <br />
$$<br />
where <math> (\mu, \nu) </math> are Lagrange multipliers for the equality constraints on u, v respectively. Then applying Newton's method gives the the update rule:<br />
$$<br />
Q \begin{bmatrix} \Delta u \\ \Delta v \\ \Delta \mu \\ \Delta \nu \\ \end{bmatrix} = - \begin{bmatrix} P v + \log u + 1 + \mu 1 \\ P^T u - \log v - 1 + \nu 1 \\ 1^T u - 1 \\ 1^T v - 1 \\ \end{bmatrix}, \qquad (2)<br />
$$<br />
where Q is the Hessian of the Lagrangian, given by <br />
$$ <br />
Q = \begin{bmatrix} <br />
diag(\frac{1}{u}) & P & 1 & 0 \\ <br />
P^T & -diag(\frac{1}{v}) & 0 & 1\\<br />
1^T & 0 & 0 & 0 \\<br />
0 & 1^T & 0 & 0 \\<br />
\end{bmatrix}. <br />
$$<br />
<br />
'''Differentiating Through QRE Solutions''':<br />
The QRE solver provides a method to compute the necessary Jacobian-vector products. Specifically, we compute the gradient of the loss given the solution <math> (u^*,v^*) </math> to the QRE, and some loss function <math> L(u^*,v^*) </math>: <br />
<br />
1. Take differentials of the KKT conditions: <br />
<math><br />
Q \begin{bmatrix} <br />
du & dv & d\mu & d\nu \\ <br />
\end{bmatrix} ^T = \begin{bmatrix} <br />
-dPv & -dP^Tu & 0 & 0 \\ <br />
\end{bmatrix}^T. \ <br />
</math><br />
<br />
2. For small changes du, dv, <br />
<math><br />
dL = \begin{bmatrix} <br />
v^TdP^T & u^TdP & 0 & 0 \\ <br />
\end{bmatrix} Q^{-1} \begin{bmatrix} <br />
-\nabla_u L & -\nabla_v L & 0 & 0 \\ <br />
\end{bmatrix}^T.<br />
</math><br />
<br />
3. Apply this to P, and take limits as dP is small:<br />
<math><br />
\nabla_P L = y_u v^T + u y_v^T, \qquad (3)<br />
</math> where <br />
<math><br />
\begin{bmatrix} <br />
y_u & y_v & y_{\mu} & y_{\nu}\\ <br />
\end{bmatrix}=Q^{-1}\begin{bmatrix} <br />
-\nabla_u L & -\nabla_v L & 0 & 0 \\ <br />
\end{bmatrix}^T.<br />
</math><br />
<br />
Hence, the forward pass is given by using the expression in (2) to solve for the logit equilibrium given P, and the backward pass is given by using <math> \nabla_u L </math> and <math> \nabla_v L </math> to obtain <math> \nabla_P L </math> using (3). There does not always exist a unique P which generates <math> u^*, v^* </math> under the logit QRE, and we cannot expect to recover P when under-constrained.<br />
<br />
== Learning Extensive form games ==<br />
<br />
The normal form representation for games where players have many choices quickly becomes intractable. For example, consider a chess game: One the first turn, player 1 has 20 possible moves and then player 2 has 20 possible responses. If in the following number of turns each player is estimated to have ~30 possible moves and if a typical game is 40 moves per player, the total number of strategies is roughly <math>10^{120} </math> per player (this is known as the Shannon number for game-tree complexity of chess) and so the payoff matrix for a typical game of chess must therefore have <math> O(10^{240}) </math> entries.<br />
<br />
Instead, it is much more useful to represent the game graphically as an "'''Extensive form game'''" (EFG). We'll also need to consider types of games where there is '''imperfect information''' - players do not necessarily have access to the full state of the game. An example of this is one-card poker: (1) Each player draws a single card from a 13-card deck (ignore suits) (2) Player 1 decides whether to bet/hold (3) Player 2 decides whether to call/raise (4) Player 1 must either call/fold if Player 2 raised. From this description, player 1 has <math> 2^{13} </math> possible first moves (all combinations of (card, raise/hold)) and has <math> 2^{13} </math> possible second moves (whenever player 1 gets a second move) for a total of <math> 2^{26} </math> possible strategies. In addition, Player 1 never knows what cards player 2 has and vice versa. So instead of representing the game with a huge payoff matrix we can instead represent it as a simple decision tree (for a ''single'' drawn card of player 1):<br />
<br />
<br />
<center> [[File:1cardpoker.PNG]] </center><br />
<br />
where player 1 is represented by "1", a node that has two branches corresponding to the allowed moves of player 1. However there must also be a notion of information available to either player: While this tree might correspond to say, player 1 holding a "9", it contains no information on what card player 2 is holding (and is much simpler because of this). This leads to the definition of an '''information set''': the set of all nodes belonging to a single player for which the other player cannot distinguish which node has been reached. The information set may therefore be treated as a node itself, for which actions stemming from the node must be chosen in ignorance to what the other player did immediately before arriving at the node. In the poker example, the full game tree consists of a much more complex version of the tree shown above (containing repetitions of the given tree for every possible combination of cards dealt) and the and an example of an information set for player 1 is the set of all of nodes owned by player 2 that immediately follow player 1's decision to hold. In other words, if player 1 holds there are 13 possible nodes describing the responses of player 2 (raise/hold for player 2 having card = ace, 1, ... King) and all 13 of these nodes are indistinguishable to player 1, and so form an information set for player 1.<br />
<br />
The following is a review of important concepts for extensive form games first formalized in [2]. Let <math> \mathcal{I}_i </math> be the set of all information sets for player i, and for each <math> t \in \mathcal{I}_i </math> let <math> \sigma_t </math> be the actions taken by player i to arrive at <math> t </math> and <math> C_t </math> be the actions that player i can take from <math> u </math>. Then the set of all possible sequences that can be taken by player i is given by<br />
<br />
$$<br />
S_i = \{\emptyset \} \cup \{ \sigma_t c | u\in \mathcal{I}_i, c \in C_t \}<br />
$$<br />
<br />
So for the one-card poker we would have <math>S_1 = \{\emptyset, \text{raise}, \text{hold}, \text{hold-call}, \text{hold-fold\} }</math>. From the possible sequences follows two important concepts:<br />
<ol><br />
<li>The EFG '''payoff matrix''' <math> P </math> of size <math>|S_1| \times |S_2| </math> (this is all possible actions available to either player), is populated with rewards from each leaf of the tree (or "zero" for each <math> (s_1, s_2) </math> that is an invalid pair), and the expected payoff for realization plans <math> (u, v) </math> is given by <math> u^T P v </math> </li><br />
<li> A '''realization plan''' <math> u \in \mathbb{R}^{|S_1|} </math> for player 1 (<math> v \in \mathbb{R}^{|S_2|} </math> for player 2 ) will describe probabilities for players to carry out each possible sequence, and each realization plan must be constrained by (i) compatibility of sequences (e.g. "raise" is not compatible with "hold-call") and (ii) information sets available to the player. These constraints are linear:<br />
<br />
$$<br />
Eu = e \\<br />
Fv = f<br />
$$<br />
<br />
where <math> e = f = (1, 0, ..., 0)^T </math> and <math> E, F</math> contain entries in <math> {-1, 0, 1} </math> describing compatibility and information sets. </li><br />
<br />
</ol> <br />
<br />
<br />
The paper's main contribution is to develop a minmax problem for extensive form games:<br />
<br />
<br />
$$<br />
\min_u \max_v u^T P v + \sum_{t\in \mathcal{I}_1} \sum_{c \in C_t} u_c \log \frac{u_c}{u_{p_t}} - \sum_{t\in \mathcal{I}_2} \sum_{c \in C_t} v_c \log \frac{v_c}{v_{p_t}}<br />
$$<br />
<br />
where <math> p_t </math> is the action immediately preceding information set <math> t </math>. Intuitively, each sum resembles a cross entropy over the distribution of probabilities in the realization plan comparing each probability to proceed from an information set to the probability to arrive at that information set. Importantly, these entropies are strictly convex or concave (for player 1 and player 2 respectively) [3] so that the minmax problem will have a unique solution and ''the objective function is continuous and continuously differentiable'' - this means there is a way to optimize the function. As noted in Theorem 1 of [1], the solution to this problem is equivalently a solution for the QRE of the game in reduced normal form.<br />
<br />
Minmax can also be seen from an algorithmic perspective. Referring to the above figure containing a tree, it contains a sequence of states and action which alternates between two or more competing players. The above formulation of the minmax problem essentially measures how well a decision rule is from the perspective of a single player. To describe it in terms of the tree, if it is player 1's turn, then it is a mutual recursion of player 1 choosing to maximize its payoff and player 2 choosing to minimize player 1's payoff.<br />
<br />
Having decided on a cost function, the method of Lagrange multipliers may be used to construct the Lagrangian that encodes the known constraints (<math> Eu = e \,, Fv = f </math>, and <math> u, v \geq 0</math>), and then optimize the Lagrangian using Newton's method (identically to the previous section). Accounting for the constraints, the Lagrangian becomes <br />
<br />
<br />
$$<br />
\mathcal{L} = g(u, v) + \sum_i \mu_i(Eu - e)_i + \sum_i \nu_i (Fv - f)_i<br />
$$<br />
<br />
where <math>g</math> is the argument from the minmax statement above and <math>u, v \geq 0</math> become KKT conditions. The general update rule for Newton's method may be written in terms of the derivatives of <math> \mathcal{L} </math> with respect to primal variables <math>u, v </math> and dual variables <math> \mu, \nu</math>, yielding:<br />
<br />
$$<br />
\nabla_{u,v,\mu,\nu}^2 \mathcal{L} \cdot (\Delta u, \Delta v, \Delta \mu, \Delta \nu)^T= - \nabla_{u,v,\mu,\nu} \mathcal{L}<br />
$$<br />
where <math>\nabla_{u,v,\mu,\nu}^2 \mathcal{L} </math> is the Hessian of the Lagrangian and <math>\nabla_{u,v,\mu,\nu} \mathcal{L} </math> is simply a column vector of the KKT stationarity conditions. Combined with the previous section, this completes the goal of the paper: To construct a differentiable problem for learning normal form and extensive form games.<br />
<br />
== Experiments ==<br />
<br />
The authors demonstrated learning on extensive form games in the presence of ''side information'', with ''partial observations'' using three experiments. In all cases, the goal was to maximize the likelihood of realizing an observed sequence from the player, assuming they act in accordance to the QRE. The authors found that the best way to implement the module was to use a medium to large batch size, RMSProp, or Adam optimizers with a learning rate between <math>\left[0.0001,0.01\right].</math> <br />
<br />
=== Rock, Paper, Scissors ===<br />
<br />
Rock, Paper, Scissors is a 2-player zero-sum game. For this game, the best strategy to reach a Nash equilibrium and a Quantal response equilibrium is to uniformly play each hand with equal odds.<br />
The first experiment was to learn a non-symmetric variant of Rock, Paper, Scissors with ''incomplete information'' with the following payoff matrix:<br />
<br />
{| class="wikitable" style="float:center; margin-left:1em; text-align:center;"<br />
|+ align="bottom"|''Payoff matrix of modified Rock-Paper-Scissors''<br />
! <br />
! ''Rock''<br />
! ''Paper''<br />
! ''Scissors''<br />
|-<br />
! ''Rock''<br />
| '''''0'''''<br />
| <math>-b_1</math><br />
| <math>b_2</math><br />
|-<br />
! ''Paper''<br />
| <math>b_1</math><br />
| '''''0'''''<br />
| <math>-b_3</math><br />
|-<br />
! ''Scissors''<br />
| <math>-b_2</math><br />
| <math>b_3</math><br />
| '''''0'''''<br />
|}<br />
<br />
where each of the <math> b </math> ’s are linear function of some features <math> x \in \mathbb{R}^{2} </math> (i.e., <math> b_y = x^Tw_y </math>, <math> y \in </math> {<math>1,2,3</math>} , where <math> w_y </math> are to be learned by the algorithm). Using many trials of random rewards the technique produced the following results for optimal strategies[1]: <br />
<br />
[[File:RPS Results.png|500px ]]<br />
<br />
From the graphs above, we can tell the following: 1) both parameters learned and predicted strategies improve with larger dataset; and 2) with a reasonably sized dataset, >1000 here, convergence is stable and is fairly quick.<br />
<br />
=== One-Card Poker ===<br />
<br />
Next they investigated extensive form games using the one-Card Poker (with ''imperfect information'') introduced in the previous section. In the experimental setup, they used a deck stacked non-uniformly (meaning repeat cards were allowed). Their goal was to learn this distribution of cards from observations of many rounds of the play. Different from the distribution of cards dealt, the method built in the paper is more suited to learn the player’s perceived or believed distribution of cards. It may even be a function of contextual features such as demographics of players. Three experiments were run with <math> n=4 </math>. Each experiment comprised 5 runs of training, with same weights but different training sets. Let <math> d \in \mathbb{R}^{n}, d \ge 0, \sum_{i} d_i = 1 </math> be the weights of the cards. The probability that the players are dealt cards <math> (i,j) </math> is <math> \frac{d_i d_j}{1-d_i} </math>. This distribution is asymmetric between players. Matrix <math> P, E, F </math> for the case <math> n=4 </math> are presented in [1]. With training for 2500 epochs, the mean squared error of learned parameters (card weights, <math> u, v </math> ) are averaged over all runs of and are presented as following [1]: <br />
<br />
<br />
[[File:One-card_Poker_Results.png|500px ]]<br />
<br />
=== Security Resource Allocation Game ===<br />
<br />
<br />
From Security Resource Allocation Game, they demonstrated the ability to learn from ''imperfect observations''. The defender possesses <math> k </math> indistinguishable and indivisible defensive resources which he splits among <math> n </math> targets, { <math> T_1, ……, T_n </math>}. The attacker chooses one target. If the attack succeeds, the attacker gets <math> R_i </math> reward and defender gets <math> -R_i </math>, otherwise zero payoff for both. If there are n defenders guarding <math> T_i </math>, probability of successful attack on <math> T_i </math> is <math> \frac{1}{2^n} </math>. The expected payoff matrix when <math> n = 2, k = 3 </math>, where the attackers are the row players is:<br />
<br />
{| class="wikitable" style="float:center; margin-left:1em; text-align:center;"<br />
|+ align="bottom"|''Payoff matrix when <math> n = 2, k = 3 </math>''<br />
! {#<math>D_1</math>,#<math>D_2</math>}<br />
! {0, 3}<br />
! {1, 2}<br />
! {2, 1}<br />
! {3, 0}<br />
|-<br />
! <math>T_1</math><br />
| <math>-R_1</math><br />
| <math>-\frac{1}{2}R_1</math><br />
| <math>-\frac{1}{4}R_1</math><br />
| <math>-\frac{1}{8}R_1</math><br />
|-<br />
! <math>T_2</math><br />
| <math>-\frac{1}{8}R_2</math><br />
| <math>-\frac{1}{4}R_2</math><br />
| <math>-\frac{1}{2}R_2</math><br />
| <math>-R_2</math><br />
|} <br />
<br />
<br />
For a multi-stage game the attacker can launch <math> t </math> attacks, one in each stage while defender can only stick with stage 1. The attacker may change target if the attack in stage 1 is failed. Three experiments are run with <math> n = 2, k = 5 </math> for games with single attack and double attack, i.e, <math> t = 1 </math> and <math> t = 2 </math>. The results of simulated experiments are shown below [1]:<br />
<br />
[[File:Security Game Results.png|500px ]]<br />
<br />
<br />
They learned <math> R_i </math> only based on observations of the defender’s actions and could still recover the game setting by only observing the defender’s actions. Same as expectation, the larger dataset size improves the learned parameters. Two outliers are 1) Security Game, the green plot for when <math> t = 2 </math>; and 2) RPS, when comparing between training sizes of 2000 and 5000.<br />
<br />
== Conclusion ==<br />
Unsurprisingly, the results of this study show that in general the quality of learned parameters improved as the number of observations increased. The network presented in this paper demonstrated improvement over existing methodology. <br />
<br />
This paper presents an end-to-end framework for implementing a game solver, for both extensive and normal form, as a module in a deep neural network for zero-sum games. This method, unlike many previous works in this area, does not require the parameters of the game to be known to the agent prior to the start of the game. The two-part method analytically computes both the optimal solution and the parameters of the game. Future work involves taking advantage of the KKT matrix structure to increase computation speed, and extensions to the area of learning general-sum games.<br />
<br />
== Critiques ==<br />
The proposed method appears to suffer from two flaws. Firstly, the assumption that players behave in accordance to the QRE severely limits the space of player strategies, and is known to exhibit pathological behaviour even in one-player settings. Second, the solvers are computationally inefficient and are unable to scale. For this setting, they used Newton's method and it is found that the second-order algorithms do not scale to large games as with Nash equilibrium [4]. <br />
<br />
This method of proposing that real players will follow a laid out scheme or playing strategy is almost always a drastic oversimplification of real world scenarios and severely limits the applications. In order to better fit a model to the real players, there almost always has to be some sort of stochastic implementation which accounts for the presence of irrational users in the system.<br />
<br />
== References ==<br />
<br />
[1] Ling, C. K., Fang, F., & Kolter, J. Z. (2018). What game are we playing? end-to-end learning in normal and extensive form games. arXiv preprint arXiv:1805.02777.<br />
<br />
[2] B. von Stengel. Efficient computation of behavior strategies.Games and Economics Behavior,14(0050):220–246, 1996.<br />
<br />
[3] Boyd, S., Boyd, S. P., & Vandenberghe, L. (2004). Convex optimization. Cambridge university press.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=what_game_are_we_playing&diff=45997what game are we playing2020-11-23T03:24:06Z<p>J244yang: /* Critiques */</p>
<hr />
<div>== Authors == <br />
Yuxin Wang, Evan Peters, Yifan Mou, Sangeeth Kalaichanthiran <br />
<br />
== Introduction ==<br />
Recently, there have been many different studies of methods using AI to solve large-scale, zero-sum, extensive form problems. However, most of these works operate under the assumption that the parameters of the game are known, and the objective is just finding the optimal strategy for the game. This scenario is unrealistic since most of the time parameters of the game are unknown. This paper proposes a framework for finding an optimal solution using a primal-dual Newton Method and then using back-propagation to analytically compute the gradients of all the relevant game parameters.<br />
<br />
The approach to solving this problem is to consider ''quantal response equilibrium'' (QRE), which is a generalization of Nash equilibrium (NE) where the agents can make suboptimal decisions. It is shown that the solution to the QRE is a differentiable function of the payoff matrix. Consequently, back-propagation can be used to analytically solve for the payoff matrix (or other game parameters). This strategy has many future application areas as it allows for game-solving (both extensive and normal form) to be integrated as a module in a deep neural network.<br />
<br />
An example of architecture is presented below:<br />
<br />
[[File:Framework.png ]]<br />
<br />
Payoff matrix <math> P </math> is parameterized by a domain-dependent low dimensional vector <math> \phi </math>, where <math> \phi </math> depends on a differentiable function <math> M_1(x) </math>. Furthermore, <math> P </math> is applied to QRE to get the equilibrium strategies <math> (u^∗, v^∗) </math>. Lastly, the loss function is calculated after applying any differentiable <math> M_2(u^∗, v^∗) </math>.<br />
<br />
The effectiveness of this model is demonstrated using the games “Rock, Paper, Scissors”, one-card poker, and a security defense game.<br />
<br />
== Learning and Quantal Response in Normal Form Games ==<br />
<br />
The game-solving module provides all elements required in differentiable learning, which maps contextual features to payoff matrices, and computes equilibrium strategies under a set of contextual features. This paper will learn zero-sum games and start with normal form games since they have game solver and learning approach capturing much of intuition and basic methodology.<br />
<br />
=== Zero-Sum Normal Form Games ===<br />
<br />
In two-player zero-sum games there is a '''payoff matrix''' <math>P</math> that describes the rewards for two players employing specific strategies u and v respectively. The optimal strategy mixture may be found with a classic min-max formulation:<br />
$$\min_u \max_v \ u^T P v \\ subject \ to \ 1^T u =1, u \ge 0 \\ 1^T v =1, v \ge 0. \ $$<br />
<br />
Here, we consider the case where <math>P</math> is not known a priori. The solution <math> (u^*, v_0) </math> to this optimization and the solution <math> (u_0,v^*) </math> to the corresponding problem with inverse player order form the Nash equilibrium <math>(u^*,v^*) </math>. At this equilibrium, the players do not have anything to gain by changing their strategy, so this point is a stable state of the system. When the payoff matrix P is not known, we observe samples of actions <math> a^{(i)}, i =1,...,N </math> from one or both players, which depends on some external content <math> x </math>, sampled from the equilibrium strategies <math>(u^*,v^*) </math>, to recover the true underlying payoff matrix P or a function form P(x) depending on the current context.<br />
<br />
=== Quantal Response Equilibria ===<br />
<br />
However, NE is poorly suited because NEs are overly strict, discontinuous with respect to P, and may not be unique. To address these issues, model the players' actions with the '''quantal response equilibria''' (QRE), where noise is added to the payoff matric. Specifically, consider the ''logit'' equilibrium for zero-sum games that obeys the fixed point:<br />
$$<br />
u^* _i = \frac {exp(-Pv)_i}{\sum_{q \in [n]} exp (-Pv)_q}, \ v^* _j= \frac {exp(P^T u)_j}{\sum_{q \in [m]} exp (P^T u)_q} .\qquad \ (1)<br />
$$<br />
For a fixed opponent strategy, the logit equilibrium corresponding to a strategy is strictly convex, and thus the regularized best response is unique.<br />
<br />
=== End-to-End Learning ===<br />
<br />
Then to integrate zero-sum solver, [1] introduced a method to solve the QRE and to differentiate through its solution.<br />
<br />
'''QRE solver''':<br />
To find the fixed point in (1), it is equivalent to solve the regularized min-max game:<br />
$$<br />
\min_{u \in \mathbb{R}^n} \max_{v \in \mathbb{R}^m} \ u^T P v -H(v) + H(u) \\<br />
\text{subject to } 1^T u =1, \ 1^T v =1, <br />
$$<br />
where H(y) is the Gibbs entropy <math> \sum_i y_i log y_i</math>.<br />
Entropy regularization guarantees the non-negative condition and makes the equilibrium continuous with respect to P, which means players are encouraged to play more randomly, and all actions have non-zero probability. Moreover, this problem has a unique saddle point corresponding to <math> (u^*, v^*) </math>.<br />
<br />
Using a primal-dual Newton Method to solve the QRE for two-player zero-sum games, the KKT conditions for the problem are:<br />
$$ <br />
Pv + \log(u) + 1 +\mu 1 = 0 \\<br />
P^T v -\log(v) -1 +\nu 1 = 0 \\<br />
1^T u = 1, \ 1^T v = 1, <br />
$$<br />
where <math> (\mu, \nu) </math> are Lagrange multipliers for the equality constraints on u, v respectively. Then applying Newton's method gives the the update rule:<br />
$$<br />
Q \begin{bmatrix} \Delta u \\ \Delta v \\ \Delta \mu \\ \Delta \nu \\ \end{bmatrix} = - \begin{bmatrix} P v + \log u + 1 + \mu 1 \\ P^T u - \log v - 1 + \nu 1 \\ 1^T u - 1 \\ 1^T v - 1 \\ \end{bmatrix}, \qquad (2)<br />
$$<br />
where Q is the Hessian of the Lagrangian, given by <br />
$$ <br />
Q = \begin{bmatrix} <br />
diag(\frac{1}{u}) & P & 1 & 0 \\ <br />
P^T & -diag(\frac{1}{v}) & 0 & 1\\<br />
1^T & 0 & 0 & 0 \\<br />
0 & 1^T & 0 & 0 \\<br />
\end{bmatrix}. <br />
$$<br />
<br />
'''Differentiating Through QRE Solutions''':<br />
The QRE solver provides a method to compute the necessary Jacobian-vector products. Specifically, we compute the gradient of the loss given the solution <math> (u^*,v^*) </math> to the QRE, and some loss function <math> L(u^*,v^*) </math>: <br />
<br />
1. Take differentials of the KKT conditions: <br />
<math><br />
Q \begin{bmatrix} <br />
du & dv & d\mu & d\nu \\ <br />
\end{bmatrix} ^T = \begin{bmatrix} <br />
-dPv & -dP^Tu & 0 & 0 \\ <br />
\end{bmatrix}^T. \ <br />
</math><br />
<br />
2. For small changes du, dv, <br />
<math><br />
dL = \begin{bmatrix} <br />
v^TdP^T & u^TdP & 0 & 0 \\ <br />
\end{bmatrix} Q^{-1} \begin{bmatrix} <br />
-\nabla_u L & -\nabla_v L & 0 & 0 \\ <br />
\end{bmatrix}^T.<br />
</math><br />
<br />
3. Apply this to P, and take limits as dP is small:<br />
<math><br />
\nabla_P L = y_u v^T + u y_v^T, \qquad (3)<br />
</math> where <br />
<math><br />
\begin{bmatrix} <br />
y_u & y_v & y_{\mu} & y_{\nu}\\ <br />
\end{bmatrix}=Q^{-1}\begin{bmatrix} <br />
-\nabla_u L & -\nabla_v L & 0 & 0 \\ <br />
\end{bmatrix}^T.<br />
</math><br />
<br />
Hence, the forward pass is given by using the expression in (2) to solve for the logit equilibrium given P, and the backward pass is given by using <math> \nabla_u L </math> and <math> \nabla_v L </math> to obtain <math> \nabla_P L </math> using (3). There does not always exist a unique P which generates <math> u^*, v^* </math> under the logit QRE, and we cannot expect to recover P when under-constrained.<br />
<br />
== Learning Extensive form games ==<br />
<br />
The normal form representation for games where players have many choices quickly becomes intractable. For example, consider a chess game: One the first turn, player 1 has 20 possible moves and then player 2 has 20 possible responses. If in the following number of turns each player is estimated to have ~30 possible moves and if a typical game is 40 moves per player, the total number of strategies is roughly <math>10^{120} </math> per player (this is known as the Shannon number for game-tree complexity of chess) and so the payoff matrix for a typical game of chess must therefore have <math> O(10^{240}) </math> entries.<br />
<br />
Instead, it is much more useful to represent the game graphically as an "'''Extensive form game'''" (EFG). We'll also need to consider types of games where there is '''imperfect information''' - players do not necessarily have access to the full state of the game. An example of this is one-card poker: (1) Each player draws a single card from a 13-card deck (ignore suits) (2) Player 1 decides whether to bet/hold (3) Player 2 decides whether to call/raise (4) Player 1 must either call/fold if Player 2 raised. From this description, player 1 has <math> 2^{13} </math> possible first moves (all combinations of (card, raise/hold)) and has <math> 2^{13} </math> possible second moves (whenever player 1 gets a second move) for a total of <math> 2^{26} </math> possible strategies. In addition, Player 1 never knows what cards player 2 has and vice versa. So instead of representing the game with a huge payoff matrix we can instead represent it as a simple decision tree (for a ''single'' drawn card of player 1):<br />
<br />
<br />
<center> [[File:1cardpoker.PNG]] </center><br />
<br />
where player 1 is represented by "1", a node that has two branches corresponding to the allowed moves of player 1. However there must also be a notion of information available to either player: While this tree might correspond to say, player 1 holding a "9", it contains no information on what card player 2 is holding (and is much simpler because of this). This leads to the definition of an '''information set''': the set of all nodes belonging to a single player for which the other player cannot distinguish which node has been reached. The information set may therefore be treated as a node itself, for which actions stemming from the node must be chosen in ignorance to what the other player did immediately before arriving at the node. In the poker example, the full game tree consists of a much more complex version of the tree shown above (containing repetitions of the given tree for every possible combination of cards dealt) and the and an example of an information set for player 1 is the set of all of nodes owned by player 2 that immediately follow player 1's decision to hold. In other words, if player 1 holds there are 13 possible nodes describing the responses of player 2 (raise/hold for player 2 having card = ace, 1, ... King) and all 13 of these nodes are indistinguishable to player 1, and so form an information set for player 1.<br />
<br />
The following is a review of important concepts for extensive form games first formalized in [2]. Let <math> \mathcal{I}_i </math> be the set of all information sets for player i, and for each <math> t \in \mathcal{I}_i </math> let <math> \sigma_t </math> be the actions taken by player i to arrive at <math> t </math> and <math> C_t </math> be the actions that player i can take from <math> u </math>. Then the set of all possible sequences that can be taken by player i is given by<br />
<br />
$$<br />
S_i = \{\emptyset \} \cup \{ \sigma_t c | u\in \mathcal{I}_i, c \in C_t \}<br />
$$<br />
<br />
So for the one-card poker we would have <math>S_1 = \{\emptyset, \text{raise}, \text{hold}, \text{hold-call}, \text{hold-fold\} }</math>. From the possible sequences follows two important concepts:<br />
<ol><br />
<li>The EFG '''payoff matrix''' <math> P </math> of size <math>|S_1| \times |S_2| </math> (this is all possible actions available to either player), is populated with rewards from each leaf of the tree (or "zero" for each <math> (s_1, s_2) </math> that is an invalid pair), and the expected payoff for realization plans <math> (u, v) </math> is given by <math> u^T P v </math> </li><br />
<li> A '''realization plan''' <math> u \in \mathbb{R}^{|S_1|} </math> for player 1 (<math> v \in \mathbb{R}^{|S_2|} </math> for player 2 ) will describe probabilities for players to carry out each possible sequence, and each realization plan must be constrained by (i) compatibility of sequences (e.g. "raise" is not compatible with "hold-call") and (ii) information sets available to the player. These constraints are linear:<br />
<br />
$$<br />
Eu = e \\<br />
Fv = f<br />
$$<br />
<br />
where <math> e = f = (1, 0, ..., 0)^T </math> and <math> E, F</math> contain entries in <math> {-1, 0, 1} </math> describing compatibility and information sets. </li><br />
<br />
</ol> <br />
<br />
<br />
The paper's main contribution is to develop a minmax problem for extensive form games:<br />
<br />
<br />
$$<br />
\min_u \max_v u^T P v + \sum_{t\in \mathcal{I}_1} \sum_{c \in C_t} u_c \log \frac{u_c}{u_{p_t}} - \sum_{t\in \mathcal{I}_2} \sum_{c \in C_t} v_c \log \frac{v_c}{v_{p_t}}<br />
$$<br />
<br />
where <math> p_t </math> is the action immediately preceding information set <math> t </math>. Intuitively, each sum resembles a cross entropy over the distribution of probabilities in the realization plan comparing each probability to proceed from an information set to the probability to arrive at that information set. Importantly, these entropies are strictly convex or concave (for player 1 and player 2 respectively) [3] so that the minmax problem will have a unique solution and ''the objective function is continuous and continuously differentiable'' - this means there is a way to optimize the function. As noted in Theorem 1 of [1], the solution to this problem is equivalently a solution for the QRE of the game in reduced normal form.<br />
<br />
Minmax can also be seen from an algorithmic perspective. Referring to the above figure containing a tree, it contains a sequence of states and action which alternates between two or more competing players. The above formulation of the minmax problem essentially measures how well a decision rule is from the perspective of a single player. To describe it in terms of the tree, if it is player 1's turn, then it is a mutual recursion of player 1 choosing to maximize its payoff and player 2 choosing to minimize player 1's payoff.<br />
<br />
Having decided on a cost function, the method of Lagrange multipliers may be used to construct the Lagrangian that encodes the known constraints (<math> Eu = e \,, Fv = f </math>, and <math> u, v \geq 0</math>), and then optimize the Lagrangian using Newton's method (identically to the previous section). Accounting for the constraints, the Lagrangian becomes <br />
<br />
<br />
$$<br />
\mathcal{L} = g(u, v) + \sum_i \mu_i(Eu - e)_i + \sum_i \nu_i (Fv - f)_i<br />
$$<br />
<br />
where <math>g</math> is the argument from the minmax statement above and <math>u, v \geq 0</math> become KKT conditions. The general update rule for Newton's method may be written in terms of the derivatives of <math> \mathcal{L} </math> with respect to primal variables <math>u, v </math> and dual variables <math> \mu, \nu</math>, yielding:<br />
<br />
$$<br />
\nabla_{u,v,\mu,\nu}^2 \mathcal{L} \cdot (\Delta u, \Delta v, \Delta \mu, \Delta \nu)^T= - \nabla_{u,v,\mu,\nu} \mathcal{L}<br />
$$<br />
where <math>\nabla_{u,v,\mu,\nu}^2 \mathcal{L} </math> is the Hessian of the Lagrangian and <math>\nabla_{u,v,\mu,\nu} \mathcal{L} </math> is simply a column vector of the KKT stationarity conditions. Combined with the previous section, this completes the goal of the paper: To construct a differentiable problem for learning normal form and extensive form games.<br />
<br />
== Experiments ==<br />
<br />
The authors demonstrated learning on extensive form games in the presence of ''side information'', with ''partial observations'' using three experiments. In all cases, the goal was to maximize the likelihood of realizing an observed sequence from the player, assuming they act in accordance to the QRE. The authors found that the best way to implement the module was to use a medium to large batch size, RMSProp, or Adam optimizers with a learning rate between <math>\left[0.0001,0.01\right].</math> <br />
<br />
=== Rock, Paper, Scissors ===<br />
<br />
Rock, Paper, Scissors is a 2-player zero-sum game. For this game, the best strategy to reach a Nash equilibrium and a Quantal response equilibrium is to uniformly play each hand with equal odds.<br />
The first experiment was to learn a non-symmetric variant of Rock, Paper, Scissors with ''incomplete information'' with the following payoff matrix:<br />
<br />
{| class="wikitable" style="float:center; margin-left:1em; text-align:center;"<br />
|+ align="bottom"|''Payoff matrix of modified Rock-Paper-Scissors''<br />
! <br />
! ''Rock''<br />
! ''Paper''<br />
! ''Scissors''<br />
|-<br />
! ''Rock''<br />
| '''''0'''''<br />
| <math>-b_1</math><br />
| <math>b_2</math><br />
|-<br />
! ''Paper''<br />
| <math>b_1</math><br />
| '''''0'''''<br />
| <math>-b_3</math><br />
|-<br />
! ''Scissors''<br />
| <math>-b_2</math><br />
| <math>b_3</math><br />
| '''''0'''''<br />
|}<br />
<br />
where each of the <math> b </math> ’s are linear function of some features <math> x \in \mathbb{R}^{2} </math> (i.e., <math> b_y = x^Tw_y </math>, <math> y \in </math> {<math>1,2,3</math>} , where <math> w_y </math> are to be learned by the algorithm). Using many trials of random rewards the technique produced the following results for optimal strategies[1]: <br />
<br />
[[File:RPS Results.png|500px ]]<br />
<br />
From the graphs above, we can tell the following: 1) both parameters learned and predicted strategies improve with larger dataset; and 2) with a reasonably sized dataset, >1000 here, convergence is stable and is fairly quick.<br />
<br />
=== One-Card Poker ===<br />
<br />
Next they investigated extensive form games using the one-Card Poker (with ''imperfect information'') introduced in the previous section. In the experimental setup, they used a deck stacked non-uniformly (meaning repeat cards were allowed). Their goal was to learn this distribution of cards from observations of many rounds of the play. Different from the distribution of cards dealt, the method built in the paper is more suited to learn the player’s perceived or believed distribution of cards. It may even be a function of contextual features such as demographics of players. Three experiments were run with <math> n=4 </math>. Each experiment comprised 5 runs of training, with same weights but different training sets. Let <math> d \in \mathbb{R}^{n}, d \ge 0, \sum_{i} d_i = 1 </math> be the weights of the cards. The probability that the players are dealt cards <math> (i,j) </math> is <math> \frac{d_i d_j}{1-d_i} </math>. This distribution is asymmetric between players. Matrix <math> P, E, F </math> for the case <math> n=4 </math> are presented in [1]. With training for 2500 epochs, the mean squared error of learned parameters (card weights, <math> u, v </math> ) are averaged over all runs of and are presented as following [1]: <br />
<br />
<br />
[[File:One-card_Poker_Results.png|500px ]]<br />
<br />
=== Security Resource Allocation Game ===<br />
<br />
<br />
From Security Resource Allocation Game, they demonstrated the ability to learn from ''imperfect observations''. The defender possesses <math> k </math> indistinguishable and indivisible defensive resources which he splits among <math> n </math> targets, { <math> T_1, ……, T_n </math>}. The attacker chooses one target. If the attack succeeds, the attacker gets <math> R_i </math> reward and defender gets <math> -R_i </math>, otherwise zero payoff for both. If there are n defenders guarding <math> T_i </math>, probability of successful attack on <math> T_i </math> is <math> \frac{1}{2^n} </math>. The expected payoff matrix when <math> n = 2, k = 3 </math>, where the attackers are the row players is:<br />
<br />
{| class="wikitable" style="float:center; margin-left:1em; text-align:center;"<br />
|+ align="bottom"|''Payoff matrix when <math> n = 2, k = 3 </math>''<br />
! {#<math>D_1</math>,#<math>D_2</math>}<br />
! {0, 3}<br />
! {1, 2}<br />
! {2, 1}<br />
! {3, 0}<br />
|-<br />
! <math>T_1</math><br />
| <math>-R_1</math><br />
| <math>-\frac{1}{2}R_1</math><br />
| <math>-\frac{1}{4}R_1</math><br />
| <math>-\frac{1}{8}R_1</math><br />
|-<br />
! <math>T_2</math><br />
| <math>-\frac{1}{8}R_2</math><br />
| <math>-\frac{1}{4}R_2</math><br />
| <math>-\frac{1}{2}R_2</math><br />
| <math>-R_2</math><br />
|} <br />
<br />
<br />
For a multi-stage game the attacker can launch <math> t </math> attacks, one in each stage while defender can only stick with stage 1. The attacker may change target if the attack in stage 1 is failed. Three experiments are run with <math> n = 2, k = 5 </math> for games with single attack and double attack, i.e, <math> t = 1 </math> and <math> t = 2 </math>. The results of simulated experiments are shown below [1]:<br />
<br />
[[File:Security Game Results.png|500px ]]<br />
<br />
<br />
They learned <math> R_i </math> only based on observations of the defender’s actions and could still recover the game setting by only observing the defender’s actions. Same as expectation, the larger dataset size improves the learned parameters. Two outliers are 1) Security Game, the green plot for when <math> t = 2 </math>; and 2) RPS, when comparing between training sizes of 2000 and 5000.<br />
<br />
== Conclusion ==<br />
Unsurprisingly, the results of this study show that in general the quality of learned parameters improved as the number of observations increased. The network presented in this paper demonstrated improvement over existing methodology. <br />
<br />
This paper presents an end-to-end framework for implementing a game solver, for both extensive and normal form, as a module in a deep neural network for zero-sum games. This method, unlike many previous works in this area, does not require the parameters of the game to be known to the agent prior to the start of the game. The two-part method analytically computes both the optimal solution and the parameters of the game. Future work involves taking advantage of the KKT matrix structure to increase computation speed, and extensions to the area of learning general-sum games.<br />
<br />
== Critiques ==<br />
The proposed method appears to suffer from two flaws. Firstly, the assumption that players behave in accordance to the QRE severely limits the space of player strategies, and is known to exhibit pathological behaviour even in one-player settings. Second, the solvers are computationally inefficient and are unable to scale. For this setting, they used Newton's method and it is found that the second-order algorithms do not scale to large games as with Nash equilibrium. <br />
<br />
This method of proposing that real players will follow a laid out scheme or playing strategy is almost always a drastic oversimplification of real world scenarios and severely limits the applications. In order to better fit a model to the real players, there almost always has to be some sort of stochastic implementation which accounts for the presence of irrational users in the system.<br />
<br />
== References ==<br />
<br />
[1] Ling, C. K., Fang, F., & Kolter, J. Z. (2018). What game are we playing? end-to-end learning in normal and extensive form games. arXiv preprint arXiv:1805.02777.<br />
<br />
[2] B. von Stengel. Efficient computation of behavior strategies.Games and Economics Behavior,14(0050):220–246, 1996.<br />
<br />
[3] Boyd, S., Boyd, S. P., & Vandenberghe, L. (2004). Convex optimization. Cambridge university press.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Neural_ODEs&diff=45982Neural ODEs2020-11-23T02:37:18Z<p>J244yang: /* More Critiques */</p>
<hr />
<div>== Introduction ==<br />
Chen et al. propose a new class of neural networks called neural ordinary differential equations (ODEs) in their 2018 paper under the same title. Neural network models, such as residual or recurrent networks, can be generalized as a set of transformations through hidden states (a.k.a layers) <math>\mathbf{h}</math>, given by the equation <br />
<br />
<div style="text-align:center;"><math> \mathbf{h}_{t+1} = \mathbf{h}_t + f(\mathbf{h}_t,\theta_t) </math> (1) </div><br />
<br />
where <math>t \in \{0,...,T\}</math> and <math>\theta_t</math> corresponds to the set of parameters or weights in state <math>t</math>. It is important to note that it has been shown (Lu et al., 2017)(Haber<br />
and Ruthotto, 2017)(Ruthotto and Haber, 2018) that Equation 1 can be viewed as an Euler discretization. Given this Euler description, if the number of layers and step size between layers are taken to their limits, then Equation 1 can instead be described continuously in the form of the ODE, <br />
<br />
<div style="text-align:center;"><math> \frac{d\mathbf{h}(t)}{dt} = f(\mathbf{h}(t),t,\theta) </math> (2). </div><br />
<br />
Equation 2 now describes a network where the output layer <math>\mathbf{h}(T)</math> is generated by solving for the ODE at time <math>T</math>, given the initial value at <math>t=0</math>, where <math>\mathbf{h}(0)</math> is the input layer of the network. <br />
<br />
With a vast amount of theory and research in the field of solving ODEs numerically, there are a number of benefits to formulating the hidden state dynamics this way. One major advantage is that a continuous description of the network allows for the calculation of <math>f</math> at arbitrary intervals and locations. The authors provide an example in section five of how the neural ODE network outperforms the discretized version i.e. residual networks, by taking advantage of the continuity of <math>f</math>. A depiction of this distinction is shown in the figure below. <br />
<br />
<div style="text-align:center;"> [[File:NeuralODEs_Fig1.png|350px]] </div><br />
<br />
In section four the authors show that the single-unit bottleneck of normalizing flows can be overcome by constructing a new class of density models that incorporates the neural ODE network formulation.<br />
The next section on automatic differentiation will describe how utilizing ODE solvers allows for the calculation of gradients of the loss function without storing any of the hidden state information. This results in a very low memory requirement for neural ODE networks in comparison to traditional networks that rely on intermediate hidden state quantities for backpropagation.<br />
<br />
== Reverse-mode Automatic Differentiation of ODE Solutions ==<br />
Like most neural networks, optimizing the weight parameters <math>\theta</math> for a neural ODE network involves finding the gradient of a loss function with respect to those parameters. Differentiating in the forward direction is a simple task, however, this method is very computationally expensive and unstable, as it introduces additional numerical error. Instead, the authors suggest that the gradients can be calculated in the reverse-mode with the adjoint sensitivity method (Pontryagin et al., 1962). This "backpropagation" method solves an augmented version of the forward ODE problem but in reverse, which is something that all ODE solvers are capable of. Section 3 provides results showing that this method gives very desirable memory costs and numerical stability. <br />
<br />
The authors provide an example of the adjoint method by considering the minimization of the scalar-valued loss function <math>L</math>, which takes the solution of the ODE solver as its argument.<br />
<br />
<div style="text-align:center;">[[File:NeuralODEs_Eq1.png|700px]],</div> <br />
This minimization problem requires the calculation of <math>\frac{\partial L}{\partial \mathbf{z}(t_0)}</math> and <math>\frac{\partial L}{\partial \theta}</math>.<br />
<br />
The adjoint itself is defined as <math>\mathbf{a}(t) = \frac{\partial L}{\partial \mathbf{z}(t)}</math>, which describes the gradient of the loss with respect to the hidden state <math>\mathbf{z}(t)</math>. By taking the first derivative of the adjoint, another ODE arises in the form of,<br />
<br />
<div style="text-align:center;"><math>\frac{d \mathbf{a}(t)}{dt} = -\mathbf{a}(t)^T \frac{\partial f(\mathbf{z}(t),t,\theta)}{\partial \mathbf{z}}</math> (3).</div> <br />
<br />
Since the value <math>\mathbf{a}(t_0)</math> is required to minimize the loss, the ODE in equation 3 must be solved backwards in time from <math>\mathbf{a}(t_1)</math>. Solving this problem is dependent on the knowledge of the hidden state <math>\mathbf{z}(t)</math> for all <math>t</math>, which an neural ODE does not save on the forward pass. Luckily, both <math>\mathbf{a}(t)</math> and <math>\mathbf{z}(t)</math> can be calculated in reverse, at the same time, by setting up an augmented version of the dynamics and is shown in the final algorithm. Finally, the derivative <math>dL/d\theta</math> can be expressed in terms of the adjoint and the hidden state as, <br />
<br />
<div style="text-align:center;"><math> \frac{dL}{d\theta} -\int_{t_1}^{t_0} \mathbf{a}(t)^T\frac{\partial f(\mathbf{z}(t),t,\theta)}{\partial \theta}dt</math> (4).</div><br />
<br />
To obtain very inexpensive calculations of <math>\frac{\partial f}{\partial z}</math> and <math>\frac{\partial f}{\partial \theta}</math> in equation 3 and 4, automatic differentiation can be utilized. The authors present an algorithm to calculate the gradients of <math>L</math> and their dependent quantities with only one call to an ODE solver and is shown below. <br />
<br />
<div style="text-align:center;">[[File:NeuralODEs Algorithm1.png|850px]]</div><br />
<br />
If the loss function has a stronger dependence on the hidden states for <math>t \neq t_0,t_1</math>, then Algorithm 1 can be modified to handle multiple calls to the ODESolve step since most ODE solvers have the capability to provide <math>z(t)</math> at arbitrary times. A visual depiction of this scenario is shown below. <br />
<br />
<div style="text-align:center;">[[File:NeuralODES Fig2.png|350px]]</div><br />
<br />
Please see the [https://arxiv.org/pdf/1806.07366.pdf#page=13 appendix] for extended versions of Algorithm 1 and detailed derivations of each equation in this section.<br />
<br />
== Replacing Residual Networks with ODEs for Supervised Learning ==<br />
Section three of the paper investigates an application of the reverse-mode differentiation described in section two, for the training of neural ODE networks on the MNIST digit data set. To solve for the forward pass in the neural ODE network, the following experiment used Adams method, which is an implicit ODE solver. Although it has a marked improvement over explicit ODE solvers in numerical accuracy, integrating backward through the network for backpropagation is still not preferred and the adjoint sensitivity method is used to perform efficient weight optimization. The network with this "backpropagation" technique is referred to as ODE-Net in this section. <br />
<br />
=== Implementation ===<br />
A residual network (ResNet), studied by He et al. (2016), with six standard residual blocks was used as a comparative model for this experiment. The competing model, ODE-net, replaces the residual blocks of the ResNet with the Adams solver. As a hybrid of the two models ResNet and ODE-net, a third network was created called RK-Net, which solves the weight optimization of the neural ODE network explicitly through backward Runge-Kutta integration. The following table shows the training and performance results of each network. <br />
<br />
<div style="text-align:center;">[[File:NeuralODEs Table1.png|400px]]</div><br />
<br />
Note that <math>L</math> and <math>\tilde{L}</math> are the number of layers in ResNet and the number of function calls that the Adams method makes for the two ODE networks and are effectively analogous quantities. As shown in Table 1, both of the ODE networks achieve comparable performance to that of the ResNet with a notable decrease in memory cost for ODE-net.<br />
<br />
<br />
Another interesting component of ODE networks is the ability to control the tolerance in the ODE solver used and subsequently the numerical error in the solution. <br />
<br />
<div style="text-align:center;">[[File:NeuralODEs Fig3.png|700px]]</div><br />
<br />
The tolerance of the ODE solver is represented by the colour bar in Figure 3 above and notice that a variety of effects arise from adjusting this parameter. Primarily, if one was to treat the tolerance as a hyperparameter of sorts, you could tune it such that you find a balance between accuracy (Figure 3a) and computational complexity (Figure 3b). Figure 3c also provides further evidence for the benefits of the adjoint method for the backward pass in ODE-nets since there is a nearly 1:0.5 ratio of forward to backward function calls. In the ResNet and RK-Net examples, this ratio is 1:1.<br />
<br />
Additionally, the authors loosely define the concept of depth in a neural ODE network by referring to Figure 3d. Here it's evident that as you continue to train an ODE network, the number of function evaluations the ODE solver performs increases. As previously mentioned, this quantity is comparable to the network depth of a discretized network. However, as the authors note, this result should be seen as the progression of the network's complexity over training epochs, which is something we expect to increase over time.<br />
<br />
== Continuous Normalizing Flows ==<br />
<br />
Section four tackles the implementation of continuous-depth Neural Networks, but to do so, in the first part of section four the authors discuss theoretically how to establish this kind of network through the use of normalizing flows. The authors use a change of variables method presented in other works (Rezende and Mohamed, 2015), (Dinh et al., 2014), to compute the change of a probability distribution if sample points are transformed through a bijective function, <math>f</math>.<br />
<br />
<div style="text-align:center;"><math>z_1=f(z_0) \Rightarrow \log(p(z_1))=\log(p(z_0))-\log|\det\frac{\partial f}{\partial z_0}|</math></div><br />
<br />
Where p(z) is the probability distribution of the samples and <math>det\frac{\partial f}{\partial z_0}</math> is the determinant of the Jacobian which has a cubic cost in the dimension of '''z''' or the number of hidden units in the network. The authors discovered however that transforming the discrete set of hidden layers in the normalizing flow network to continuous transformations simplifies the computations significantly, due primarily to the following theorem:<br />
<br />
'''''Theorem 1:''' (Instantaneous Change of Variables). Let z(t) be a finite continuous random variable with probability p(z(t)) dependent on time. Let dz/dt=f(z(t),t) be a differential equation describing a continuous-in-time transformation of z(t). Assuming that f is uniformly Lipschitz continuous in z and continuous in t, then the change in log probability also follows a differential equation:''<br />
<br />
<div style="text-align:center;"><math>\frac{\partial \log(p(z(t)))}{\partial t}=-tr\left(\frac{df}{dz(t)}\right)</math></div><br />
<br />
The biggest advantage to using this theorem is that the trace function is a linear function, so if the dynamics of the problem, f, is represented by a sum of functions, then so is the log density. This essentially means that you can now compute flow models with only a linear cost with respect to the number of hidden units, <math>M</math>. In standard normalizing flow models, the cost is <math>O(M^3)</math>, so they will generally fit many layers with a single hidden unit in each layer.<br />
<br />
Finally the authors use these realizations to construct Continuous Normalizing Flow networks (CNFs) by specifying the parameters of the flow as a function of ''t'', ie, <math>f(z(t),t)</math>. They also use a gating mechanism for each hidden unit, <math>\frac{dz}{dt}=\sum_n \sigma_n(t)f_n(z)</math> where <math>\sigma_n(t)\in (0,1)</math> is a separate neural network which learns when to apply each dynamic <math>f_n</math>.<br />
<br />
===Implementation===<br />
<br />
The authors construct two separate types of neural networks to compare against each other, the first is the standard planar Normalizing Flow network (NF) using 64 layers of single hidden units, and the second is their new CNF with 64 hidden units. The NF model is trained over 500,000 iterations using RMSprop, and the CNF network is trained over 10,000 iterations using Adam. The loss function is <math>KL(q(x)||p(x))</math> where <math>q(x)</math> is the flow model and <math>p(x)</math> is the target probability density.<br />
<br />
One of the biggest advantages when implementing CNF is that you can train the flow parameters just by performing maximum likelihood estimation on <math>\log(q(x))</math> given <math>p(x)</math>, where <math>q(x)</math> is found via the theorem above, and then reversing the CNF to generate random samples from <math>q(x)</math>. This reversal of the CNF is done with about the same cost of the forward pass which is not able to be done in an NF network. The following two figures demonstrate the ability of CNF to generate more expressive and accurate output data as compared to standard NF networks.<br />
<br />
<div style="text-align:center;"><br />
[[Image:CNFcomparisons.png]]<br />
<br />
[[Image:CNFtransitions.png]]<br />
</div><br />
<br />
Figure 4 shows clearly that the CNF structure exhibits significantly lower loss functions than NF. In figure 5 both networks were tasked with transforming a standard Gaussian distribution into a target distribution, not only was the CNF network more accurate on the two moons target, but also the steps it took along the way are much more intuitive than the output from NF.<br />
<br />
== A Generative Latent Function Time-Series Model ==<br />
<br />
One of the largest issues at play in terms of Neural ODE networks is the fact that in many instances, data points are either very sparsely distributed, or irregularly-sampled. The latent dynamics are discretized and the observations are in the bins of fixed duration. An example of this is medical records which are only updated when a patient visits a doctor or the hospital. To solve this issue the authors had to create a generative time-series model which would be able to fill in the gaps of missing data. The authors consider each time series as a latent trajectory stemming from the initial local state <math>z_{t_0 }</math> and determined from a global set of latent parameters. Given a set of observation times and initial state, the generative model constructs points via the following sample procedure:<br />
<br />
<div style="text-align:center;"><br />
<math><br />
z_{t_0}∼p(z_{t_0}) <br />
</math><br />
</div> <br />
<br />
<div style="text-align:center;"><br />
<math><br />
z_{t_1},z_{t_2},\dots,z_{t_N}=ODESolve(z_{t_0},f,θ_f,t_0,...,t_N)<br />
</math><br />
</div><br />
<br />
<div style="text-align:center;"><br />
each <br />
<math><br />
x_{t_i}∼p(x│z_{t_i},θ_x)<br />
</math><br />
</div><br />
<br />
<math>f</math> is a function which outputs the gradient <math>\frac{\partial z(t)}{\partial t}=f(z(t),θ_f)</math> which is parameterized via a neural net. In order to train this latent variable model, the authors had to first encode their given data and observation times using an RNN encoder, construct the new points using the trained parameters, then decode the points back into the original space. The following figure describes this process:<br />
<br />
<div style="text-align:center;"><br />
[[Image:EncodingFigure.png]]<br />
</div><br />
<br />
Another variable which could affect the latent state of a time-series model is how often an event actually occurs. The authors solved this by parameterizing the rate of events in terms of a Poisson process. They described the set of independent observation times in an interval <math>\left[t_{start},t_{end}\right]</math> as:<br />
<br />
<div style="text-align:center;"> <br />
<math><br />
log(p(t_1,t_2,\dots,t_N ))=\sum_{i=1}^Nlog(\lambda(z(t_i)))-\int_{t_{start}}^{t_{end}}λ(z(t))dt<br />
</math><br />
</div><br />
<br />
where <math>\lambda(*)</math> is parameterized via another neural network.<br />
<br />
===Implementation===<br />
<br />
To test the effectiveness of the Latent time-series ODE model (LODE), they fit the encoder with 25 hidden units, parametrize function f with a one-layer 20 hidden unit network, and the decoder as another neural network with 20 hidden units. They compare this against a standard recurrent neural net (RNN) with 25 hidden units trained to minimize gaussian log-likelihood. The authors tested both of these network systems on a dataset of 2-dimensional spirals which either rotated clockwise or counter-clockwise and sampled the positions of each spiral at 100 equally spaced time steps. They can then simulate irregularly timed data by taking random amounts of points without replacement from each spiral. The next two figures show the outcome of these experiments:<br />
<br />
<div style="text-align:center;"><br />
[[Image:LODEtestresults.png]] [[Image:SpiralFigure.png|The blue lines represent the test data learned curves and the red lines represent the extrapolated curves predicted by each model]]<br />
</div><br />
<br />
In the figure on the right the blue lines represent the test data learned curves and the red lines represent the extrapolated curves predicted by each model. It is noted that the LODE performs significantly better than the standard RNN model, especially on smaller sets of data points.<br />
<br />
== Scope and Limitations ==<br />
<br />
Section 6 mainly discusses the scope and limitations of the paper. Firstly while “batching” the training data is a useful step in standard neural nets, and can still be applied here by combining the ODEs associated with each batch, the authors found that controlling the error, in this case, may increase the number of calculations required. In practice, however, the number of calculations did not increase significantly.<br />
<br />
So long as the model proposed in this paper uses finite weights and Lipschitz nonlinearities, then Picard’s existence theorem (Coddington and Levinson, 1955) applies, guaranteeing the solution to the IVP exists and is unique. This theorem holds for the model presented above when the network has finite weights and uses nonlinearities in the Lipshitz class. <br />
<br />
In controlling the amount of error in the model, the authors were only able to reduce tolerances to approximately <math>10^{-3}</math> and <math>10^{-5}</math> in classification and density estimation respectively without also degrading the computational performance.<br />
<br />
The authors believe that reconstructing state trajectories by running the dynamics backward can introduce extra numerical error. They address a possible solution to this problem by checkpointing certain time steps and storing intermediate values of z on the forward pass. Then while reconstructing, you do each part individually between checkpoints. The authors acknowledged that they informally checked the validity of this method since they don’t consider it a practical problem.<br />
<br />
There remain, however, areas where standard neural networks may perform better than Neural ODEs. Firstly, conventional nets can fit non-homeomorphic functions, for example, functions whose output has a smaller dimension that their input, or that change the topology of the input space. However, this could be handled by composing ODE nets with standard network layers. Another point is that conventional nets can be evaluated exactly with a fixed amount of computation, and are typically faster to train and do not require an error tolerance for a solver.<br />
<br />
== Conclusions and Critiques ==<br />
<br />
We covered the use of black-box ODE solvers as a model component and their application to initial value problems constructed from real applications. Neural ODE Networks show promising gains in computational cost without large sacrifices in accuracy when applied to certain problems. A drawback of some of these implementations is that the ODE Neural Networks are limited by the underlying distributions of the problems they are trying to solve (requirement of Lipschitz continuity, etc.). There are plenty of further advances to be made in this field as hundreds of years of ODE theory and literature is available, so this is currently an important area of research.<br />
<br />
ODEs indeed represent an important area of applied mathematics where neural networks can be used to solve them numerically. Perhaps, a parallel area of investigation can be PDEs (Partial Differential Equations). PDEs are also widely encountered in many areas of applied mathematics, physics, social sciences and many other fields. It will be interesting to see how neural networks can be used to solve PDEs.<br />
<br />
== More Critiques ==<br />
<br />
This paper covers the memory efficiency of Neural ODE Networks, but does not address runtime. In practice, most systems are bound by latency requirements more-so than memory requirements (except in edge device cases). Though it may be unreasonable to expect the authors to produce a performance-optimized implementation, it would be insightful to understand the computational bottlenecks so existing frameworks can take steps to address them. This model looks promising and practical performance is the key to enabling future research in this.<br />
<br />
The above critique also questions the need for a neural network for such a problem. This problem was studied by Brunel et al. and they presented their solution in their paper ''Parametric Estimation of Ordinary Differential Equations with Orthogonality Conditions''. While this solution also requires iteratively solving a complex optimization problem, they did not require the massive memory and runtime overhead of a neural network. For the neural network solution to demonstrate its potential, it should be including experimental comparisons with specialized ordinary differential equation algorithms instead of simply comparing with a general recurrent neural network.<br />
<br />
== References ==<br />
Yiping Lu, Aoxiao Zhong, Quanzheng Li, and Bin Dong. Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations. ''arXiv preprint arXiv'':1710.10121, 2017.<br />
<br />
Eldad Haber and Lars Ruthotto. Stable architectures for deep neural networks. ''Inverse Problems'', 34 (1):014004, 2017.<br />
<br />
Lars Ruthotto and Eldad Haber. Deep neural networks motivated by partial differential equations. ''arXiv preprint arXiv'':1804.04272, 2018.<br />
<br />
Lev Semenovich Pontryagin, EF Mishchenko, VG Boltyanskii, and RV Gamkrelidze. ''The mathematical theory of optimal processes''. 1962.<br />
<br />
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Identity mappings in deep residual networks. In ''European conference on computer vision'', pages 630–645. Springer, 2016b.<br />
<br />
Earl A Coddington and Norman Levinson. ''Theory of ordinary differential equations''. Tata McGrawHill Education, 1955.<br />
<br />
Danilo Jimenez Rezende and Shakir Mohamed. Variational inference with normalizing flows. ''arXiv preprint arXiv:1505.05770'', 2015.<br />
<br />
Laurent Dinh, David Krueger, and Yoshua Bengio. NICE: Non-linear independent components estimation. ''arXiv preprint arXiv:1410.8516'', 2014.<br />
<br />
Brunel, N. J., Clairon, Q., & d’Alché-Buc, F. (2014). Parametric estimation of ordinary differential equations with orthogonality conditions. ''Journal of the American Statistical Association'', 109(505), 173-185.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Influenza_Forecasting_Framework_based_on_Gaussian_Processes&diff=45977Influenza Forecasting Framework based on Gaussian Processes2020-11-23T02:32:14Z<p>J244yang: </p>
<hr />
<div><br />
== Abstract ==<br />
<br />
This paper presents a novel framework for seasonal epidemic forecasting using Gaussian process regression. Compared with other state-of-the-art models, the new novel framework introduced in this paper shows accurate retrospective forecasts through training a subset of the CDC influenza-like-illness (ILI) dataset using the official CDC scoring rule (log-score).<br />
<br />
== Background ==<br />
<br />
Each year, the seasonal influenza epidemic affects public health systems across the globe at a massive scale. In 2019-2020 alone, the United States reported 38 million cases, 400 000 hospitalizations, and 22 000 deaths [1]. A direct result of this is the need for reliable forecasts of future influenza development, because they allow for improved public health policies and informed resource development and allocation. Many statistical methods have been developed to use data from the CDC and other real-time data sources, such as Google Trends to forecast influenza activities.<br />
<br />
Given the process of data collection and surveillance lag, accurate statistics for influenza warning systems are often delayed by some margin of time, making early prediction imperative. However, there are challenges in long-term epidemic forecasting. First, the temporal dependency is hard to capture with short-term input data. Without manually added seasonal trends, most statistical models fail to provide high accuracy. Second, the influence from other locations has not been exhaustively explored with limited data input. Spatio-temporal effects would therefore require adequate data sources to achieve good performance.<br />
<br />
== Related Work ==<br />
<br />
Given the value of epidemic forecasts, the CDC regularly publishes ILI data and has funded a seasonal ILI forecasting challenge. This challenge has led to four state-of-the-art models in the field: Historical averages, a method using the counts of past seasons to build a kernel density estimate; MSS, a physical susceptible-infected-recovered model with assumed linear noise [5]; SARIMA, a framework based on seasonal auto-regressive moving average models [2]; and LinEns, an ensemble of three linear regression models.<br />
<br />
One disadvantage of forecasting is that the publication of CDC official ILI data is usually delayed by 1-3 weeks. Therefore, several attempts use indirect web-based data to gain more timely estimates of CDC’s ILI, which is also known as nowcasting. The forecasting framework introduced in this paper is able to use those nowcasting approaches to receive a more timely data stream.<br />
<br />
== Motivation ==<br />
<br />
It has been shown that LinEns forecasts outperform the other frameworks on the ILI data-set. However, this framework assumes a deterministic relationship between the epidemic week and its case count, which does not reflect the stochastic nature of the trend. Therefore, it is natural to ask whether a similar framework that assumes a stochastic relationship between these variables would provide a better performance. This motivated the development of the proposed Gaussian process regression framework and the subsequent performance comparison to the benchmark models.<br />
<br />
== Gaussian Process Regression ==<br />
<br />
A Gaussian process is specified with a mean function and a kernel function. Besides, the mean and the variance function of the Gaussian process is defined by:<br />
\[\mu(x) = k(x, X)^T(K_n+\sigma^2I)^{-1}Y\]<br />
\[\sigma(x) = k^{**}(x,x)-k(x,X)^T(K_n+\sigma^2I)^{-1}k(x,X)\]<br />
where <math>K_n</math> is the covariance matrix and for the kernel, it is being specified that it will use the Gaussian kernel.<br />
<br />
Consider the following set up: let <math>X = [\mathbf{x}_1,\ldots,\mathbf{x}_n]</math> <math>(d\times n)</math> be your training data, <math>\mathbf{y} = [y_1,y_2,\ldots,y_n]^T</math> be your noisy observations where <math>y_i = f(\mathbf{x}_i) + \epsilon_i</math>, <math>(\epsilon_i:i = 1,\ldots,n)</math> i.i.d. <math>\sim \mathcal{N}(0,{\sigma}^2)</math>, and <math>f</math> is the trend we are trying to model (by <math>\hat{f}</math>). Let <math>\mathbf{x}^*</math> <math>(d\times 1)</math> be your test data point, and <math>\hat{y} = \hat{f}(\mathbf{x}^*)</math> be your predicted outcome.<br />
<br />
<br />
Instead of assuming a deterministic form of <math>f</math>, and thus of <math>\mathbf{y}</math> and <math>\hat{y}</math> (as classical linear regression would, for example), Gaussian process regression assumes <math>f</math> is stochastic. More precisely, <math>\mathbf{y}</math> and <math>\hat{y}</math> are assumed to have a joint prior distribution. Indeed, we have <br />
<br />
$$<br />
(\mathbf{y},\hat{y}) \sim \mathcal{N}(0,\Sigma(X,\mathbf{x}^*))<br />
$$<br />
<br />
where <math>\Sigma(X,\mathbf{x}^*)</math> is a matrix of covariances dependent on some kernel function <math>k</math>. In this paper, the kernel function is assumed to be Gaussian and takes the form <br />
<br />
$$<br />
k(\mathbf{x}_i,\mathbf{x}_j) = \sigma^2\exp(-\frac{1}{2}(\mathbf{x}_i-\mathbf{x}_j)^T\Sigma(\mathbf{x}_i-\mathbf{x}_j)).<br />
$$<br />
<br />
It is important to note that this gives a joint prior distribution of '''functions''' ('''Fig. 1''' left, grey curves). <br />
<br />
By restricting this distribution to contain only those functions ('''Fig. 1''' right, grey curves) that agree with the observed data points <math>\mathbf{x}</math> ('''Fig. 1''' right, solid black) we obtain the posterior distribution for <math>\hat{y}</math> which has the form<br />
<br />
$$<br />
p(\hat{y} | \mathbf{x}^*, X, \mathbf{y}) \sim \mathcal{N}(\mu(\mathbf{x}^*,X,\mathbf{y}),\sigma(\mathbf{x}^*,X))<br />
$$<br />
<br />
<br />
<div style="text-align:center;"> [[File:GPRegression.png|500px]] </div><br />
<br />
<div align="center">'''Figure 1. Gaussian process regression''': Select the functions from your joint prior distribution (left, grey curves) with mean <math>0</math> (left, bold line) that agree with the observed data points (right, black bullets). These form your posterior distribution (right, grey curves) with mean <math>\mu(\mathbf{x})</math> (right, bold line). Red triangle helps compare the two images (location marker) [4]. </div><br />
<br />
== Data-set ==<br />
<br />
Let <math>d_j^i</math> denote the number of epidemic cases recorded in week <math>j</math> of season <math>i</math>, and let <math>j^*</math> and <math>i^*</math> denote the current week and season, respectively. The ILI data-set contains <math>d_j^i</math> for all previous weeks and seasons, up to the current season with a 1-3 week publishing delay. Note that a season refers to the time of year when the epidemic is prevalent (e.g. an influenza season lasts 30 weeks and contains the last 10 weeks of year k, and the first 20 weeks of year k+1). The goal is to predict <math>\hat{y}_T = \hat{f}_T(x^*) = d^{i^*}_{j* + T}</math> where <math>T, \;(T = 1,\ldots,K)</math> is the target week (how many weeks into the future that you want to predict).<br />
<br />
To do this, a design matrix <math>X</math> is constructed where each element <math>X_{ji} = d_j^i</math> corresponds to the number of cases in week (row) j of season (column) i. The training outcomes <math>y_{i,T}, i = 1,\ldots,n</math> correspond to the number of cases that were observed in target week <math>T,\; (T = 1,\ldots,K)</math> of season <math>i, (i = 1,\ldots,n)</math>.<br />
<br />
== Proposed Framework ==<br />
<br />
To compute <math>\hat{y}</math>, the following algorithm is executed. <br />
<br />
<ol><br />
<br />
<li> Let <math>J \subseteq \{j^*-4 \leq j \leq j^*\}</math> (subset of possible weeks).<br />
<br />
<li> Assemble the Training Set <math>\{X_J, \mathbf{y}_{T,J}\}</math> <br />
<br />
<li> Train the Gaussian process<br />
<br />
<li> Calculate the '''distribution''' of <math>\hat{y}_{T,J}</math> using <math>p(\hat{y}_{T,J} | \mathbf{x}^*, X_J, \mathbf{y}_{T,J}) \sim \mathcal{N}(\mu(\mathbf{x}^*,X,\mathbf{y}_{T,J}),\sigma(\mathbf{x}^*,X_J))</math><br />
<br />
<li> Set <math>\hat{y}_{T,J} =\mu(x^*,X_J,\mathbf{y}_{T,J})</math><br />
<br />
<li> Repeat steps 2-5 for all sets of weeks <math>J</math><br />
<br />
<li> Determine the best 3 performing sets J (on the 2010/11 and 2011/12 validation sets)<br />
<br />
<li> Calculate the ensemble forecast by averaging the 3 best performing predictive distribution densities i.e. <math>\hat{y}_T = \frac{1}{3}\sum_{k=1}^3 \hat{y}_{T,J_{best}}</math><br />
<br />
</ol><br />
<br />
== Results ==<br />
<br />
To demonstrate the accuracy of their results, retrospective forecasting was done on the ILI data-set. In other words, the Gaussian process model was trained to assume a previous season (2012/13) was the current season. In this fashion, the forecast could be compared to the already observed true outcome. <br />
<br />
To produce a forecast for the entire 2012/13 season, 30 Gaussian processes were trained (each influenza season has 30 test points <math>\mathbf{x^*}</math>) and a curve connecting the predicted outputs <math>y_T = \hat{f}(\mathbf{x^*)}</math> was plotted ('''Fig.2''', blue line). As shown in '''Fig.2''', this forecast (blue line) was reliable for both 1 (left) and 3 (right) week targets, given that the 95% prediction interval ('''Fig.2''', purple shaded) contained the true values ('''Fig.2''', red x's) 95% of the time.<br />
<br />
<div style="text-align:center;"> [[File:ResultsOne.png|600px]] </div><br />
<br />
<div align="center">'''Figure 2. Retrospective forecasts and their uncertainty''': One week retrospective influenza forecasting for two targets (T = 1, 3). Red x’s are the true observed values, and blue lines and purple shaded areas represent point forecasts and 95% prediction intervals, respectively. </div><br />
<br />
<br />
Moreover, as shown in '''Fig.3''', the novel Gaussian process regression framework outperformed all state-of-the-art models, included LinEns, for four different targets <math>(T = 1,\ldots, 4)</math>, when compared using the official CDC scoring criterion ''log-score''. Log-score describes the logarithmic probability of the forecast being within an interval around the true value. <br />
<br />
<div style="text-align:center;"> [[File:ComparisonNew.png|600px]] </div><br />
<br />
<div align="center">'''Figure 3. Average log-score gain of proposed framework''': Each bar shows the mean seasonal log-score gain of the proposed framework vs. the given state-of-the-art model, and each panel corresponds to a different target week <math> T = 1,...4 </math>. </div><br />
<br />
== Conclusion ==<br />
<br />
This paper presented a novel framework for forecasting seasonal epidemics using Gaussian process regression that outperformed multiple state-of-the-art forecasting methods on the CDC's ILI data-set. Since influenza data has only been collected from 2003, therefore as more data is obtained: the training models can be further improved upon with more robust model optimizations. Hence, this work may play a key role in future influenza forecasting and as result, the improvement of public health policies and resource allocation.<br />
<br />
== Critique ==<br />
<br />
The proposed framework provides a computationally efficient method to forecast any seasonal epidemic count data that is easily extendable to multiple target types. In particular, one can compute key parameters such as the peak infection incidence <math>\left(\hat{y} = \text{max}_{0 \leq j \leq 52} d^i_j \right)</math>, the timing of the peak infection incidence <math>\left(\hat{y} = \text{argmax}_{0 \leq j \leq 52} d^i_j\right)</math> and the final epidemic size of a season <math>\left(\hat{y} = \sum_{j=1}^{52} d^i_j\right)</math>. However, given it is not a physical model, it cannot provide insights on parameters describing the disease spread. Moreover, the framework requires training data and hence, is not applicable for non-seasonal epidemics.<br />
<br />
This paper provides a state of the art approach for forecasting epidemics. It would have been interesting to see other types of kernels being used, such as a periodic kernel <math>k(x, x') = \sigma^2 \exp\left({-\frac{2 \sin^2 (\pi|x-x'|)/p}{l^2}}\right) </math>, as intuitively epidemics are known to have waves within seasons. This may have resulted in better-calibrated uncertainty estimates as well.<br />
<br />
It is mentioned that the the framework might not be good for non-seasonal epidemics because it requires training data, given that the COVID-19 pandemic comes in multiple waves and we have enough data from the first wave and second wave, we might be able to use this framework to predict the third wave and possibly the fourth one as well. It'd be interesting to see this forecasting framework being trained using the data from the first and second wave of COVID-19.<br />
<br />
Gaussian Process Regression (GPR) can be extended to COVID-19 outbreak forecast [3]. A Multi-Task Gaussian Process Regression (MTGP) model is a special case of GPR that yields multiple outputs. It was first proposed back in 2008, and its recent application was in the battery capacity prediction by Richardson et. al. The proposed MTGP model was applied on Worldwide, China, India, Italy, and USA data that covers COVID-19 statistics from Dec 31 2019 to June 25 2020. Results show that MTGP outperforms linear regression, support vector regression, random forest regression, and long short-term memory model when it comes to forecasting accuracy.<br />
<br />
A critique for GPR is that it does not take into account the physicality of the epidemic process. So it would be interesting to investigate if we can incorporate elements of physical processes in this such as using Ordinary Differential Equations (ODE) based modeling and seeing if that improves prediction accuracy or helps us explain phenomena.<br />
<br />
== References ==<br />
<br />
[1] Estimated Influenza Illnesses, Medical visits, Hospitalizations, and Deaths in the United States - 2019–2020 Influenza Season. (2020). Retrieved November 16, 2020, from https://www.cdc.gov/flu/about/burden/2019-2020.html<br />
<br />
[2] Ray, E. L., Sakrejda, K., Lauer, S. A., Johansson, M. A.,and Reich, N. G. (2017).Infectious disease prediction with kernel conditional densityestimation.Statistics in Medicine, 36(30):4908–4929.<br />
<br />
[3] Ketu, S., Mishra, P.K. Enhanced Gaussian process regression-based forecasting model for COVID-19 outbreak and significance of IoT for its detection. Appl Intell (2020). https://doi.org/10.1007/s10489-020-01889-9<br />
<br />
[4] Schulz, E., Speekenbrink, M., and Krause, A. (2017).A tutorial on gaussian process regression with a focus onexploration-exploitation scenarios.bioRxiv.<br />
<br />
[5] Zimmer, C., Leuba, S. I., Cohen, T., and Yaesoubi, R.(2019).Accurate quantification of uncertainty in epidemicparameter estimates and predictions using stochasticcompartmental models.Statistical Methods in Medical Research,28(12):3591–3608.PMID: 30428780.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Influenza_Forecasting_Framework_based_on_Gaussian_Processes&diff=45976Influenza Forecasting Framework based on Gaussian Processes2020-11-23T02:31:11Z<p>J244yang: /* Critique */</p>
<hr />
<div><br />
== Abstract ==<br />
<br />
This paper presents a novel framework for seasonal epidemic forecasting using Gaussian process regression. Compared with other state-of-the-art models, the new novel framework introduced in this paper shows accurate retrospective forecasts through training a subset of the CDC influenza-like-illness (ILI) dataset using the official CDC scoring rule (log-score).<br />
<br />
== Background ==<br />
<br />
Each year, the seasonal influenza epidemic affects public health systems across the globe at a massive scale. In 2019-2020 alone, the United States reported 38 million cases, 400 000 hospitalizations, and 22 000 deaths [1]. A direct result of this is the need for reliable forecasts of future influenza development, because they allow for improved public health policies and informed resource development and allocation. Many statistical methods have been developed to use data from the CDC and other real-time data sources, such as Google Trends to forecast influenza activities.<br />
<br />
Given the process of data collection and surveillance lag, accurate statistics for influenza warning systems are often delayed by some margin of time, making early prediction imperative. However, there are challenges in long-term epidemic forecasting. First, the temporal dependency is hard to capture with short-term input data. Without manually added seasonal trends, most statistical models fail to provide high accuracy. Second, the influence from other locations has not been exhaustively explored with limited data input. Spatio-temporal effects would therefore require adequate data sources to achieve good performance.<br />
<br />
== Related Work ==<br />
<br />
Given the value of epidemic forecasts, the CDC regularly publishes ILI data and has funded a seasonal ILI forecasting challenge. This challenge has led to four state-of-the-art models in the field: Historical averages, a method using the counts of past seasons to build a kernel density estimate; MSS, a physical susceptible-infected-recovered model with assumed linear noise [3]; SARIMA, a framework based on seasonal auto-regressive moving average models [2]; and LinEns, an ensemble of three linear regression models.<br />
<br />
One disadvantage of forecasting is that the publication of CDC official ILI data is usually delayed by 1-3 weeks. Therefore, several attempts use indirect web-based data to gain more timely estimates of CDC’s ILI, which is also known as nowcasting. The forecasting framework introduced in this paper is able to use those nowcasting approaches to receive a more timely data stream.<br />
<br />
== Motivation ==<br />
<br />
It has been shown that LinEns forecasts outperform the other frameworks on the ILI data-set. However, this framework assumes a deterministic relationship between the epidemic week and its case count, which does not reflect the stochastic nature of the trend. Therefore, it is natural to ask whether a similar framework that assumes a stochastic relationship between these variables would provide a better performance. This motivated the development of the proposed Gaussian process regression framework and the subsequent performance comparison to the benchmark models.<br />
<br />
== Gaussian Process Regression ==<br />
<br />
A Gaussian process is specified with a mean function and a kernel function. Besides, the mean and the variance function of the Gaussian process is defined by:<br />
\[\mu(x) = k(x, X)^T(K_n+\sigma^2I)^{-1}Y\]<br />
\[\sigma(x) = k^{**}(x,x)-k(x,X)^T(K_n+\sigma^2I)^{-1}k(x,X)\]<br />
where <math>K_n</math> is the covariance matrix and for the kernel, it is being specified that it will use the Gaussian kernel.<br />
<br />
Consider the following set up: let <math>X = [\mathbf{x}_1,\ldots,\mathbf{x}_n]</math> <math>(d\times n)</math> be your training data, <math>\mathbf{y} = [y_1,y_2,\ldots,y_n]^T</math> be your noisy observations where <math>y_i = f(\mathbf{x}_i) + \epsilon_i</math>, <math>(\epsilon_i:i = 1,\ldots,n)</math> i.i.d. <math>\sim \mathcal{N}(0,{\sigma}^2)</math>, and <math>f</math> is the trend we are trying to model (by <math>\hat{f}</math>). Let <math>\mathbf{x}^*</math> <math>(d\times 1)</math> be your test data point, and <math>\hat{y} = \hat{f}(\mathbf{x}^*)</math> be your predicted outcome.<br />
<br />
<br />
Instead of assuming a deterministic form of <math>f</math>, and thus of <math>\mathbf{y}</math> and <math>\hat{y}</math> (as classical linear regression would, for example), Gaussian process regression assumes <math>f</math> is stochastic. More precisely, <math>\mathbf{y}</math> and <math>\hat{y}</math> are assumed to have a joint prior distribution. Indeed, we have <br />
<br />
$$<br />
(\mathbf{y},\hat{y}) \sim \mathcal{N}(0,\Sigma(X,\mathbf{x}^*))<br />
$$<br />
<br />
where <math>\Sigma(X,\mathbf{x}^*)</math> is a matrix of covariances dependent on some kernel function <math>k</math>. In this paper, the kernel function is assumed to be Gaussian and takes the form <br />
<br />
$$<br />
k(\mathbf{x}_i,\mathbf{x}_j) = \sigma^2\exp(-\frac{1}{2}(\mathbf{x}_i-\mathbf{x}_j)^T\Sigma(\mathbf{x}_i-\mathbf{x}_j)).<br />
$$<br />
<br />
It is important to note that this gives a joint prior distribution of '''functions''' ('''Fig. 1''' left, grey curves). <br />
<br />
By restricting this distribution to contain only those functions ('''Fig. 1''' right, grey curves) that agree with the observed data points <math>\mathbf{x}</math> ('''Fig. 1''' right, solid black) we obtain the posterior distribution for <math>\hat{y}</math> which has the form<br />
<br />
$$<br />
p(\hat{y} | \mathbf{x}^*, X, \mathbf{y}) \sim \mathcal{N}(\mu(\mathbf{x}^*,X,\mathbf{y}),\sigma(\mathbf{x}^*,X))<br />
$$<br />
<br />
<br />
<div style="text-align:center;"> [[File:GPRegression.png|500px]] </div><br />
<br />
<div align="center">'''Figure 1. Gaussian process regression''': Select the functions from your joint prior distribution (left, grey curves) with mean <math>0</math> (left, bold line) that agree with the observed data points (right, black bullets). These form your posterior distribution (right, grey curves) with mean <math>\mu(\mathbf{x})</math> (right, bold line). Red triangle helps compare the two images (location marker) [4]. </div><br />
<br />
== Data-set ==<br />
<br />
Let <math>d_j^i</math> denote the number of epidemic cases recorded in week <math>j</math> of season <math>i</math>, and let <math>j^*</math> and <math>i^*</math> denote the current week and season, respectively. The ILI data-set contains <math>d_j^i</math> for all previous weeks and seasons, up to the current season with a 1-3 week publishing delay. Note that a season refers to the time of year when the epidemic is prevalent (e.g. an influenza season lasts 30 weeks and contains the last 10 weeks of year k, and the first 20 weeks of year k+1). The goal is to predict <math>\hat{y}_T = \hat{f}_T(x^*) = d^{i^*}_{j* + T}</math> where <math>T, \;(T = 1,\ldots,K)</math> is the target week (how many weeks into the future that you want to predict).<br />
<br />
To do this, a design matrix <math>X</math> is constructed where each element <math>X_{ji} = d_j^i</math> corresponds to the number of cases in week (row) j of season (column) i. The training outcomes <math>y_{i,T}, i = 1,\ldots,n</math> correspond to the number of cases that were observed in target week <math>T,\; (T = 1,\ldots,K)</math> of season <math>i, (i = 1,\ldots,n)</math>.<br />
<br />
== Proposed Framework ==<br />
<br />
To compute <math>\hat{y}</math>, the following algorithm is executed. <br />
<br />
<ol><br />
<br />
<li> Let <math>J \subseteq \{j^*-4 \leq j \leq j^*\}</math> (subset of possible weeks).<br />
<br />
<li> Assemble the Training Set <math>\{X_J, \mathbf{y}_{T,J}\}</math> <br />
<br />
<li> Train the Gaussian process<br />
<br />
<li> Calculate the '''distribution''' of <math>\hat{y}_{T,J}</math> using <math>p(\hat{y}_{T,J} | \mathbf{x}^*, X_J, \mathbf{y}_{T,J}) \sim \mathcal{N}(\mu(\mathbf{x}^*,X,\mathbf{y}_{T,J}),\sigma(\mathbf{x}^*,X_J))</math><br />
<br />
<li> Set <math>\hat{y}_{T,J} =\mu(x^*,X_J,\mathbf{y}_{T,J})</math><br />
<br />
<li> Repeat steps 2-5 for all sets of weeks <math>J</math><br />
<br />
<li> Determine the best 3 performing sets J (on the 2010/11 and 2011/12 validation sets)<br />
<br />
<li> Calculate the ensemble forecast by averaging the 3 best performing predictive distribution densities i.e. <math>\hat{y}_T = \frac{1}{3}\sum_{k=1}^3 \hat{y}_{T,J_{best}}</math><br />
<br />
</ol><br />
<br />
== Results ==<br />
<br />
To demonstrate the accuracy of their results, retrospective forecasting was done on the ILI data-set. In other words, the Gaussian process model was trained to assume a previous season (2012/13) was the current season. In this fashion, the forecast could be compared to the already observed true outcome. <br />
<br />
To produce a forecast for the entire 2012/13 season, 30 Gaussian processes were trained (each influenza season has 30 test points <math>\mathbf{x^*}</math>) and a curve connecting the predicted outputs <math>y_T = \hat{f}(\mathbf{x^*)}</math> was plotted ('''Fig.2''', blue line). As shown in '''Fig.2''', this forecast (blue line) was reliable for both 1 (left) and 3 (right) week targets, given that the 95% prediction interval ('''Fig.2''', purple shaded) contained the true values ('''Fig.2''', red x's) 95% of the time.<br />
<br />
<div style="text-align:center;"> [[File:ResultsOne.png|600px]] </div><br />
<br />
<div align="center">'''Figure 2. Retrospective forecasts and their uncertainty''': One week retrospective influenza forecasting for two targets (T = 1, 3). Red x’s are the true observed values, and blue lines and purple shaded areas represent point forecasts and 95% prediction intervals, respectively. </div><br />
<br />
<br />
Moreover, as shown in '''Fig.3''', the novel Gaussian process regression framework outperformed all state-of-the-art models, included LinEns, for four different targets <math>(T = 1,\ldots, 4)</math>, when compared using the official CDC scoring criterion ''log-score''. Log-score describes the logarithmic probability of the forecast being within an interval around the true value. <br />
<br />
<div style="text-align:center;"> [[File:ComparisonNew.png|600px]] </div><br />
<br />
<div align="center">'''Figure 3. Average log-score gain of proposed framework''': Each bar shows the mean seasonal log-score gain of the proposed framework vs. the given state-of-the-art model, and each panel corresponds to a different target week <math> T = 1,...4 </math>. </div><br />
<br />
== Conclusion ==<br />
<br />
This paper presented a novel framework for forecasting seasonal epidemics using Gaussian process regression that outperformed multiple state-of-the-art forecasting methods on the CDC's ILI data-set. Since influenza data has only been collected from 2003, therefore as more data is obtained: the training models can be further improved upon with more robust model optimizations. Hence, this work may play a key role in future influenza forecasting and as result, the improvement of public health policies and resource allocation.<br />
<br />
== Critique ==<br />
<br />
The proposed framework provides a computationally efficient method to forecast any seasonal epidemic count data that is easily extendable to multiple target types. In particular, one can compute key parameters such as the peak infection incidence <math>\left(\hat{y} = \text{max}_{0 \leq j \leq 52} d^i_j \right)</math>, the timing of the peak infection incidence <math>\left(\hat{y} = \text{argmax}_{0 \leq j \leq 52} d^i_j\right)</math> and the final epidemic size of a season <math>\left(\hat{y} = \sum_{j=1}^{52} d^i_j\right)</math>. However, given it is not a physical model, it cannot provide insights on parameters describing the disease spread. Moreover, the framework requires training data and hence, is not applicable for non-seasonal epidemics.<br />
<br />
This paper provides a state of the art approach for forecasting epidemics. It would have been interesting to see other types of kernels being used, such as a periodic kernel <math>k(x, x') = \sigma^2 \exp\left({-\frac{2 \sin^2 (\pi|x-x'|)/p}{l^2}}\right) </math>, as intuitively epidemics are known to have waves within seasons. This may have resulted in better-calibrated uncertainty estimates as well.<br />
<br />
It is mentioned that the the framework might not be good for non-seasonal epidemics because it requires training data, given that the COVID-19 pandemic comes in multiple waves and we have enough data from the first wave and second wave, we might be able to use this framework to predict the third wave and possibly the fourth one as well. It'd be interesting to see this forecasting framework being trained using the data from the first and second wave of COVID-19.<br />
<br />
Gaussian Process Regression (GPR) can be extended to COVID-19 outbreak forecast [3]. A Multi-Task Gaussian Process Regression (MTGP) model is a special case of GPR that yields multiple outputs. It was first proposed back in 2008, and its recent application was in the battery capacity prediction by Richardson et. al. The proposed MTGP model was applied on Worldwide, China, India, Italy, and USA data that covers COVID-19 statistics from Dec 31 2019 to June 25 2020. Results show that MTGP outperforms linear regression, support vector regression, random forest regression, and long short-term memory model when it comes to forecasting accuracy.<br />
<br />
A critique for GPR is that it does not take into account the physicality of the epidemic process. So it would be interesting to investigate if we can incorporate elements of physical processes in this such as using Ordinary Differential Equations (ODE) based modeling and seeing if that improves prediction accuracy or helps us explain phenomena.<br />
<br />
== References ==<br />
<br />
[1] Estimated Influenza Illnesses, Medical visits, Hospitalizations, and Deaths in the United States - 2019–2020 Influenza Season. (2020). Retrieved November 16, 2020, from https://www.cdc.gov/flu/about/burden/2019-2020.html<br />
<br />
[2] Ray, E. L., Sakrejda, K., Lauer, S. A., Johansson, M. A.,and Reich, N. G. (2017).Infectious disease prediction with kernel conditional densityestimation.Statistics in Medicine, 36(30):4908–4929.<br />
<br />
[3] Ketu, S., Mishra, P.K. Enhanced Gaussian process regression-based forecasting model for COVID-19 outbreak and significance of IoT for its detection. Appl Intell (2020). https://doi.org/10.1007/s10489-020-01889-9<br />
<br />
[4] Schulz, E., Speekenbrink, M., and Krause, A. (2017).A tutorial on gaussian process regression with a focus onexploration-exploitation scenarios.bioRxiv.<br />
<br />
[5] Zimmer, C., Leuba, S. I., Cohen, T., and Yaesoubi, R.(2019).Accurate quantification of uncertainty in epidemicparameter estimates and predictions using stochasticcompartmental models.Statistical Methods in Medical Research,28(12):3591–3608.PMID: 30428780.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Influenza_Forecasting_Framework_based_on_Gaussian_Processes&diff=45975Influenza Forecasting Framework based on Gaussian Processes2020-11-23T02:29:51Z<p>J244yang: /* Related Work */</p>
<hr />
<div><br />
== Abstract ==<br />
<br />
This paper presents a novel framework for seasonal epidemic forecasting using Gaussian process regression. Compared with other state-of-the-art models, the new novel framework introduced in this paper shows accurate retrospective forecasts through training a subset of the CDC influenza-like-illness (ILI) dataset using the official CDC scoring rule (log-score).<br />
<br />
== Background ==<br />
<br />
Each year, the seasonal influenza epidemic affects public health systems across the globe at a massive scale. In 2019-2020 alone, the United States reported 38 million cases, 400 000 hospitalizations, and 22 000 deaths [1]. A direct result of this is the need for reliable forecasts of future influenza development, because they allow for improved public health policies and informed resource development and allocation. Many statistical methods have been developed to use data from the CDC and other real-time data sources, such as Google Trends to forecast influenza activities.<br />
<br />
Given the process of data collection and surveillance lag, accurate statistics for influenza warning systems are often delayed by some margin of time, making early prediction imperative. However, there are challenges in long-term epidemic forecasting. First, the temporal dependency is hard to capture with short-term input data. Without manually added seasonal trends, most statistical models fail to provide high accuracy. Second, the influence from other locations has not been exhaustively explored with limited data input. Spatio-temporal effects would therefore require adequate data sources to achieve good performance.<br />
<br />
== Related Work ==<br />
<br />
Given the value of epidemic forecasts, the CDC regularly publishes ILI data and has funded a seasonal ILI forecasting challenge. This challenge has led to four state-of-the-art models in the field: Historical averages, a method using the counts of past seasons to build a kernel density estimate; MSS, a physical susceptible-infected-recovered model with assumed linear noise [3]; SARIMA, a framework based on seasonal auto-regressive moving average models [2]; and LinEns, an ensemble of three linear regression models.<br />
<br />
One disadvantage of forecasting is that the publication of CDC official ILI data is usually delayed by 1-3 weeks. Therefore, several attempts use indirect web-based data to gain more timely estimates of CDC’s ILI, which is also known as nowcasting. The forecasting framework introduced in this paper is able to use those nowcasting approaches to receive a more timely data stream.<br />
<br />
== Motivation ==<br />
<br />
It has been shown that LinEns forecasts outperform the other frameworks on the ILI data-set. However, this framework assumes a deterministic relationship between the epidemic week and its case count, which does not reflect the stochastic nature of the trend. Therefore, it is natural to ask whether a similar framework that assumes a stochastic relationship between these variables would provide a better performance. This motivated the development of the proposed Gaussian process regression framework and the subsequent performance comparison to the benchmark models.<br />
<br />
== Gaussian Process Regression ==<br />
<br />
A Gaussian process is specified with a mean function and a kernel function. Besides, the mean and the variance function of the Gaussian process is defined by:<br />
\[\mu(x) = k(x, X)^T(K_n+\sigma^2I)^{-1}Y\]<br />
\[\sigma(x) = k^{**}(x,x)-k(x,X)^T(K_n+\sigma^2I)^{-1}k(x,X)\]<br />
where <math>K_n</math> is the covariance matrix and for the kernel, it is being specified that it will use the Gaussian kernel.<br />
<br />
Consider the following set up: let <math>X = [\mathbf{x}_1,\ldots,\mathbf{x}_n]</math> <math>(d\times n)</math> be your training data, <math>\mathbf{y} = [y_1,y_2,\ldots,y_n]^T</math> be your noisy observations where <math>y_i = f(\mathbf{x}_i) + \epsilon_i</math>, <math>(\epsilon_i:i = 1,\ldots,n)</math> i.i.d. <math>\sim \mathcal{N}(0,{\sigma}^2)</math>, and <math>f</math> is the trend we are trying to model (by <math>\hat{f}</math>). Let <math>\mathbf{x}^*</math> <math>(d\times 1)</math> be your test data point, and <math>\hat{y} = \hat{f}(\mathbf{x}^*)</math> be your predicted outcome.<br />
<br />
<br />
Instead of assuming a deterministic form of <math>f</math>, and thus of <math>\mathbf{y}</math> and <math>\hat{y}</math> (as classical linear regression would, for example), Gaussian process regression assumes <math>f</math> is stochastic. More precisely, <math>\mathbf{y}</math> and <math>\hat{y}</math> are assumed to have a joint prior distribution. Indeed, we have <br />
<br />
$$<br />
(\mathbf{y},\hat{y}) \sim \mathcal{N}(0,\Sigma(X,\mathbf{x}^*))<br />
$$<br />
<br />
where <math>\Sigma(X,\mathbf{x}^*)</math> is a matrix of covariances dependent on some kernel function <math>k</math>. In this paper, the kernel function is assumed to be Gaussian and takes the form <br />
<br />
$$<br />
k(\mathbf{x}_i,\mathbf{x}_j) = \sigma^2\exp(-\frac{1}{2}(\mathbf{x}_i-\mathbf{x}_j)^T\Sigma(\mathbf{x}_i-\mathbf{x}_j)).<br />
$$<br />
<br />
It is important to note that this gives a joint prior distribution of '''functions''' ('''Fig. 1''' left, grey curves). <br />
<br />
By restricting this distribution to contain only those functions ('''Fig. 1''' right, grey curves) that agree with the observed data points <math>\mathbf{x}</math> ('''Fig. 1''' right, solid black) we obtain the posterior distribution for <math>\hat{y}</math> which has the form<br />
<br />
$$<br />
p(\hat{y} | \mathbf{x}^*, X, \mathbf{y}) \sim \mathcal{N}(\mu(\mathbf{x}^*,X,\mathbf{y}),\sigma(\mathbf{x}^*,X))<br />
$$<br />
<br />
<br />
<div style="text-align:center;"> [[File:GPRegression.png|500px]] </div><br />
<br />
<div align="center">'''Figure 1. Gaussian process regression''': Select the functions from your joint prior distribution (left, grey curves) with mean <math>0</math> (left, bold line) that agree with the observed data points (right, black bullets). These form your posterior distribution (right, grey curves) with mean <math>\mu(\mathbf{x})</math> (right, bold line). Red triangle helps compare the two images (location marker) [4]. </div><br />
<br />
== Data-set ==<br />
<br />
Let <math>d_j^i</math> denote the number of epidemic cases recorded in week <math>j</math> of season <math>i</math>, and let <math>j^*</math> and <math>i^*</math> denote the current week and season, respectively. The ILI data-set contains <math>d_j^i</math> for all previous weeks and seasons, up to the current season with a 1-3 week publishing delay. Note that a season refers to the time of year when the epidemic is prevalent (e.g. an influenza season lasts 30 weeks and contains the last 10 weeks of year k, and the first 20 weeks of year k+1). The goal is to predict <math>\hat{y}_T = \hat{f}_T(x^*) = d^{i^*}_{j* + T}</math> where <math>T, \;(T = 1,\ldots,K)</math> is the target week (how many weeks into the future that you want to predict).<br />
<br />
To do this, a design matrix <math>X</math> is constructed where each element <math>X_{ji} = d_j^i</math> corresponds to the number of cases in week (row) j of season (column) i. The training outcomes <math>y_{i,T}, i = 1,\ldots,n</math> correspond to the number of cases that were observed in target week <math>T,\; (T = 1,\ldots,K)</math> of season <math>i, (i = 1,\ldots,n)</math>.<br />
<br />
== Proposed Framework ==<br />
<br />
To compute <math>\hat{y}</math>, the following algorithm is executed. <br />
<br />
<ol><br />
<br />
<li> Let <math>J \subseteq \{j^*-4 \leq j \leq j^*\}</math> (subset of possible weeks).<br />
<br />
<li> Assemble the Training Set <math>\{X_J, \mathbf{y}_{T,J}\}</math> <br />
<br />
<li> Train the Gaussian process<br />
<br />
<li> Calculate the '''distribution''' of <math>\hat{y}_{T,J}</math> using <math>p(\hat{y}_{T,J} | \mathbf{x}^*, X_J, \mathbf{y}_{T,J}) \sim \mathcal{N}(\mu(\mathbf{x}^*,X,\mathbf{y}_{T,J}),\sigma(\mathbf{x}^*,X_J))</math><br />
<br />
<li> Set <math>\hat{y}_{T,J} =\mu(x^*,X_J,\mathbf{y}_{T,J})</math><br />
<br />
<li> Repeat steps 2-5 for all sets of weeks <math>J</math><br />
<br />
<li> Determine the best 3 performing sets J (on the 2010/11 and 2011/12 validation sets)<br />
<br />
<li> Calculate the ensemble forecast by averaging the 3 best performing predictive distribution densities i.e. <math>\hat{y}_T = \frac{1}{3}\sum_{k=1}^3 \hat{y}_{T,J_{best}}</math><br />
<br />
</ol><br />
<br />
== Results ==<br />
<br />
To demonstrate the accuracy of their results, retrospective forecasting was done on the ILI data-set. In other words, the Gaussian process model was trained to assume a previous season (2012/13) was the current season. In this fashion, the forecast could be compared to the already observed true outcome. <br />
<br />
To produce a forecast for the entire 2012/13 season, 30 Gaussian processes were trained (each influenza season has 30 test points <math>\mathbf{x^*}</math>) and a curve connecting the predicted outputs <math>y_T = \hat{f}(\mathbf{x^*)}</math> was plotted ('''Fig.2''', blue line). As shown in '''Fig.2''', this forecast (blue line) was reliable for both 1 (left) and 3 (right) week targets, given that the 95% prediction interval ('''Fig.2''', purple shaded) contained the true values ('''Fig.2''', red x's) 95% of the time.<br />
<br />
<div style="text-align:center;"> [[File:ResultsOne.png|600px]] </div><br />
<br />
<div align="center">'''Figure 2. Retrospective forecasts and their uncertainty''': One week retrospective influenza forecasting for two targets (T = 1, 3). Red x’s are the true observed values, and blue lines and purple shaded areas represent point forecasts and 95% prediction intervals, respectively. </div><br />
<br />
<br />
Moreover, as shown in '''Fig.3''', the novel Gaussian process regression framework outperformed all state-of-the-art models, included LinEns, for four different targets <math>(T = 1,\ldots, 4)</math>, when compared using the official CDC scoring criterion ''log-score''. Log-score describes the logarithmic probability of the forecast being within an interval around the true value. <br />
<br />
<div style="text-align:center;"> [[File:ComparisonNew.png|600px]] </div><br />
<br />
<div align="center">'''Figure 3. Average log-score gain of proposed framework''': Each bar shows the mean seasonal log-score gain of the proposed framework vs. the given state-of-the-art model, and each panel corresponds to a different target week <math> T = 1,...4 </math>. </div><br />
<br />
== Conclusion ==<br />
<br />
This paper presented a novel framework for forecasting seasonal epidemics using Gaussian process regression that outperformed multiple state-of-the-art forecasting methods on the CDC's ILI data-set. Since influenza data has only been collected from 2003, therefore as more data is obtained: the training models can be further improved upon with more robust model optimizations. Hence, this work may play a key role in future influenza forecasting and as result, the improvement of public health policies and resource allocation.<br />
<br />
== Critique ==<br />
<br />
The proposed framework provides a computationally efficient method to forecast any seasonal epidemic count data that is easily extendable to multiple target types. In particular, one can compute key parameters such as the peak infection incidence <math>\left(\hat{y} = \text{max}_{0 \leq j \leq 52} d^i_j \right)</math>, the timing of the peak infection incidence <math>\left(\hat{y} = \text{argmax}_{0 \leq j \leq 52} d^i_j\right)</math> and the final epidemic size of a season <math>\left(\hat{y} = \sum_{j=1}^{52} d^i_j\right)</math>. However, given it is not a physical model, it cannot provide insights on parameters describing the disease spread. Moreover, the framework requires training data and hence, is not applicable for non-seasonal epidemics.<br />
<br />
This paper provides a state of the art approach for forecasting epidemics. It would have been interesting to see other types of kernels being used, such as a periodic kernel <math>k(x, x') = \sigma^2 \exp\left({-\frac{2 \sin^2 (\pi|x-x'|)/p}{l^2}}\right) </math>, as intuitively epidemics are known to have waves within seasons. This may have resulted in better-calibrated uncertainty estimates as well.<br />
<br />
It is mentioned that the the framework might not be good for non-seasonal epidemics because it requires training data, given that the COVID-19 pandemic comes in multiple waves and we have enough data from the first wave and second wave, we might be able to use this framework to predict the third wave and possibly the fourth one as well. It'd be interesting to see this forecasting framework being trained using the data from the first and second wave of COVID-19.<br />
<br />
Gaussian Process Regression (GPR) can be extended to COVID-19 outbreak forecast (link: https://link.springer.com/article/10.1007/s10489-020-01889-9). A Multi-Task Gaussian Process Regression (MTGP) model is a special case of GPR that yields multiple outputs. It was first proposed back in 2008, and its recent application was in the battery capacity prediction by Richardson et. al. The proposed MTGP model was applied on Worldwide, China, India, Italy, and USA data that covers COVID-19 statistics from Dec 31 2019 to June 25 2020. Results show that MTGP outperforms linear regression, support vector regression, random forest regression, and long short-term memory model when it comes to forecasting accuracy.<br />
<br />
A critique for GPR is that it does not take into account the physicality of the epidemic process. So it would be interesting to investigate if we can incorporate elements of physical processes in this such as using Ordinary Differential Equations (ODE) based modeling and seeing if that improves prediction accuracy or helps us explain phenomena.<br />
<br />
== References ==<br />
<br />
[1] Estimated Influenza Illnesses, Medical visits, Hospitalizations, and Deaths in the United States - 2019–2020 Influenza Season. (2020). Retrieved November 16, 2020, from https://www.cdc.gov/flu/about/burden/2019-2020.html<br />
<br />
[2] Ray, E. L., Sakrejda, K., Lauer, S. A., Johansson, M. A.,and Reich, N. G. (2017).Infectious disease prediction with kernel conditional densityestimation.Statistics in Medicine, 36(30):4908–4929.<br />
<br />
[3] Ketu, S., Mishra, P.K. Enhanced Gaussian process regression-based forecasting model for COVID-19 outbreak and significance of IoT for its detection. Appl Intell (2020). https://doi.org/10.1007/s10489-020-01889-9<br />
<br />
[4] Schulz, E., Speekenbrink, M., and Krause, A. (2017).A tutorial on gaussian process regression with a focus onexploration-exploitation scenarios.bioRxiv.<br />
<br />
[5] Zimmer, C., Leuba, S. I., Cohen, T., and Yaesoubi, R.(2019).Accurate quantification of uncertainty in epidemicparameter estimates and predictions using stochasticcompartmental models.Statistical Methods in Medical Research,28(12):3591–3608.PMID: 30428780.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Influenza_Forecasting_Framework_based_on_Gaussian_Processes&diff=45974Influenza Forecasting Framework based on Gaussian Processes2020-11-23T02:29:38Z<p>J244yang: /* Gaussian Process Regression */</p>
<hr />
<div><br />
== Abstract ==<br />
<br />
This paper presents a novel framework for seasonal epidemic forecasting using Gaussian process regression. Compared with other state-of-the-art models, the new novel framework introduced in this paper shows accurate retrospective forecasts through training a subset of the CDC influenza-like-illness (ILI) dataset using the official CDC scoring rule (log-score).<br />
<br />
== Background ==<br />
<br />
Each year, the seasonal influenza epidemic affects public health systems across the globe at a massive scale. In 2019-2020 alone, the United States reported 38 million cases, 400 000 hospitalizations, and 22 000 deaths [1]. A direct result of this is the need for reliable forecasts of future influenza development, because they allow for improved public health policies and informed resource development and allocation. Many statistical methods have been developed to use data from the CDC and other real-time data sources, such as Google Trends to forecast influenza activities.<br />
<br />
Given the process of data collection and surveillance lag, accurate statistics for influenza warning systems are often delayed by some margin of time, making early prediction imperative. However, there are challenges in long-term epidemic forecasting. First, the temporal dependency is hard to capture with short-term input data. Without manually added seasonal trends, most statistical models fail to provide high accuracy. Second, the influence from other locations has not been exhaustively explored with limited data input. Spatio-temporal effects would therefore require adequate data sources to achieve good performance.<br />
<br />
== Related Work ==<br />
<br />
Given the value of epidemic forecasts, the CDC regularly publishes ILI data and has funded a seasonal ILI forecasting challenge. This challenge has led to four state-of-the-art models in the field: Historical averages, a method using the counts of past seasons to build a kernel density estimate; MSS, a physical susceptible-infected-recovered model with assumed linear noise [4]; SARIMA, a framework based on seasonal auto-regressive moving average models [2]; and LinEns, an ensemble of three linear regression models.<br />
<br />
One disadvantage of forecasting is that the publication of CDC official ILI data is usually delayed by 1-3 weeks. Therefore, several attempts use indirect web-based data to gain more timely estimates of CDC’s ILI, which is also known as nowcasting. The forecasting framework introduced in this paper is able to use those nowcasting approaches to receive a more timely data stream.<br />
<br />
== Motivation ==<br />
<br />
It has been shown that LinEns forecasts outperform the other frameworks on the ILI data-set. However, this framework assumes a deterministic relationship between the epidemic week and its case count, which does not reflect the stochastic nature of the trend. Therefore, it is natural to ask whether a similar framework that assumes a stochastic relationship between these variables would provide a better performance. This motivated the development of the proposed Gaussian process regression framework and the subsequent performance comparison to the benchmark models.<br />
<br />
== Gaussian Process Regression ==<br />
<br />
A Gaussian process is specified with a mean function and a kernel function. Besides, the mean and the variance function of the Gaussian process is defined by:<br />
\[\mu(x) = k(x, X)^T(K_n+\sigma^2I)^{-1}Y\]<br />
\[\sigma(x) = k^{**}(x,x)-k(x,X)^T(K_n+\sigma^2I)^{-1}k(x,X)\]<br />
where <math>K_n</math> is the covariance matrix and for the kernel, it is being specified that it will use the Gaussian kernel.<br />
<br />
Consider the following set up: let <math>X = [\mathbf{x}_1,\ldots,\mathbf{x}_n]</math> <math>(d\times n)</math> be your training data, <math>\mathbf{y} = [y_1,y_2,\ldots,y_n]^T</math> be your noisy observations where <math>y_i = f(\mathbf{x}_i) + \epsilon_i</math>, <math>(\epsilon_i:i = 1,\ldots,n)</math> i.i.d. <math>\sim \mathcal{N}(0,{\sigma}^2)</math>, and <math>f</math> is the trend we are trying to model (by <math>\hat{f}</math>). Let <math>\mathbf{x}^*</math> <math>(d\times 1)</math> be your test data point, and <math>\hat{y} = \hat{f}(\mathbf{x}^*)</math> be your predicted outcome.<br />
<br />
<br />
Instead of assuming a deterministic form of <math>f</math>, and thus of <math>\mathbf{y}</math> and <math>\hat{y}</math> (as classical linear regression would, for example), Gaussian process regression assumes <math>f</math> is stochastic. More precisely, <math>\mathbf{y}</math> and <math>\hat{y}</math> are assumed to have a joint prior distribution. Indeed, we have <br />
<br />
$$<br />
(\mathbf{y},\hat{y}) \sim \mathcal{N}(0,\Sigma(X,\mathbf{x}^*))<br />
$$<br />
<br />
where <math>\Sigma(X,\mathbf{x}^*)</math> is a matrix of covariances dependent on some kernel function <math>k</math>. In this paper, the kernel function is assumed to be Gaussian and takes the form <br />
<br />
$$<br />
k(\mathbf{x}_i,\mathbf{x}_j) = \sigma^2\exp(-\frac{1}{2}(\mathbf{x}_i-\mathbf{x}_j)^T\Sigma(\mathbf{x}_i-\mathbf{x}_j)).<br />
$$<br />
<br />
It is important to note that this gives a joint prior distribution of '''functions''' ('''Fig. 1''' left, grey curves). <br />
<br />
By restricting this distribution to contain only those functions ('''Fig. 1''' right, grey curves) that agree with the observed data points <math>\mathbf{x}</math> ('''Fig. 1''' right, solid black) we obtain the posterior distribution for <math>\hat{y}</math> which has the form<br />
<br />
$$<br />
p(\hat{y} | \mathbf{x}^*, X, \mathbf{y}) \sim \mathcal{N}(\mu(\mathbf{x}^*,X,\mathbf{y}),\sigma(\mathbf{x}^*,X))<br />
$$<br />
<br />
<br />
<div style="text-align:center;"> [[File:GPRegression.png|500px]] </div><br />
<br />
<div align="center">'''Figure 1. Gaussian process regression''': Select the functions from your joint prior distribution (left, grey curves) with mean <math>0</math> (left, bold line) that agree with the observed data points (right, black bullets). These form your posterior distribution (right, grey curves) with mean <math>\mu(\mathbf{x})</math> (right, bold line). Red triangle helps compare the two images (location marker) [4]. </div><br />
<br />
== Data-set ==<br />
<br />
Let <math>d_j^i</math> denote the number of epidemic cases recorded in week <math>j</math> of season <math>i</math>, and let <math>j^*</math> and <math>i^*</math> denote the current week and season, respectively. The ILI data-set contains <math>d_j^i</math> for all previous weeks and seasons, up to the current season with a 1-3 week publishing delay. Note that a season refers to the time of year when the epidemic is prevalent (e.g. an influenza season lasts 30 weeks and contains the last 10 weeks of year k, and the first 20 weeks of year k+1). The goal is to predict <math>\hat{y}_T = \hat{f}_T(x^*) = d^{i^*}_{j* + T}</math> where <math>T, \;(T = 1,\ldots,K)</math> is the target week (how many weeks into the future that you want to predict).<br />
<br />
To do this, a design matrix <math>X</math> is constructed where each element <math>X_{ji} = d_j^i</math> corresponds to the number of cases in week (row) j of season (column) i. The training outcomes <math>y_{i,T}, i = 1,\ldots,n</math> correspond to the number of cases that were observed in target week <math>T,\; (T = 1,\ldots,K)</math> of season <math>i, (i = 1,\ldots,n)</math>.<br />
<br />
== Proposed Framework ==<br />
<br />
To compute <math>\hat{y}</math>, the following algorithm is executed. <br />
<br />
<ol><br />
<br />
<li> Let <math>J \subseteq \{j^*-4 \leq j \leq j^*\}</math> (subset of possible weeks).<br />
<br />
<li> Assemble the Training Set <math>\{X_J, \mathbf{y}_{T,J}\}</math> <br />
<br />
<li> Train the Gaussian process<br />
<br />
<li> Calculate the '''distribution''' of <math>\hat{y}_{T,J}</math> using <math>p(\hat{y}_{T,J} | \mathbf{x}^*, X_J, \mathbf{y}_{T,J}) \sim \mathcal{N}(\mu(\mathbf{x}^*,X,\mathbf{y}_{T,J}),\sigma(\mathbf{x}^*,X_J))</math><br />
<br />
<li> Set <math>\hat{y}_{T,J} =\mu(x^*,X_J,\mathbf{y}_{T,J})</math><br />
<br />
<li> Repeat steps 2-5 for all sets of weeks <math>J</math><br />
<br />
<li> Determine the best 3 performing sets J (on the 2010/11 and 2011/12 validation sets)<br />
<br />
<li> Calculate the ensemble forecast by averaging the 3 best performing predictive distribution densities i.e. <math>\hat{y}_T = \frac{1}{3}\sum_{k=1}^3 \hat{y}_{T,J_{best}}</math><br />
<br />
</ol><br />
<br />
== Results ==<br />
<br />
To demonstrate the accuracy of their results, retrospective forecasting was done on the ILI data-set. In other words, the Gaussian process model was trained to assume a previous season (2012/13) was the current season. In this fashion, the forecast could be compared to the already observed true outcome. <br />
<br />
To produce a forecast for the entire 2012/13 season, 30 Gaussian processes were trained (each influenza season has 30 test points <math>\mathbf{x^*}</math>) and a curve connecting the predicted outputs <math>y_T = \hat{f}(\mathbf{x^*)}</math> was plotted ('''Fig.2''', blue line). As shown in '''Fig.2''', this forecast (blue line) was reliable for both 1 (left) and 3 (right) week targets, given that the 95% prediction interval ('''Fig.2''', purple shaded) contained the true values ('''Fig.2''', red x's) 95% of the time.<br />
<br />
<div style="text-align:center;"> [[File:ResultsOne.png|600px]] </div><br />
<br />
<div align="center">'''Figure 2. Retrospective forecasts and their uncertainty''': One week retrospective influenza forecasting for two targets (T = 1, 3). Red x’s are the true observed values, and blue lines and purple shaded areas represent point forecasts and 95% prediction intervals, respectively. </div><br />
<br />
<br />
Moreover, as shown in '''Fig.3''', the novel Gaussian process regression framework outperformed all state-of-the-art models, included LinEns, for four different targets <math>(T = 1,\ldots, 4)</math>, when compared using the official CDC scoring criterion ''log-score''. Log-score describes the logarithmic probability of the forecast being within an interval around the true value. <br />
<br />
<div style="text-align:center;"> [[File:ComparisonNew.png|600px]] </div><br />
<br />
<div align="center">'''Figure 3. Average log-score gain of proposed framework''': Each bar shows the mean seasonal log-score gain of the proposed framework vs. the given state-of-the-art model, and each panel corresponds to a different target week <math> T = 1,...4 </math>. </div><br />
<br />
== Conclusion ==<br />
<br />
This paper presented a novel framework for forecasting seasonal epidemics using Gaussian process regression that outperformed multiple state-of-the-art forecasting methods on the CDC's ILI data-set. Since influenza data has only been collected from 2003, therefore as more data is obtained: the training models can be further improved upon with more robust model optimizations. Hence, this work may play a key role in future influenza forecasting and as result, the improvement of public health policies and resource allocation.<br />
<br />
== Critique ==<br />
<br />
The proposed framework provides a computationally efficient method to forecast any seasonal epidemic count data that is easily extendable to multiple target types. In particular, one can compute key parameters such as the peak infection incidence <math>\left(\hat{y} = \text{max}_{0 \leq j \leq 52} d^i_j \right)</math>, the timing of the peak infection incidence <math>\left(\hat{y} = \text{argmax}_{0 \leq j \leq 52} d^i_j\right)</math> and the final epidemic size of a season <math>\left(\hat{y} = \sum_{j=1}^{52} d^i_j\right)</math>. However, given it is not a physical model, it cannot provide insights on parameters describing the disease spread. Moreover, the framework requires training data and hence, is not applicable for non-seasonal epidemics.<br />
<br />
This paper provides a state of the art approach for forecasting epidemics. It would have been interesting to see other types of kernels being used, such as a periodic kernel <math>k(x, x') = \sigma^2 \exp\left({-\frac{2 \sin^2 (\pi|x-x'|)/p}{l^2}}\right) </math>, as intuitively epidemics are known to have waves within seasons. This may have resulted in better-calibrated uncertainty estimates as well.<br />
<br />
It is mentioned that the the framework might not be good for non-seasonal epidemics because it requires training data, given that the COVID-19 pandemic comes in multiple waves and we have enough data from the first wave and second wave, we might be able to use this framework to predict the third wave and possibly the fourth one as well. It'd be interesting to see this forecasting framework being trained using the data from the first and second wave of COVID-19.<br />
<br />
Gaussian Process Regression (GPR) can be extended to COVID-19 outbreak forecast (link: https://link.springer.com/article/10.1007/s10489-020-01889-9). A Multi-Task Gaussian Process Regression (MTGP) model is a special case of GPR that yields multiple outputs. It was first proposed back in 2008, and its recent application was in the battery capacity prediction by Richardson et. al. The proposed MTGP model was applied on Worldwide, China, India, Italy, and USA data that covers COVID-19 statistics from Dec 31 2019 to June 25 2020. Results show that MTGP outperforms linear regression, support vector regression, random forest regression, and long short-term memory model when it comes to forecasting accuracy.<br />
<br />
A critique for GPR is that it does not take into account the physicality of the epidemic process. So it would be interesting to investigate if we can incorporate elements of physical processes in this such as using Ordinary Differential Equations (ODE) based modeling and seeing if that improves prediction accuracy or helps us explain phenomena.<br />
<br />
== References ==<br />
<br />
[1] Estimated Influenza Illnesses, Medical visits, Hospitalizations, and Deaths in the United States - 2019–2020 Influenza Season. (2020). Retrieved November 16, 2020, from https://www.cdc.gov/flu/about/burden/2019-2020.html<br />
<br />
[2] Ray, E. L., Sakrejda, K., Lauer, S. A., Johansson, M. A.,and Reich, N. G. (2017).Infectious disease prediction with kernel conditional densityestimation.Statistics in Medicine, 36(30):4908–4929.<br />
<br />
[3] Ketu, S., Mishra, P.K. Enhanced Gaussian process regression-based forecasting model for COVID-19 outbreak and significance of IoT for its detection. Appl Intell (2020). https://doi.org/10.1007/s10489-020-01889-9<br />
<br />
[4] Schulz, E., Speekenbrink, M., and Krause, A. (2017).A tutorial on gaussian process regression with a focus onexploration-exploitation scenarios.bioRxiv.<br />
<br />
[5] Zimmer, C., Leuba, S. I., Cohen, T., and Yaesoubi, R.(2019).Accurate quantification of uncertainty in epidemicparameter estimates and predictions using stochasticcompartmental models.Statistical Methods in Medical Research,28(12):3591–3608.PMID: 30428780.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Influenza_Forecasting_Framework_based_on_Gaussian_Processes&diff=45973Influenza Forecasting Framework based on Gaussian Processes2020-11-23T02:28:42Z<p>J244yang: /* References */ Adding a ref</p>
<hr />
<div><br />
== Abstract ==<br />
<br />
This paper presents a novel framework for seasonal epidemic forecasting using Gaussian process regression. Compared with other state-of-the-art models, the new novel framework introduced in this paper shows accurate retrospective forecasts through training a subset of the CDC influenza-like-illness (ILI) dataset using the official CDC scoring rule (log-score).<br />
<br />
== Background ==<br />
<br />
Each year, the seasonal influenza epidemic affects public health systems across the globe at a massive scale. In 2019-2020 alone, the United States reported 38 million cases, 400 000 hospitalizations, and 22 000 deaths [1]. A direct result of this is the need for reliable forecasts of future influenza development, because they allow for improved public health policies and informed resource development and allocation. Many statistical methods have been developed to use data from the CDC and other real-time data sources, such as Google Trends to forecast influenza activities.<br />
<br />
Given the process of data collection and surveillance lag, accurate statistics for influenza warning systems are often delayed by some margin of time, making early prediction imperative. However, there are challenges in long-term epidemic forecasting. First, the temporal dependency is hard to capture with short-term input data. Without manually added seasonal trends, most statistical models fail to provide high accuracy. Second, the influence from other locations has not been exhaustively explored with limited data input. Spatio-temporal effects would therefore require adequate data sources to achieve good performance.<br />
<br />
== Related Work ==<br />
<br />
Given the value of epidemic forecasts, the CDC regularly publishes ILI data and has funded a seasonal ILI forecasting challenge. This challenge has led to four state-of-the-art models in the field: Historical averages, a method using the counts of past seasons to build a kernel density estimate; MSS, a physical susceptible-infected-recovered model with assumed linear noise [4]; SARIMA, a framework based on seasonal auto-regressive moving average models [2]; and LinEns, an ensemble of three linear regression models.<br />
<br />
One disadvantage of forecasting is that the publication of CDC official ILI data is usually delayed by 1-3 weeks. Therefore, several attempts use indirect web-based data to gain more timely estimates of CDC’s ILI, which is also known as nowcasting. The forecasting framework introduced in this paper is able to use those nowcasting approaches to receive a more timely data stream.<br />
<br />
== Motivation ==<br />
<br />
It has been shown that LinEns forecasts outperform the other frameworks on the ILI data-set. However, this framework assumes a deterministic relationship between the epidemic week and its case count, which does not reflect the stochastic nature of the trend. Therefore, it is natural to ask whether a similar framework that assumes a stochastic relationship between these variables would provide a better performance. This motivated the development of the proposed Gaussian process regression framework and the subsequent performance comparison to the benchmark models.<br />
<br />
== Gaussian Process Regression ==<br />
<br />
A Gaussian process is specified with a mean function and a kernel function. Besides, the mean and the variance function of the Gaussian process is defined by:<br />
\[\mu(x) = k(x, X)^T(K_n+\sigma^2I)^{-1}Y\]<br />
\[\sigma(x) = k^{**}(x,x)-k(x,X)^T(K_n+\sigma^2I)^{-1}k(x,X)\]<br />
where <math>K_n</math> is the covariance matrix and for the kernel, it is being specified that it will use the Gaussian kernel.<br />
<br />
Consider the following set up: let <math>X = [\mathbf{x}_1,\ldots,\mathbf{x}_n]</math> <math>(d\times n)</math> be your training data, <math>\mathbf{y} = [y_1,y_2,\ldots,y_n]^T</math> be your noisy observations where <math>y_i = f(\mathbf{x}_i) + \epsilon_i</math>, <math>(\epsilon_i:i = 1,\ldots,n)</math> i.i.d. <math>\sim \mathcal{N}(0,{\sigma}^2)</math>, and <math>f</math> is the trend we are trying to model (by <math>\hat{f}</math>). Let <math>\mathbf{x}^*</math> <math>(d\times 1)</math> be your test data point, and <math>\hat{y} = \hat{f}(\mathbf{x}^*)</math> be your predicted outcome.<br />
<br />
<br />
Instead of assuming a deterministic form of <math>f</math>, and thus of <math>\mathbf{y}</math> and <math>\hat{y}</math> (as classical linear regression would, for example), Gaussian process regression assumes <math>f</math> is stochastic. More precisely, <math>\mathbf{y}</math> and <math>\hat{y}</math> are assumed to have a joint prior distribution. Indeed, we have <br />
<br />
$$<br />
(\mathbf{y},\hat{y}) \sim \mathcal{N}(0,\Sigma(X,\mathbf{x}^*))<br />
$$<br />
<br />
where <math>\Sigma(X,\mathbf{x}^*)</math> is a matrix of covariances dependent on some kernel function <math>k</math>. In this paper, the kernel function is assumed to be Gaussian and takes the form <br />
<br />
$$<br />
k(\mathbf{x}_i,\mathbf{x}_j) = \sigma^2\exp(-\frac{1}{2}(\mathbf{x}_i-\mathbf{x}_j)^T\Sigma(\mathbf{x}_i-\mathbf{x}_j)).<br />
$$<br />
<br />
It is important to note that this gives a joint prior distribution of '''functions''' ('''Fig. 1''' left, grey curves). <br />
<br />
By restricting this distribution to contain only those functions ('''Fig. 1''' right, grey curves) that agree with the observed data points <math>\mathbf{x}</math> ('''Fig. 1''' right, solid black) we obtain the posterior distribution for <math>\hat{y}</math> which has the form<br />
<br />
$$<br />
p(\hat{y} | \mathbf{x}^*, X, \mathbf{y}) \sim \mathcal{N}(\mu(\mathbf{x}^*,X,\mathbf{y}),\sigma(\mathbf{x}^*,X))<br />
$$<br />
<br />
<br />
<div style="text-align:center;"> [[File:GPRegression.png|500px]] </div><br />
<br />
<div align="center">'''Figure 1. Gaussian process regression''': Select the functions from your joint prior distribution (left, grey curves) with mean <math>0</math> (left, bold line) that agree with the observed data points (right, black bullets). These form your posterior distribution (right, grey curves) with mean <math>\mu(\mathbf{x})</math> (right, bold line). Red triangle helps compare the two images (location marker) [3]. </div><br />
<br />
== Data-set ==<br />
<br />
Let <math>d_j^i</math> denote the number of epidemic cases recorded in week <math>j</math> of season <math>i</math>, and let <math>j^*</math> and <math>i^*</math> denote the current week and season, respectively. The ILI data-set contains <math>d_j^i</math> for all previous weeks and seasons, up to the current season with a 1-3 week publishing delay. Note that a season refers to the time of year when the epidemic is prevalent (e.g. an influenza season lasts 30 weeks and contains the last 10 weeks of year k, and the first 20 weeks of year k+1). The goal is to predict <math>\hat{y}_T = \hat{f}_T(x^*) = d^{i^*}_{j* + T}</math> where <math>T, \;(T = 1,\ldots,K)</math> is the target week (how many weeks into the future that you want to predict).<br />
<br />
To do this, a design matrix <math>X</math> is constructed where each element <math>X_{ji} = d_j^i</math> corresponds to the number of cases in week (row) j of season (column) i. The training outcomes <math>y_{i,T}, i = 1,\ldots,n</math> correspond to the number of cases that were observed in target week <math>T,\; (T = 1,\ldots,K)</math> of season <math>i, (i = 1,\ldots,n)</math>.<br />
<br />
== Proposed Framework ==<br />
<br />
To compute <math>\hat{y}</math>, the following algorithm is executed. <br />
<br />
<ol><br />
<br />
<li> Let <math>J \subseteq \{j^*-4 \leq j \leq j^*\}</math> (subset of possible weeks).<br />
<br />
<li> Assemble the Training Set <math>\{X_J, \mathbf{y}_{T,J}\}</math> <br />
<br />
<li> Train the Gaussian process<br />
<br />
<li> Calculate the '''distribution''' of <math>\hat{y}_{T,J}</math> using <math>p(\hat{y}_{T,J} | \mathbf{x}^*, X_J, \mathbf{y}_{T,J}) \sim \mathcal{N}(\mu(\mathbf{x}^*,X,\mathbf{y}_{T,J}),\sigma(\mathbf{x}^*,X_J))</math><br />
<br />
<li> Set <math>\hat{y}_{T,J} =\mu(x^*,X_J,\mathbf{y}_{T,J})</math><br />
<br />
<li> Repeat steps 2-5 for all sets of weeks <math>J</math><br />
<br />
<li> Determine the best 3 performing sets J (on the 2010/11 and 2011/12 validation sets)<br />
<br />
<li> Calculate the ensemble forecast by averaging the 3 best performing predictive distribution densities i.e. <math>\hat{y}_T = \frac{1}{3}\sum_{k=1}^3 \hat{y}_{T,J_{best}}</math><br />
<br />
</ol><br />
<br />
== Results ==<br />
<br />
To demonstrate the accuracy of their results, retrospective forecasting was done on the ILI data-set. In other words, the Gaussian process model was trained to assume a previous season (2012/13) was the current season. In this fashion, the forecast could be compared to the already observed true outcome. <br />
<br />
To produce a forecast for the entire 2012/13 season, 30 Gaussian processes were trained (each influenza season has 30 test points <math>\mathbf{x^*}</math>) and a curve connecting the predicted outputs <math>y_T = \hat{f}(\mathbf{x^*)}</math> was plotted ('''Fig.2''', blue line). As shown in '''Fig.2''', this forecast (blue line) was reliable for both 1 (left) and 3 (right) week targets, given that the 95% prediction interval ('''Fig.2''', purple shaded) contained the true values ('''Fig.2''', red x's) 95% of the time.<br />
<br />
<div style="text-align:center;"> [[File:ResultsOne.png|600px]] </div><br />
<br />
<div align="center">'''Figure 2. Retrospective forecasts and their uncertainty''': One week retrospective influenza forecasting for two targets (T = 1, 3). Red x’s are the true observed values, and blue lines and purple shaded areas represent point forecasts and 95% prediction intervals, respectively. </div><br />
<br />
<br />
Moreover, as shown in '''Fig.3''', the novel Gaussian process regression framework outperformed all state-of-the-art models, included LinEns, for four different targets <math>(T = 1,\ldots, 4)</math>, when compared using the official CDC scoring criterion ''log-score''. Log-score describes the logarithmic probability of the forecast being within an interval around the true value. <br />
<br />
<div style="text-align:center;"> [[File:ComparisonNew.png|600px]] </div><br />
<br />
<div align="center">'''Figure 3. Average log-score gain of proposed framework''': Each bar shows the mean seasonal log-score gain of the proposed framework vs. the given state-of-the-art model, and each panel corresponds to a different target week <math> T = 1,...4 </math>. </div><br />
<br />
== Conclusion ==<br />
<br />
This paper presented a novel framework for forecasting seasonal epidemics using Gaussian process regression that outperformed multiple state-of-the-art forecasting methods on the CDC's ILI data-set. Since influenza data has only been collected from 2003, therefore as more data is obtained: the training models can be further improved upon with more robust model optimizations. Hence, this work may play a key role in future influenza forecasting and as result, the improvement of public health policies and resource allocation.<br />
<br />
== Critique ==<br />
<br />
The proposed framework provides a computationally efficient method to forecast any seasonal epidemic count data that is easily extendable to multiple target types. In particular, one can compute key parameters such as the peak infection incidence <math>\left(\hat{y} = \text{max}_{0 \leq j \leq 52} d^i_j \right)</math>, the timing of the peak infection incidence <math>\left(\hat{y} = \text{argmax}_{0 \leq j \leq 52} d^i_j\right)</math> and the final epidemic size of a season <math>\left(\hat{y} = \sum_{j=1}^{52} d^i_j\right)</math>. However, given it is not a physical model, it cannot provide insights on parameters describing the disease spread. Moreover, the framework requires training data and hence, is not applicable for non-seasonal epidemics.<br />
<br />
This paper provides a state of the art approach for forecasting epidemics. It would have been interesting to see other types of kernels being used, such as a periodic kernel <math>k(x, x') = \sigma^2 \exp\left({-\frac{2 \sin^2 (\pi|x-x'|)/p}{l^2}}\right) </math>, as intuitively epidemics are known to have waves within seasons. This may have resulted in better-calibrated uncertainty estimates as well.<br />
<br />
It is mentioned that the the framework might not be good for non-seasonal epidemics because it requires training data, given that the COVID-19 pandemic comes in multiple waves and we have enough data from the first wave and second wave, we might be able to use this framework to predict the third wave and possibly the fourth one as well. It'd be interesting to see this forecasting framework being trained using the data from the first and second wave of COVID-19.<br />
<br />
Gaussian Process Regression (GPR) can be extended to COVID-19 outbreak forecast (link: https://link.springer.com/article/10.1007/s10489-020-01889-9). A Multi-Task Gaussian Process Regression (MTGP) model is a special case of GPR that yields multiple outputs. It was first proposed back in 2008, and its recent application was in the battery capacity prediction by Richardson et. al. The proposed MTGP model was applied on Worldwide, China, India, Italy, and USA data that covers COVID-19 statistics from Dec 31 2019 to June 25 2020. Results show that MTGP outperforms linear regression, support vector regression, random forest regression, and long short-term memory model when it comes to forecasting accuracy.<br />
<br />
A critique for GPR is that it does not take into account the physicality of the epidemic process. So it would be interesting to investigate if we can incorporate elements of physical processes in this such as using Ordinary Differential Equations (ODE) based modeling and seeing if that improves prediction accuracy or helps us explain phenomena.<br />
<br />
== References ==<br />
<br />
[1] Estimated Influenza Illnesses, Medical visits, Hospitalizations, and Deaths in the United States - 2019–2020 Influenza Season. (2020). Retrieved November 16, 2020, from https://www.cdc.gov/flu/about/burden/2019-2020.html<br />
<br />
[2] Ray, E. L., Sakrejda, K., Lauer, S. A., Johansson, M. A.,and Reich, N. G. (2017).Infectious disease prediction with kernel conditional densityestimation.Statistics in Medicine, 36(30):4908–4929.<br />
<br />
[3] Ketu, S., Mishra, P.K. Enhanced Gaussian process regression-based forecasting model for COVID-19 outbreak and significance of IoT for its detection. Appl Intell (2020). https://doi.org/10.1007/s10489-020-01889-9<br />
<br />
[4] Schulz, E., Speekenbrink, M., and Krause, A. (2017).A tutorial on gaussian process regression with a focus onexploration-exploitation scenarios.bioRxiv.<br />
<br />
[5] Zimmer, C., Leuba, S. I., Cohen, T., and Yaesoubi, R.(2019).Accurate quantification of uncertainty in epidemicparameter estimates and predictions using stochasticcompartmental models.Statistical Methods in Medical Research,28(12):3591–3608.PMID: 30428780.</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=Streaming_Bayesian_Inference_for_Crowdsourced_Classification&diff=45969Streaming Bayesian Inference for Crowdsourced Classification2020-11-23T02:17:52Z<p>J244yang: /* Empirical Analysis */</p>
<hr />
<div>Group 4 Paper Presentation Summary<br />
<br />
By Jonathan Chow, Nyle Dharani, Ildar Nasirov<br />
<br />
== Motivation ==<br />
Crowdsourcing can be a useful tool for data generation in classification projects. Often this takes the form of online questions which many respondents will manually answer for payment. One example of this is Amazon's Mechanical Turk, a website where businesses (or "requesters") will remotely hire individuals(known as "Turkers" or "crowdsourcers") to perform human intelligence tasks (tasks that computers cannot do). In theory, it is effective in processing high volumes of small tasks that would be expensive to achieve otherwise.<br />
<br />
The primary limitation with this form of acquiring data is that respondents are liable to submit incorrect responses. This results in datasets that are noisy and unreliable.<br />
<br />
However, the integrity of the data is then limited by how well ground-truth can be determined. The primary method for doing so is probabilistic inference. However, current methods are computationally expensive, lack theoretical guarantees, or are limited to specific settings.<br />
<br />
== Dawid-Skene Model for Crowdsourcing ==<br />
The one-coin Dawid-Skene model is popular for contextualizing crowdsourcing problems. For task <math>i</math> in set <math>M</math>, let the ground-truth be the binary <math>y_i = {\pm 1}</math>. We get labels <math>X = {x_{ij}}</math> where <math>j \in N</math> is the index for that worker.<br />
<br />
At each time step <math>t</math>, a worker <math>j = a(t) </math> provides their label for an assigned task <math>i</math> and provides the label<math>x_{ij} = {\pm 1}</math>. We denote responses up to time <math>t</math> via superscript.<br />
<br />
We let <math>x_{ij} = 0</math> if worker <math>j</math> has not completed task <math>i</math>. We assume that <math>P(x_{ij} = y_i) = p_j</math>. This implies that each worker is independent and has equal probability of correctly labelling regardless of task. In crowdsourcing the data, we must determine how workers are assigned to tasks. We introduce two methods.<br />
<br />
Under uniform sampling, workers are allocated to tasks such that each task is completed by the same number of workers, rounded to the nearest integer, and no worker completes a task more than once. This policy is given by <center><math>\pi_{uni}(t) = argmin_{i \notin M_{a(t)}^t}\{ | N_i^t | \}.</math></center><br />
<br />
Under uncertainty sampling, we assign more workers to tasks that are less certain. Assuming, we are able to estimate the posterior probability of ground-truth, we can allocate workers to the task with the lowest probability of falling into the predicted class. This policy is given by <center><math>\pi_{us}(t) = argmin_{i \notin M_{a(t)}^t}\{ (max_{k \in \{\pm 1\}} ( P(y_i = k | X^t) ) \}.</math></center><br />
<br />
We then need to aggregate the data. The simple method of majority voting makes predictions for a given task based on the class the most workers have assigned it, <math>\hat{y}_i = \text{sign}\{\sum_{j \in N_i} x_{ij}\}</math>.<br />
<br />
== Streaming Bayesian Inference for Crowdsourced Classification (SBIC) ==<br />
The aim of the SBIC algorithm is to estimate the posterior probability, <math>P(y, p | X^t, \theta)</math> where <math>X^t</math> are the observed responses at time <math>t</math> and <math>\theta</math> is our prior. We can then generate predictions <math>\hat{y}^t</math> as the marginal probability over each <math>y_i</math> given <math>X^t</math>, and <math>\theta</math>.<br />
<br />
We factor <math>P(y, p | X^t, \theta) \approx \prod_{i \in M} \mu_i^t (y_i) \prod_{j \in N} \nu_j^t (p_j) </math> where <math>\mu_i^t</math> corresponds to each task and <math>\nu_j^t</math> to each worker.<br />
<br />
We then sequentially optimize the factors <math>\mu^t</math> and <math>\nu^t</math>. We begin by assuming that the worker accuracy follows a beta distribution with parameters <math>\alpha</math> and <math>\beta</math>. Initialize the task factors <math>\mu_i^0(+1) = q</math> and <math>\mu_i^0(-1) = 1 – q</math> for all <math>i</math>.<br />
<br />
When a new label is observed at time <math>t</math>, we update the <math>\nu_j^t</math> of worker <math>j</math>. We then update <math>\mu_i</math>. These updates are given by<br />
<br />
<center><math>\nu_j^t(p_j) \sim \text{Beta}(\sum_{i \in M_j^{t - 1}} \mu_i^{t - 1}(x_{ij}) + \alpha, \sum_{i \in M_j^{t - 1}} \mu_i^{t - 1}(-x_{ij}) + \beta) </math></center><br />
<br />
<center><math>\mu_i^t(y_i) \propto \begin{cases} \mu_i^{t - 1}(y_i)\overline{p}_j^t & x_{ij} = y_i \\ \mu_i^{t - 1}(y_i)(1 - \overline{p}_j^t) & x_{ij} \ne y_i \end{cases}</math></center><br />
where <math>\hat{p}_j^t = \frac{\sum_{i \in M_j^{t - 1}} \mu_i^{t - 1}(x_{ij}) + \alpha}{|M_j^{t - 1}| + \alpha + \beta }</math>.<br />
<br />
We choose our predictions to be the maximum <math>\mu_i^t(k) </math> for <math>k= \{-1,1\}</math>.<br />
<br />
Depending on our ordering of labels <math>X</math>, we can select for different applications.<br />
<br />
== Fast SBIC ==<br />
The pseudocode for Fast SBIC is shown below.<br />
<br />
<center>[[Image:FastSBIC.png|800px|]]</center><br />
<br />
As the name implies, the goal of this algorithm is speed. To facilitate this, we leave the order of <math>X</math> unchanged.<br />
<br />
We express <math>\mu_i^t</math> in terms of its log-odds<br />
<center><math>z_i^t = \log(\frac{\mu_i^t(+1)}{ \mu_i^t(-1)}) = z_i^{t - 1} + x_{ij} \log(\frac{\overline{p}_j^t}{1 - \overline{p}_j^t })</math></center><br />
where <math>z_i^0 = \log(\frac{q}{1 - q})</math>.<br />
<br />
The product chain then becomes a summation and removes the need to normalize each <math>\mu_i^t</math>. We use these log-odds to compute worker accuracy,<br />
<br />
<center><math>\overline{p}_j^t = \frac{\sum_{i \in M_j^{t - 1}} \sigma(x_{ij} z_i^{t-1}) + \alpha}{|M_j^{t - 1}| + \alpha + \beta}</math></center><br />
where <math>\sigma(z_i^{t-1}) := \frac{1}{1 + exp(-z_i^{t - 1})} = \mu_i^{t - 1}(+1) </math><br />
<br />
The final predictions are made by choosing class <math>\hat{y}_i^T = \text{sign}(z_i^T) </math>. We see later that Fast SBIC has similar computational speed to majority voting.<br />
<br />
== Sorted SBIC ==<br />
To increase the accuracy of the SBIC algorithm in exchange for computational efficiency, we run the algorithm in parallel giving labels in different orders. The pseudocode for this algorithm is given below.<br />
<br />
<center>[[Image:SortedSBIC.png|800px|]]</center><br />
<br />
From the general discussion of SBIC, we know that predictions on task <math>i</math> are more accurate toward the end of the collection process. This is a result of observing more data points and having run more updates on <math>\mu_i^t</math> and <math>\nu_j^t</math> to move them further from their prior. This means that task <math>i</math> is predicted more accurately when its corresponding labels are seen closer to the end of the process.<br />
<br />
We take advantage of this property by maintaining a distinct “view” of the log-odds for each task. When a label is observed, we update views for all tasks except the one for which the label was observed. At the end of the collection process, we process skipped labels. When run online, this process must be repeated at every timestep.<br />
<br />
We see that sorted SBIC is slower than Fast SBIC by a factor of M, the number of tasks. However, we can reduce the complexity by viewing <math>s^k</math> across different tasks in an offline setting when the whole dataset is known in advance.<br />
<br />
== Theoretical Analysis ==<br />
The authors prove an exponential relationship between the error probability and the number of labels per task. This allows for an upper bound to be placed on the error, in the asymptotic regime, where it can be assumed the SBIC predictions are close to the true values. The two theorems, for the different sampling regimes, are presented below.<br />
<br />
<center>[[Image:Theorem1.png|800px|]]</center><br />
<br />
<center>[[Image:Theorem2.png|800px|]]</center><br />
<br />
== Empirical Analysis ==<br />
The purpose of the empirical analysis is to compare SBIC to the existing state of the art algorithms. The SBIC algorithm is run on five real-world binary classification datasets. The results can be found in the table below. Other algorithms in the comparison are, from left to right, majority voting, expectation-maximization, mean-field, belief-propagation, Monte-Carlo sampling, and triangular estimation. <br />
<br />
First of all, the algorithms are run on a synthetic data that meets the assumptions of an underlying one-coin Dawid-Skene model, which allows the authors to compare SBIC's performance empirically with the theoretical results previously shown. <br />
<br />
<center>[[Image:RealWorldResults.png|800px|]]</center><br />
<br />
In bold are the best performing algorithms for each dataset. We see that both versions of the SBIC algorithm are competitive, having similar prediction errors to EM, AMF, and MC. All are considered state-of-the-art Bayesian algorithms.<br />
<br />
The figure below shows the average time required to simulate predictions on synthetic data under an uncertainty sampling policy. We see that Fast SBIC is comparable to majority voting and significantly faster than the other algorithms. This speed improvement, coupled with comparable accuracy, makes the Fast SBIC algorithm powerful.<br />
<br />
<center>[[Image:TimeRequirement.png|800px|]]</center><br />
<br />
== Conclusion and Future Research ==<br />
In conclusion, we have seen that SBIC is computationally efficient, accurate in practice, and has theoretical guarantees. The authors intend to extend the algorithm to the multi-class case in the future.<br />
<br />
== Critique ==<br />
In crowdsourcing data, the cost associated with collecting additional labels is not usually prohibitively expensive. As a result, if there is concern over ground-truth, paying for additional data to ensure <math>X</math> is sufficiently dense may be the desired response as opposed to sacrificing ground-truth accuracy. This may result in the SBIC algorithm being less practically useful than intended.Perhaps, a study can be done to compare the cost of acquiring additional data and checking how much it improves the accuracy of ground-truth. This can help us decide the usefulness of this algorithm.Second, SBIC should be used in multiple types of data like audio, text and images to make sure that it delivers consistent results. <br />
<br />
The paper is tackling the classic problem of aggregating labels in a crowdsourced application, with a focus on speed. The algorithms proposed are fast and simple to implement and come with theoretical guarantees on the bounds for error rates. However, the paper starts with an objective of designing fast label aggregation algorithms for a streaming setting yet doesn’t spend any time motivating the applications in which such algorithms are needed. All the datasets used in the empirical analysis are static datasets therefore for the paper to be useful, the problem considered should be well motivated. It also appears that the output from the algorithm depends on the order in which the data is processed, which may need to be clarified. Finally, the theoretical results are presented under the assumption that the predictions of the FBI converge to the ground truth, however, the reasoning behind this assumption is not explained.<br />
<br />
The paper assumes that crowdsourcing from human beings is systematic: that is, respondents to the problems would act in similar ways that can be classified into some categories. There are lots of other factors that need to be considered for a human respondent, such as fatigue effects and conflicts of interest. Those factors would seriously jeopardize the validity of the results and the model if they were not carefully designed and taken care of. For example, one formally accurate subject reacts badly to the subject one day generating lots of faulty data, and it would take lots of correct votes to even out the effects. Even in lots of medical experiment that involves human subjects, with rigorous standards and procedures, the results could still be invalid. The trade-off for speed while sacrificing validity of results is not wise.<br />
<br />
== References ==<br />
[1] Manino, Tran-Thanh, and Jennings. Streaming Bayesian Inference for Crowdsourced Classification. 33rd Conference on Neural Information Processing Systems, 2019</div>J244yanghttp://wiki.math.uwaterloo.ca/statwiki/index.php?title=F21-STAT_441/841_CM_763-Proposal&diff=42635F21-STAT 441/841 CM 763-Proposal2020-10-08T03:31:41Z<p>J244yang: Added Group 11</p>
<hr />
<div>Use this format (Don’t remove Project 0)<br />
<br />
Project # 0 Group members:<br />
<br />
Last name, First name<br />
<br />
Last name, First name<br />
<br />
Last name, First name<br />
<br />
Last name, First name<br />
<br />
Title: Making a String Telephone<br />
<br />
Description: We use paper cups to make a string phone and talk with friends while learning about sound waves with this science project. (Explain your project in one or two paragraphs).<br />
<br />
--------------------------------------------------------------------<br />
<br />
'''Project # 1 Group members:'''<br />
<br />
Song, Quinn<br />
<br />
Loh, William<br />
<br />
Bai, Junyue<br />
<br />
Choi, Phoebe<br />
<br />
'''Title:''' APTOS 2019 Blindness Detection<br />
<br />
'''Description:'''<br />
<br />
Our team chose the APTOS 2019 Blindness Detection Challenge from Kaggle. The goal of this challenge is to build a machine learning model that detects diabetic retinopathy by screening retina images.<br />
<br />
Millions of people suffer from diabetic retinopathy, the leading cause of blindness among working-aged adults. It is caused by damage to the blood vessels of the light-sensitive tissue at the back of the eye (retina). In rural areas where medical screening is difficult to conduct, it is challenging to detect the disease efficiently. Aravind Eye Hospital hopes to utilize machine learning techniques to gain the ability to automatically screen images for disease and provide information on how severe the condition may be.<br />
<br />
Our team plans to solve this problem by applying our knowledge in image processing and classification.<br />
<br />
<br />
----<br />
<br />
'''Project # 2 Group members:'''<br />
<br />
Li, Dylan<br />
<br />
Li, Mingdao<br />
<br />
Lu, Leonie<br />
<br />
Sharman,Bharat<br />
<br />
'''Title:''' Risk prediction in life insurance industry using supervised learning algorithms<br />
<br />
'''Description:'''<br />
<br />
In this project, we aim to replicate and possibly improve upon the work of Jayabalan et al. in their paper “Risk prediction in life insurance industry using supervised learning algorithms”. We will be using the Prudential Life Insurance Data Set that the authors have used and have shared with us. We will be pre-processing the data to replace missing values, using feature selection using CFS and feature reduction using PCA use this processed data to perform Classification via four algorithms – Neural Networks, Random Tree, REPTree and Multiple Linear Regression. We will compare the performance of these Algorithms using MAE and RMSE metrics and come up with visualizations that can explain the results easily even to a non-quantitative audience. <br />
<br />
Our goal behind this project is to learn applying the algorithms that we learned in our class to an industry dataset and come up with results that we can aid better, data-driven decision making.<br />
<br />
----<br />
<br />
'''Project # 3 Group members:'''<br />
<br />
Parco, Russel<br />
<br />
Sun, Scholar<br />
<br />
Yao, Jacky<br />
<br />
Zhang, Daniel<br />
<br />
'''Title:''' Lyft Motion Prediction for Autonomous Vehicles<br />
<br />
'''Description:''' <br />
<br />
Our team has decided to participate in the Lyft Motion Prediction for Autonomous Vehicles Kaggle competition. The aim of this competition is to build a model which given a set of objects on the road (pedestrians, other cars, etc), predict the future movement of these objects.<br />
<br />
Autonomous vehicles (AVs) are expected to dramatically redefine the future of transportation. However, there are still significant engineering challenges to be solved before one can fully realize the benefits of self-driving cars. One such challenge is building models that reliably predict the movement of traffic agents around the AV, such as cars, cyclists, and pedestrians.<br />
<br />
Our aim is to apply classification techniques learned in class to optimally predict how these objects move.<br />
<br />
----<br />
<br />
'''Project # 4 Group members:'''<br />
<br />
Chow, Jonathan<br />
<br />
Dharani, Nyle<br />
<br />
Nasirov, Ildar<br />
<br />
'''Title:''' Classification with Abstinence<br />
<br />
'''Description:''' <br />
<br />
We seek to implement the algorithm described in [https://papers.nips.cc/paper/9247-deep-gamblers-learning-to-abstain-with-portfolio-theory.pdf Deep Gamblers: Learning to Abstain with Portfolio Theory]. The paper describes augmenting classification problems to include the option of abstaining from making a prediction when confidence is low.<br />
<br />
Medical imaging diagnostics is a field in which classification could assist professionals and improve life expectancy for patients through increased accuracy. However, there are also severe consequences to incorrect predictions. As such, we also hope to apply the algorithm implemented to the classification of medical images, specifically instances of normal and pneumonia [https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia? chest x-rays]. <br />
<br />
----<br />
<br />
'''Project # 5 Group members:'''<br />
<br />
Jones, Hayden<br />
<br />
Leung, Michael<br />
<br />
Haque, Bushra<br />
<br />
Mustatea, Cristian<br />
<br />
'''Title:''' Combine Convolution with Recurrent Networks for Text Classification<br />
<br />
'''Description:''' <br />
<br />
Our team chose to reproduce the paper [https://arxiv.org/pdf/2006.15795.pdf Combine Convolution with Recurrent Networks for Text Classification] on Arxiv. The goal of this paper is to combine CNN and RNN architectures in a way that more flexibly combines the output of both architectures other than simple concatenation through the use of a “neural tensor layer” for the purpose of improving at the task of text classification. In particular, the paper claims that their novel architecture excels at the following types of text classification: sentiment analysis, news categorization, and topical classification. Our team plans to recreate this paper by working in pairs of 2, one pair to implement the CNN pipeline and the other pair to implement the RNN pipeline. We will be working with Tensorflow 2, Google Collab, and reproducing the paper’s experimental results with training on the same 6 publicly available datasets found in the paper.<br />
<br />
----<br />
<br />
'''Project # 6 Group members:'''<br />
<br />
Chin, Ruixian<br />
<br />
Ong, Jason<br />
<br />
Chiew, Wen Cheen<br />
<br />
Tan, Yan Kai<br />
<br />
'''Title:''' Mechanisms of Action (MoA) Prediction<br />
<br />
'''Description:''' <br />
<br />
Our team chose to participate in a Kaggle research challenge "Mechanisms of Action (MoA) Prediction". This competition is a project within the Broad Institute of MIT and Harvard, the Laboratory for Innovation Science at Harvard (LISH), and the NIH Common Funds Library of Integrated Network-Based Cellular Signatures (LINCS), present this challenge with the goal of advancing drug development through improvements to MoA prediction algorithms.<br />
----<br />
<br />
'''Project # 7 Group members:'''<br />
<br />
Ren, Haotian <br />
<br />
Cheung, Ian Long Yat<br />
<br />
Hussain, Swaleh <br />
<br />
Zahid, Bin, Haris <br />
<br />
'''Title:''' Transaction Fraud Detection <br />
<br />
'''Description:''' <br />
<br />
Protecting people from fraudulent transactions is an important topic for all banks and internet security companies. This Kaggle project is based on the dataset from IEEE Computational Intelligence Society (IEEE-CIS). Our objective is to build a more efficient model in order to recognize each fraud transaction with a higher accuracy and higher speed.<br />
----<br />
<br />
'''Project # 8 Group members:'''<br />
<br />
ZiJie, Jiang<br />
<br />
Yawen, Wang<br />
<br />
DanMeng, Cui<br />
<br />
MingKang, Jiang<br />
<br />
'''Title:''' Lyft Motion Prediction for Autonomous Vehicles <br />
<br />
'''Description:'''<br />
<br />
Our team chose to participate in the Kaggle Challenge "Lyft Motion Prediction for Autonomous Vehicles". We will apply our science skills to build motion prediction models for self-driving vehicles. The model will be able to predict the movement of traffic agents around the AV, such as cars, cyclists, and pedestrians. The goal of this competition is to predict the trajectories of other traffic participants.<br />
<br />
----------------------------------------------------------------------<br />
<br />
<br />
'''Project # 9 Group members:'''<br />
<br />
Banno, Dion <br />
<br />
Battista, Joseph<br />
<br />
Kahn, Solomon <br />
<br />
'''Title:''' Increasing Spotify user engagement through predictive personalization<br />
<br />
'''Description:''' <br />
<br />
Our project is an application of classification to the domain of predictive personalization. The goal of the project is to increase Spotify user engagement through data-driven methods. Given a set of users’ demographic data, listening preferences and behaviour, our goal is to build a recommendation system that suggests new songs to users. From a potential pool of songs to suggest, the final song recommendations will be driven by a classification algorithm that measures a given user’s propensity to like a song. We plan on leveraging the Spotify Web API to gather data about songs and collecting user data from consenting peers.<br />
<br />
<br />
-----------------------------------------------------------------------<br />
<br />
'''Project # 10 Group members:'''<br />
<br />
Qing, Guo <br />
<br />
Wang, Yuanxin<br />
<br />
James, Ni<br />
<br />
Xueguang, Ma<br />
<br />
'''Title:''' Mechanisms of Action (MoA) Prediction<br />
<br />
'''Description:''' <br />
<br />
Our team has decided to participate in the Mechanisms of Action (MoA) Prediction Kaggle competition. This is a challenge with the goal of advancing drug development through improvements to MoA prediction algorithms.<br />
Our team plan to develop an algorithm to predict a compound’s MoA given its cellular signature and our goal is to learn various algorithms taught in this course.<br />
<br />
<br />
-----------------------------------------------------------------------<br />
<br />
'''Project # 11 Group members:'''<br />
<br />
Yang, Jiwon <br />
<br />
Mahdi, Anas<br />
<br />
Thibault, Will<br />
<br />
Lau, Jan<br />
<br />
'''Title:''' Application of classification in human fatigue analysis<br />
<br />
'''Description:''' <br />
<br />
The goal of this project is to classify different levels of fatigue based on motion capture (Vicon) and force plates data. First, we plan to obtain data from 4 to 6 participants performing squats or squats with weights and rate them on a fatigue scale, with each participant doing at least 50 to 100 reps. We will collect data with EMG, IMU, force plates, and Vicon. When the participants are squatting, we will ask them about their fatigue level, and compare their feedback against the fatigue level recorded on EMG. The fatigue level will be on a scale of 1 to 10 (1 being not fatigued at all and 10 being cannot continue anymore). Once data is collected, we will classify the motion capture and force plates data into the different levels of fatigue.</div>J244yang