uncovering Shared Structures in Multiclass Classification

Introduction

In their paper Uncovering Shared Structures in Multiclass Classification, the authors Amit et al. wrote about how hidden structure can be utilized to improve the accuracy in multiclass classification. This notion is often called learning-to-learn or interclass transfer (Thrun, 1996).

The uncovering of such hidden structure was accomplished by a mechanism that learns the underlying characteristics that are shared between the target classes. The benefits of finding such common characteristics was demonstrated in the context of large margin multiclass linear classifiers.

Accurate classification of an instance when there is a large number of target classes is a major challenge in many areas such as object recognition, face identification, textual topic classification, and phoneme recognition.

Usually, when there is a large number of classes, the classes are strongly related to each other and have some underlying common characteristics. As a simple example, even though there are many different kinds of mammals, many of them share common characteristics such as having a striped texture. If such true underlying characteristics that are common to the many different classes can be found, then the effective complexity of the multiclass problem can be significantly reduced.

Simultaneously learning the underlying structure between many classes is a challenging optimization task. The usual goal of past was to extract powerful non-linear hidden characteristics. However, this goal was usually not convex, and often resulted in local minima. In this paper, the authors instead modeled the shared characteristics between many classes as linear transformations of the input space.