Graph Structure of Neural Networks

From statwiki
Revision as of 15:55, 10 November 2020 by Y27weng (talk | contribs)
Jump to navigation Jump to search
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

Presented By

Xiaolan Xu, Robin Wen, Yue Weng, Beizhen Chang

Introduction

Relational Graph

Parameter Definition

(1) Clustering Coefficient

(2) Average Path Length

Experimental Setup (Section 4 in the paper)

Major Conclusions (Section 5 in the paper)

(1) graph structure of neural networks matters;

(2) a “sweet spot” of relational graphs lead to neural networks with significantly improved predictive performance;

(3) neural network’s performance is approximately a smooth function of the clustering coefficient and average path length of its relational graph;

(4) our findings are consistent across many different tasks and datasets;

(5) top architectures can be identified efficiently;

(6) well-performing neural networks have graph structure surprisingly similar to those of real biological neural networks.

Critique