Simplifying Graph Convolutional Networks

TL;DR

This paper simplifies Graph Convolutional Networks by removing nonlinearities and collapsing weight matrices, resulting in a faster, more interpretable model that maintains accuracy across various applications.

Contribution

It introduces a simplified linear GCN model that reduces complexity and computational cost without sacrificing performance.

Findings

Simplified GCNs maintain accuracy in many tasks.

Model achieves up to 100x speedup over FastGCN.

Simplifications lead to more interpretable models.

Abstract

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches, and as a result, may inherit unnecessary complexity and redundant computation. In this paper, we reduce this excess complexity through successively removing nonlinearities and collapsing weight matrices between consecutive layers. We theoretically analyze the resulting linear model and show that it corresponds to a fixed low-pass filter followed by a linear classifier. Notably, our experimental evaluation demonstrates that these simplifications do not negatively impact accuracy in many downstream applications. Moreover, the resulting model scales to larger datasets, is naturally interpretable, and yields up to two orders of magnitude speedup over FastGCN.