Simplifying Graph Convolutional Networks

By Felix Wu, Tianyi Zhang, Amauri H. Souza Jr., Christopher Fifty, Kilian Q. Weinberger. 2019

3,924 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Model Architectures, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yoshua Bengio
  2. Percy Liang
  3. Mohit Bansal
  4. Jianfeng Gao
  5. Philip S. Yu
  6. Jure Leskovec
  7. Quoc V. Le
  8. Luke S. Zettlemoyer

In Statistical and Nonlinear Physics

  1. William L. Hamilton
  2. Stephan Günnemann
  3. Jure Leskovec
  4. Bryan Perozzi
  5. Michael M. Bronstein
  6. Matthias Fey
  7. Xiao Wang
  8. Aleksandar Bojchevski

In Model Architectures

  1. Matthias Fey
  2. Jure Leskovec
  3. Stephan Günnemann
  4. Shuiwang Ji
  5. William L. Hamilton
  6. Michael M. Bronstein
  7. Jianfeng Gao
  8. Aleksandar Bojchevski

In Graph Learning

  1. William L. Hamilton
  2. Jure Leskovec
  3. Stephan Günnemann
  4. Matthias Fey
  5. Aleksandar Bojchevski
  6. Marinka Zitnik
  7. Michael M. Bronstein
  8. Jian Tang

Citations in the corpus