Simplifying Graph Convolutional Networks

Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, Kilian Weinberger
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:6861-6871, 2019.

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v97-wu19e, title = {Simplifying Graph Convolutional Networks}, author = {Wu, Felix and Souza, Amauri and Zhang, Tianyi and Fifty, Christopher and Yu, Tao and Weinberger, Kilian}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {6861--6871}, year = {2019}, editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/wu19e/wu19e.pdf}, url = { http://proceedings.mlr.press/v97/wu19e.html }, 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.} }
Endnote
%0 Conference Paper %T Simplifying Graph Convolutional Networks %A Felix Wu %A Amauri Souza %A Tianyi Zhang %A Christopher Fifty %A Tao Yu %A Kilian Weinberger %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-wu19e %I PMLR %P 6861--6871 %U http://proceedings.mlr.press/v97/wu19e.html %V 97 %X 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.
APA
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T. & Weinberger, K.. (2019). Simplifying Graph Convolutional Networks. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:6861-6871 Available from http://proceedings.mlr.press/v97/wu19e.html .

Related Material