Skip to yearly menu bar Skip to main content


Simplifying Graph Convolutional Networks

Felix Wu · Amauri Souza · Tianyi Zhang · Christopher Fifty · Tao Yu · Kilian Weinberger

Pacific Ballroom #267

Keywords: [ Semi-supervised learning ] [ Networks and Relational Learning ] [ Natural Language Processing ] [ Architectures ]


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.

Live content is unavailable. Log in and register to view live content