Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces

Abstract

Graph convolution networks (GCNs) have been enormously successful in learning representations for numerous graph-based machine learning tasks. Specific to learning rich node representations, most of the methods have solely relied on the homophily assumption and have shown limited performance on the heterophilous graphs. While several methods have been developed with new architectures to address heterophily, we argue that by learning graph representations across two spaces i.e., topology and feature space GCNs can address heterophily. In this work, we experimentally demonstrate the performance of the proposed GCN framework over semi-supervised node classification task on both homophilous and heterophilous graph benchmarks by learning and combining representations across the topological and the feature spaces.

More details to appear soon!!

Acknowledgements

We are grateful to Science and Engineering Research Board (SERB), Department of Science and Technology, Govt. of India for providing support through the IMPRINT 2 grant.

Ashish Tiwari is a PhD student at IIT Gandhinagar and a recipient of the Prime Minister Research Fellowship (PMRF) from MHRD, Govt. of India.

Sresth Tosniwal is a B.Tech student in the discipline of Mechanical Engineering with minors in Computer Science & Engineering at IIT Gandhinagar, Gujarat, India.

Shanmuganathan Raman is the Jibaben Patel Chair on Artificial Intelligence, Associate Professor, IIT Gandhinagar, Gujarat, India.