Graph Neural Networks with Heterophily

Abstract

Graph Neural Networks (GNNs) have proven to be useful for many different practical applications. However, many existing GNN models have implicitly assumed homophily among the nodes connected in the graph, and therefore have largely overlooked the important setting of heterophily, where most connected nodes are from different classes. In this work, we propose a novel framework called CPGNN that generalizes GNNs for graphs with either homophily or heterophily. The proposed framework incorporates an interpretable compatibility matrix for modeling the heterophily or homophily level in the graph, which can be learned in an end-to-end fashion, enabling it to go beyond the assumption of strong homophily. Theoretically, we show that replacing the compatibility matrix in our framework with the identity (which represents pure homophily) reduces to GCN. Our extensive experiments demonstrate the effectiveness of our approach in more realistic and challenging experimental settings with significantly less training data compared to previous works: CPGNN variants achieve state-of-the-art results in heterophily settings with or without contextual node features, while maintaining comparable performance in homophily settings.

Proceedings version of AAAI 2021 with appendix and additional typo fixes; 12 pages, 4 figures

Cited by in corpus (5)

• Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
• CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph
• Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs
• $p$-Laplacian Based Graph Neural Networks
• Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks