Graph Neural Networks for Graphs with Heterophily: A Survey

TL;DR

This survey reviews recent advances in graph neural networks designed for heterophilic graphs, highlighting models, taxonomy, and future research directions.

Contribution

It provides a comprehensive taxonomy and analysis of GNNs tailored for heterophilic graphs, a less-studied but important graph property.

Findings

Systematic taxonomy of heterophilic GNN models

Analysis of heterophily's impact on GNN performance

Discussion of future research directions in heterophilic GNNs

Abstract

Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriad graph analytic tasks and applications. Most GNNs rely on the homophily assumption that nodes belonging to the same class are more likely to be connected. However, as a ubiquitous graph property in numerous real-world scenarios, heterophily, i.e., nodes with different labels tend to be linked, significantly limits the performance of tailor-made homophilic GNNs. Hence, GNNs for heterophilic graphs are gaining increasing research attention to enhance graph learning with heterophily. In this paper, we provide a comprehensive review of GNNs for heterophilic graphs. Specifically, we propose a systematic taxonomy that governs existing heterophilic GNN models, along with general summaries and detailed analyses. Furthermore, we discuss the relationship between heterophily and various graph research domains, aiming to facilitate the development of more effective GNNs across a spectrum of practical applications and learning tasks in the graph research community. In the end, we point out potential directions to advance and inspire future research and applications on heterophilic graph learning with GNNs.