Revisiting Heterophily For Graph Neural Networks

TL;DR

This paper introduces new heterophily metrics and an adaptive framework called ACM that significantly improves GNN performance on heterophilic graphs by effectively combining aggregation and diversification strategies.

Contribution

It proposes novel heterophily metrics based on post-aggregation node similarity and introduces ACM, a flexible framework that enhances GNNs by adaptively mixing channels for better node classification.

Findings

ACM outperforms traditional GNNs on heterophilic graphs.

New heterophily metrics better capture node similarity post-aggregation.

ACM achieves significant performance gains on benchmark datasets.

Abstract

Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using graph structures based on the relational inductive bias (homophily assumption). While GNNs have been commonly believed to outperform NNs in real-world tasks, recent work has identified a non-trivial set of datasets where their performance compared to NNs is not satisfactory. Heterophily has been considered the main cause of this empirical observation and numerous works have been put forward to address it. In this paper, we first revisit the widely used homophily metrics and point out that their consideration of only graph-label consistency is a shortcoming. Then, we study heterophily from the perspective of post-aggregation node similarity and define new homophily metrics, which are potentially advantageous compared to existing ones. Based on this investigation, we prove that some harmful cases of heterophily can be effectively addressed by local diversification operation. Then, we propose the Adaptive Channel Mixing (ACM), a framework to adaptively exploit aggregation, diversification and identity channels node-wisely to extract richer localized information for diverse node heterophily situations. ACM is more powerful than the commonly used uni-channel framework for node classification tasks on heterophilic graphs and is easy to be implemented in baseline GNN layers. When evaluated on 10 benchmark node classification tasks, ACM-augmented baselines consistently achieve significant performance gain, exceeding state-of-the-art GNNs on most tasks without incurring significant computational burden.