Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?

Abstract

Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using the graph structures based on the relational inductive bias (homophily assumption). Though GNNs are believed to outperform NNs in real-world tasks, performance advantages of GNNs over graph-agnostic NNs seem not generally satisfactory. Heterophily has been considered as a main cause and numerous works have been put forward to address it. In this paper, we first show that not all cases of heterophily are harmful for GNNs with aggregation operation. Then, we propose new metrics based on a similarity matrix which considers the influence of both graph structure and input features on GNNs. The metrics demonstrate advantages over the commonly used homophily metrics by tests on synthetic graphs. From the metrics and the observations, we find some cases of harmful heterophily can be addressed by diversification operation. With this fact and knowledge of filterbanks, we propose the Adaptive Channel Mixing (ACM) framework to adaptively exploit aggregation, diversification and identity channels in each GNN layer to address harmful heterophily. We validate the ACM-augmented baselines with 10 real-world node classification tasks. They consistently achieve significant performance gain and exceed the state-of-the-art GNNs on most of the tasks without incurring significant computational burden.

References in corpus (16)

• Decoupled Weight Decay Regularization
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Geometric deep learning: going beyond Euclidean data
• Fast Graph Representation Learning with PyTorch Geometric
• Simplifying Graph Convolutional Networks
• Simple and Deep Graph Convolutional Networks
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Measuring and Improving the Use of Graph Information in Graph Neural Networks
• Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
• Non-Local Graph Neural Networks
• New Benchmarks for Learning on Non-Homophilous Graphs
• Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
• Beyond Low-frequency Information in Graph Convolutional Networks
• Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
• Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs

Cited by in corpus (5)

• Is Homophily a Necessity for Graph Neural Networks?
• Spatial Heterophily Aware Graph Neural Networks
• A Hybrid Similarity-Aware Graph Neural Network with Transformer for Node Classification
• Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification
• Classification of vertices on social networks by multiple approaches