Incorporating Heterophily into Graph Neural Networks for Graph Classification

TL;DR

This paper introduces IHGNN, a novel graph neural network architecture that effectively incorporates heterophily, enabling better graph classification performance on real-world graphs exhibiting both homophily and heterophily.

Contribution

The paper proposes three design strategies and develops IHGNN, a GNN model that better handles heterophily, improving classification accuracy over existing methods.

Findings

IHGNN outperforms state-of-the-art GNNs on various datasets.

Incorporating heterophily improves graph classification accuracy.

Adaptive aggregation enhances model flexibility.

Abstract

Graph Neural Networks (GNNs) often assume strong homophily for graph classification, seldom considering heterophily, which means connected nodes tend to have different class labels and dissimilar features. In real-world scenarios, graphs may have nodes that exhibit both homophily and heterophily. Failing to generalize to this setting makes many GNNs underperform in graph classification. In this paper, we address this limitation by identifying three effective designs and develop a novel GNN architecture called IHGNN (short for Incorporating Heterophily into Graph Neural Networks). These designs include the combination of integration and separation of the ego- and neighbor-embeddings of nodes, adaptive aggregation of node embeddings from different layers, and differentiation between different node embeddings for constructing the graph-level readout function. We empirically validate IHGNN on various graph datasets and demonstrate that it outperforms the state-of-the-art GNNs for graph classification.