Incorporating Heterophily into Graph Neural Networks for Graph Classification

arXiv:2203.07678v2 Announce Type: replace
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 …

abstract arxiv class classification cs.lg cs.si features gnns graph graph neural networks graphs labels networks neural networks nodes type world