Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond

arXiv:2209.06177v4 Announce Type: replace-cross
Abstract: Homophily is a graph property describing the tendency of edges to connect similar nodes; the opposite is called heterophily. It is often believed that heterophilous graphs are challenging for standard message-passing graph neural networks (GNNs), and much effort has been put into developing efficient methods for this setting. However, there is no universally agreed-upon measure of homophily in the literature. In this work, we show that commonly used homophily measures have critical drawbacks preventing the …

abstract arxiv beyond classification cs.dm cs.lg cs.si datasets gnns graph graph neural networks graphs math.pr networks neural networks node nodes property standard type