New Benchmarks for Learning on Non-Homophilous Graphs

Understand

Much data with graph structures satisfy the principle of homophily, meaning that connected nodes tend to be similar with respect to a specific attribute.

• As such, ubiquitous datasets for graph machine learning tasks have generally been highly homophilous, rewarding methods that leverage homophily as an inductive bias.
• Recent work has pointed out this particular focus, as new non-homophilous datasets have been introduced and graph representation learning models better suited for low-homophily settings have been developed.
• However, these datasets are small and poorly suited to truly testing the effectiveness of new methods in non-homophilous settings.