Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
It addresses the need for scalable methods in non-homophilous graph learning, which is an incremental advance for researchers in graph machine learning.
The paper tackles the problem of graph machine learning on non-homophilous graphs by introducing large-scale datasets and showing that existing scalable methods degrade on them, and it presents LINKX, a simple method that achieves state-of-the-art performance on these datasets.
Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other. Recently, new Graph Neural Networks (GNNs) have been developed that move beyond the homophily regime; however, their evaluation has often been conducted on small graphs with limited application domains. We collect and introduce diverse non-homophilous datasets from a variety of application areas that have up to 384x more nodes and 1398x more edges than prior datasets. We further show that existing scalable graph learning and graph minibatching techniques lead to performance degradation on these non-homophilous datasets, thus highlighting the need for further work on scalable non-homophilous methods. To address these concerns, we introduce LINKX -- a strong simple method that admits straightforward minibatch training and inference. Extensive experimental results with representative simple methods and GNNs across our proposed datasets show that LINKX achieves state-of-the-art performance for learning on non-homophilous graphs. Our codes and data are available at https://github.com/CUAI/Non-Homophily-Large-Scale.