Timezone: »

 
Poster
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
Derek Lim · Felix Hohne · Xiuyu Li · Sijia Linda Huang · Vaishnavi Gupta · Omkar Bhalerao · Ser Nam Lim

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @
in Poster Session 7 »

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.

Keywords: Deep Learning · Machine Learning · Graph Learning

Author Information

Derek Lim (Massachusetts Institute of Technology)
Felix Hohne (Cornell University)
Xiuyu Li (Cornell University)
Sijia Linda Huang (Cornell University)
Vaishnavi Gupta (Cornell University)
Omkar Bhalerao
Ser Nam Lim (Facebook AI)

More from the Same Authors