GLINKX: A Scalable Unified Framework For Homophilous and Heterophilous Graphs
This addresses the challenge of scalable graph learning for both homophilous and heterophilous graphs, which is incremental as it combines existing ideas into a unified framework.
The authors tackled the problem of graph learning by proposing GLINKX, a scalable shallow method that works on both homophilous and heterophilous graphs, achieving effectiveness across several datasets.
In graph learning, there have been two predominant inductive biases regarding graph-inspired architectures: On the one hand, higher-order interactions and message passing work well on homophilous graphs and are leveraged by GCNs and GATs. Such architectures, however, cannot easily scale to large real-world graphs. On the other hand, shallow (or node-level) models using ego features and adjacency embeddings work well in heterophilous graphs. In this work, we propose a novel scalable shallow method -- GLINKX -- that can work both on homophilous and heterophilous graphs. GLINKX leverages (i) novel monophilous label propagations, (ii) ego/node features, (iii) knowledge graph embeddings as positional embeddings, (iv) node-level training, and (v) low-dimensional message passing. Formally, we prove novel error bounds and justify the components of GLINKX. Experimentally, we show its effectiveness on several homophilous and heterophilous datasets.