GLINKX: A Scalable Unified Framework For Homophilous and Heterophilous Graphs

TL;DR

GLINKX is a scalable, unified graph learning framework that effectively handles both homophilous and heterophilous graphs by combining label propagation, node features, and knowledge graph embeddings.

Contribution

It introduces a novel shallow method, GLINKX, that unifies approaches for different graph types and provides theoretical error bounds.

Findings

Effective on multiple datasets with different graph types

Outperforms existing methods in scalability and accuracy

Theoretically justified components and error bounds

Abstract

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.