Timezone: »

GLINKX: A Unified Framework for Large-scale Homophilous and Heterophilous Graphs
Marios Papachristou · Rishab Goel · Frank Portman · Matthew Miller · Rong Jin
Event URL: https://openreview.net/forum?id=GlViaJSwnlK »

In graph learning, there have been two main 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, to achieve scaling in large graphs. We show the effectiveness of GLINKX on several homophilous and heterophilous datasets.

Author Information

Marios Papachristou (Cornell)
Rishab Goel (Borealis AI)
Frank Portman (Twitter)
Matthew Miller (Massachusetts Institute of Technology)
Rong Jin

More from the Same Authors