Timezone: »

 
GLINKX: A Unified Framework for Large-scale Homophilous and Heterophilous Graphs
Marios Papachristou · Rishab Goel · Frank Portman · Matthew Miller · Rong Jin

@
in New Frontiers in Graph Learning »
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.

Keywords: Graph learning · heterophily · homophily · Node Classification · knowledge graph embeddings · positional embeddings · label propagation · monophily

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