REFine rewires a graph toward a label-driven reference graph to increase edge homophily, and standard GNNs trained on the rewired graph match or beat specialized heterophilic GNNs on several benchmarks.
Be- yond homophily in graph neural networks: Current limitations and effective designs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
It Takes a Graph to Know a Graph: Rewiring for Homophily with a Reference Graph
REFine rewires a graph toward a label-driven reference graph to increase edge homophily, and standard GNNs trained on the rewired graph match or beat specialized heterophilic GNNs on several benchmarks.