Injecting hand-designed structural rules (low-neighbor-degree and local-global similarity) via representation alignment improves graph contrastive learning accuracy on six homophilic benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Str-GCL: Structural Commonsense Driven Graph Contrastive Learning
Injecting hand-designed structural rules (low-neighbor-degree and local-global similarity) via representation alignment improves graph contrastive learning accuracy on six homophilic benchmarks.