C3GNN improves class-imbalanced graph classification by clustering majority classes into balanced subclasses, applying Mixup inside each subclass, and learning with hierarchical supervised contrastive losses.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cluster-guided Contrastive Class-imbalanced Graph Classification
C3GNN improves class-imbalanced graph classification by clustering majority classes into balanced subclasses, applying Mixup inside each subclass, and learning with hierarchical supervised contrastive losses.