A GNN fairness model edits graphs for higher class homophily and lower sensitive-attribute homophily, then trains with supervised contrastive and environmental losses to improve both accuracy and fairness metrics over prior CAF baselines.
Exploiting mmd and sinkhorn divergences for fair and transferable represen- tation learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network
A GNN fairness model edits graphs for higher class homophily and lower sensitive-attribute homophily, then trains with supervised contrastive and environmental losses to improve both accuracy and fairness metrics over prior CAF baselines.