GraphGini: Fostering Individual and Group Fairness in Graph Neural Networks

TMLR Paper5342 Authors

Abstract: Graph Neural Networks (GNNs) have demonstrated impressive performance across various tasks, leading to their increased adoption in high-stakes decision-making systems. However, concerns have arisen about GNNs potentially generating unfair decisions for underprivileged groups or individuals when lacking fairness constraints. This work addresses this issue by introducing GraphGini, a novel approach that incorporates the Gini coefficient to enhance both individual and group fairness within the GNN framework. We rigorously establish that the Gini coefficient offers greater robustness and promotes equal opportunity among GNN outcomes, advantages not afforded by the prevailing Lipschitz constant methodology. Additionally, we employ the Nash social welfare program to ensure our solution yields a Pareto optimal distribution of group fairness. GraphGini automatically balances the three optimization objectives of utility, individual fairness, and group fairness without requiring manual tuning of weight parameters. Extensive experimentation on real-world datasets demonstrates GraphGini's efficacy in significantly improving individual fairness compared to state-of-the-art methods while maintaining utility and group fairness.

Submission Length: Long submission (more than 12 pages of main content)

Assigned Action Editor: ~Ian_A._Kash1

Submission Number: 5342