Search papers, labs, and topics across Lattice.
This paper introduces Grad2Fair, a novel approach that addresses group fairness in graph neural networks (GNNs) without relying on demographic information. By leveraging the gradient distributions of misclassified nodes, the authors develop GradDist, a metric that quantifies bias and informs the Grad2Fair method to achieve debiasing directly through gradients. Experimental results on various real-world datasets show that Grad2Fair outperforms existing fairness methods, demonstrating its effectiveness in promoting fairness without demographic assumptions.
Bypassing demographic assumptions, Grad2Fair achieves superior fairness in GNNs by directly utilizing gradient distributions from misclassified nodes.
Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race. While this challenge has motivated extensive research, most existing solutions rely on the strong assumption that demographics are fully available. To bypass this strict requirement, a few recent studies have attempted to use predicted demographics as proxies to enforce fairness constraints. However, predicted demographics may be inaccurate, resulting in the failure to improve fairness. In this work, we investigate the problem of graph fairness without demographic information and avoid the utilization of predicted demographics. Motivated by our observation that the gradient distributions of misclassified nodes implicitly encode demographic information, we first propose GradDist, a gradient-based metric that quantifies bias by measuring the distance between local modes within these distributions. To mitigate this bias, we propose Gradient-to-Fairness (Grad2Fair), a gradient-guided approach for group fairness without demographics. Due to the potential demographics in gradients, Grad2Fair directly leverages gradients to debias and eliminates demographic prediction, thereby enabling stable fairness performance. Experiments on several real-world datasets demonstrate the effectiveness of Grad2Fair, as evidenced by superior performance over baselines in most cases. Our code is available at https://github.com/ZzoomD/Grad2Fair.
