发表机构
School of Computer Science and Engineering, Sun Yat-Sen University; School of Software Engineering, Sun Yat-sen University; Institute of Artificial Intelligence, Xiamen University（中山大学计算机科学与工程学院; 中山大学软件工程学院; 厦门大学人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究无人口统计信息的图公平性问题，提出基于梯度分布的GradDist度量偏差，进而提出梯度引导的Grad2Fair方法，直接利用梯度去偏并消除人口统计预测，实验验证该方法在多数情况下性能优于基线。
AI 中文摘要
图神经网络（GNNs）常面临群体公平性问题，对特定人口统计群体预测有偏差。多数现有解决方案依赖人口统计信息完全可用这一强假设。近期一些研究尝试用预测人口统计信息作为代理来实施公平性约束，但预测的人口统计信息可能不准确。本文研究无人口统计信息的图公平性问题，避免使用预测人口统计信息。基于误分类节点的梯度分布隐含编码人口统计信息这一观察，首先提出GradDist，一种基于梯度的量化偏差的度量。然后提出Gradient-to-Fairness（Grad2Fair），一种无人口统计信息的群体公平性梯度引导方法。Grad2Fair直接利用梯度去偏并消除人口统计预测，实验表明其在多数情况下性能优于基线，证明了其有效性。
英文摘要
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.
CommentsUnder Review
