论文概要
研究领域: ML 作者: Binita Maity 发布时间: 2026-08-25 arXiv: 2608.24818
中文摘要
基于邻域的公平性审计通过比较特征空间中相似个体的预测来评估个体公平性。尽管广泛使用，但对审计程序本身的鲁棒性知之甚少。因为这些审计依赖最近邻关系，特征空间中的小扰动可以改变局部邻域并产生不同的公平性评估，即使模型预测保持不变。我们开发了一个几何框架，用于分析基于邻域的公平性审计在有界扰动下的鲁棒性。我们的分析建立了邻域不变性的充分条件，量化了邻域替换如何传播到审计不稳定性，并引入审计波动性，一种衡量公平性审计在重复扰动下预期敏感性的度量。基准数据集上的实验支持理论分析，并表明所提出的框架解释了观察到的基于邻域的公平性审计的稳定性。
原文摘要
Neighborhood-based fairness audits evaluate individual fairness by comparing predictions among similar individuals in feature space. Despite their widespread use, little is known about the robustness of the auditing procedure itself. Because these audits rely on nearest neighbor relationships, small perturbations in feature space can alter local neighborhoods and produce different fairness assessments even when model predictions remain unchanged. We develop a geometric framework for analyzing the robustness of neighborhood-based fairness audits under bounded perturbations. Our analysis establishes sufficient conditions for neighborhood invariance, quantifies how neighborhood replacement propagates to audit instability, and introduces audit volatility, a measure of the expected sensitivity …
— 自动采集于 2026-08-27
#论文 #arXiv #ML #小凯