提出几何框架，分析公平性审计在特征扰动下的稳定性问题。
A Geometric Theory of Robust Fairness Audits
- 基于特征空间邻域的几何分析，揭示审计鲁棒性条件。
- 定义审计波动性，量化扰动对公平性评估的影响程度。
- 适用于关注模型公平性审计可靠性的研究人员。
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结果来评估个体公平性。尽管广泛应用，但其自身鲁棒性尚不明确。由于依赖最近邻关系，特征空间中的微小扰动可能改变局部邻域，导致即使模型预测不变，公平性评估结果也不同。本文建立了一个针对有界扰动下邻域公平性审计鲁棒性的几何分析框架。理论分析给出了邻域不变性的充分条件，量化了邻域替换如何传播至审计不稳定性，并引入了审计波动性（audit volatility）作为重复扰动下公平性审计敏感性的期望度量。在基准数据集上的实验支持了理论分析，表明该框架能够解释实际观测到的邻域公平性审计稳定性。
原文摘要 · Abstract (English)
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 of fairness audits under repeated perturbations. Experiments on benchmark datasets support the theoretical analysis and show that the proposed framework explains the observed stability of neighborhood-based fairness audits.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。