公平性的分布稳定性综合视角
A Comprehensive View of Fairness through Distributional Stability
浏览论文内容
中文总结 AI 辅助
本文提出将公平性视为分布稳定性，通过预测器对受保护群体构成扰动的稳定性定义公平，并以Lipschitz常数量化不公平差距，提出基于凸组合的二阶锥规划学习方法，实验验证了其有效性。
中文摘要 AI 辅助
我们将公平性视为分布稳定性的一种属性。我们不是在固定数据分布下评估预测器，而是研究当扰动改变受保护群体的构成时，其预测如何变化。如果预测器在这种变化下保持稳定，则它是公平的。在此视角下，几种经典的公平性概念表现为对特定扰动的稳定性，相应的不公平差距由预测率泛函的Lipschitz常数给出。这一表述还提供了在测试时对一系列人口构成均匀成立的保证，无需了解部署分布。它导致了一种基于重新加权预测器凸组合的学习过程，表述为二阶锥规划，我们为其建立了泛化界。在标准基准上的实验说明了该方法。
英文摘要
We view fairness as a property of distributional stability. Rather than assessing a predictor under a fixed data distribution, we study how its predictions change under perturbations that modify the composition of protected groups. A predictor is fair if it remains stable under such shifts. Under this perspective, several classical notions of fairness arise as stability with respect to specific perturbations, with the associated unfairness gap given by a Lipschitz constant of a prediction-rate functional. This formulation also yields guarantees that hold uniformly over a range of demographic compositions at test time, without requiring knowledge of the deployment distribution. It leads to a learning procedure based on convex combinations of reweighted predictors, formulated as a second-order cone program, for which we establish generalization bounds. Experiments on standard benchmarks illustrate the approach.
发表机构
- Télécom Paris, Institut Polytechnique de Paris（巴黎综合理工学院电信学院）
机构由 AI 辅助整理，请以论文原文为准。
