arXiv cs.AI· Gayane Taturyan, Charlotte Laclau, Stephan Cl\'emencon·· 11 小时前AI 评分24
把公平性视为分布稳定性：一种统一的公平性视角
A Comprehensive View of Fairness through Distributional Stability
AI 导读
研究将公平性定义为预测器在受保护群体构成变化扰动下的分布稳定性，经典公平性概念可视为对特定扰动的稳定性，对应不公平差距由预测率泛函的 Lipschitz 常数给出。该框架无需知道部署分布即可在测试时对多种人口构成提供一致保证，并导出基于重加权预测器凸组合、以二阶锥规划形式求解的学习方法，附有泛化界，在标准基准上进行了实验验证。
正文 · 原文
Abstract: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.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.37061 [cs.LG] |
| (or arXiv:2609.37061v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.37061 arXiv-issued DOI via DataCite |
Submission history
From: Charlotte Laclau [view email]
[v1]
Tue, 29 Sep 2026 09:00:49 UTC (361 KB)
[v2]
Fri, 30 Oct 2026 10:42:03 UTC (545 KB)
来源：arXiv cs.AI · arxiv.org