Bharti Beepul, Yi Paul, Sulam Jeremias
Johns Hopkins University.
University of Maryland.
Adv Neural Inf Process Syst. 2023 Dec;36:37173-37192.
As the use of machine learning models in real world high-stakes decision settings continues to grow, it is highly important that we are able to audit and control for any potential fairness violations these models may exhibit towards certain groups. To do so, one naturally requires access to sensitive attributes, such as demographics, biological sex, or other potentially sensitive features that determine group membership. Unfortunately, in many settings, this information is often unavailable. In this work we study the well (EOD) definition of fairness. In a setting without sensitive attributes, we first provide tight and computable upper bounds for the EOD violation of a predictor. These bounds precisely reflect the worst possible EOD violation. Second, we demonstrate how one can provably control the worst-case EOD by a new post-processing correction method. Our results characterize when directly controlling for EOD with respect to the predicted sensitive attributes is - and when is not - optimal when it comes to controlling worst-case EOD. Our results hold under assumptions that are milder than previous works, and we illustrate these results with experiments on synthetic and real datasets.
随着机器学习模型在现实世界高风险决策场景中的应用不断增加，我们能够对这些模型可能对某些群体表现出的任何潜在公平性违规行为进行审计和控制变得至关重要。为此，自然需要获取敏感属性，如人口统计学特征、生物性别或其他决定群体成员身份的潜在敏感特征。不幸的是，在许多情况下，这些信息往往无法获得。在这项工作中，我们研究了公平性的平等机会差异（EOD）定义。在没有敏感属性的情况下，我们首先为预测器的EOD违规提供了紧密且可计算的上限。这些界限精确反映了可能出现的最严重的EOD违规情况。其次，我们展示了如何通过一种新的后处理校正方法来可证明地控制最坏情况的EOD。我们的结果刻画了在控制最坏情况的EOD时，直接针对预测的敏感属性控制EOD何时是最优的，何时不是最优的。我们的结果在比以前的工作更温和的假设下成立，并且我们通过对合成数据集和真实数据集的实验来说明这些结果。
