Pushing the limits of fairness impossibility: Who's the fairest of them all?
Pushing the limits of fairness impossibility: Who's the fairest of them all?
复制标题
DOI：
10.48550/arxiv.2208.12606
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Brian Hsu;R. Mazumder;Preetam Nandy;Kinjal Basu
中科院分区：
文献类型：
--
作者：
Brian Hsu;R. Mazumder;Preetam Nandy;Kinjal Basu
不可能公平性定理是算法公平性文献中的一个基本结果。它指出，除了特殊情况外，一个人不可能准确且同时满足公平的所有三个常见和直观的定义--人口均等、均衡赔率和预测性比率均等。这一结果促使大多数工作将重点放在一个或两个指标的解决方案上。在本文中，我们没有效仿，而是提出了一个框架，它推动了不可能性定理的极限，以便最大限度地满足所有这三个度量标准。我们开发了一种基于整数规划的方法，该方法可以在较小的违规情况下产生同时满足多个公平准则的可证明最优的后处理方法。我们的实验表明，我们的后处理器可以在最小的模型性能损失的情况下，同时提高不同定义的公平性。我们还讨论了我们的模型选择和公平可解释性框架的应用，从而试图回答这样一个问题：谁是所有这些模型中最公平的？
The impossibility theorem of fairness is a foundational result in the algorithmic fairness literature. It states that outside of special cases, one cannot exactly and simultaneously satisfy all three common and intuitive definitions of fairness - demographic parity, equalized odds, and predictive rate parity. This result has driven most works to focus on solutions for one or two of the metrics. Rather than follow suit, in this paper we present a framework that pushes the limits of the impossibility theorem in order to satisfy all three metrics to the best extent possible. We develop an integer-programming based approach that can yield a certifiably optimal post-processing method for simultaneously satisfying multiple fairness criteria under small violations. We show experiments demonstrating that our post-processor can improve fairness across the different definitions simultaneously with minimal model performance reduction. We also discuss applications of our framework for model selection and fairness explainability, thereby attempting to answer the question: who's the fairest of them all?