arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.02817stat.MLcs.CYcs.LG
收藏

通过预处理、处理中与后处理实现带线性差异约束的贝叶斯最优公平分类

Bayes-Optimal Fair Classification with Linear Disparity Constraints via Pre-, In-, and Post-processing

Department of Statistics and Data Science, Xiamen University(厦门大学统计与数据科学系);Department of Statistics and Data Science, University of Pennsylvania(宾夕法尼亚大学统计与数据科学系);Dept of Statistics and Data Science, University of California, Los Angeles(加州大学洛杉矶分校统计与数据科学系)

Xianli Zeng, Kevin Jiang, Guang Cheng, Edgar Dobriban

AI总结:

本文提出基于线性与双线性差异度量的贝叶斯最优公平分类理论,并据此设计预处理、处理中和后处理三类方法,在直接控制群体差异的同时实现接近最优的公平性-准确性权衡。

摘要:

机器学习算法可能对受保护群体产生不同的影响。为解决这一问题,我们开发了贝叶斯最优公平分类方法,旨在给定群体公平约束下最小化分类误差。我们引入线性差异度量的概念,即概率分类器的线性函数;以及双线性差异度量,它同时对群体回归函数呈线性。我们证明了几种常见的差异度量——人口统计均等偏差、机会均等偏差和预测均等偏差——都是双线性的。通过揭示与Neyman-Pearson引理的联系,我们找到了在单一线性差异度量下贝叶斯最优公平分类器的形式。对于双线性差异度量,我们能够给出贝叶斯最优公平分类器的显式形式,即具有明确刻画阈值的群体阈值规则。我们还为预测阶段无法使用受保护属性的情形开发了类似的算法。此外,我们针对多类别受保护属性和均衡几率(equalized odds)获得了最优分类器的类似理论刻画。利用这些理论结果,我们设计了在双线性差异约束下学习公平贝叶斯最优分类器的方法。我们的方法涵盖了三种主流的公平感知分类途径:预处理(公平上采样与下采样)、处理中(公平成本敏感分类)和后处理(公平插件规则)。我们的方法直接控制差异,同时实现接近最优的公平性-准确性权衡。我们通过实验表明,与现有算法相比,我们的方法具有最先进的性能。特别是,我们的预处理方法在低差异水平下能够达到比先前预处理方法更高的准确率。

英文摘要:

Machine learning algorithms may have disparate impacts on protected groups. To address this, we develop methods for Bayes-optimal fair classification, aiming to minimize classification error subject to given group fairness constraints. We introduce the notion of \emph{linear disparity measures}, which are linear functions of a probabilistic classifier; and \emph{bilinear disparity measures}, which are also linear in the group-wise regression functions. We show that several popular disparity measures -- the deviations from demographic parity, equality of opportunity, and predictive equality -- are bilinear. We find the form of Bayes-optimal fair classifiers under a single linear disparity measure, by uncovering a connection with the Neyman-Pearson lemma. For bilinear disparity measures, we are able to find the explicit form of Bayes-optimal fair classifiers as group-wise thresholding rules with explicitly characterized thresholds. We develop similar algorithms for when protected attribute cannot be used at the prediction phase. Moreover, we obtain analogous theoretical characterizations of optimal classifiers for a multi-class protected attribute and for equalized odds. Leveraging our theoretical results, we design methods that learn fair Bayes-optimal classifiers under bilinear disparity constraints. Our methods cover three popular approaches to fairness-aware classification, via pre-processing (Fair Up- and Down-Sampling), in-processing (Fair cost-sensitive Classification) and post-processing (a Fair Plug-In Rule). Our methods control disparity directly while achieving near-optimal fairness-accuracy tradeoffs. We show empirically that our methods have state-of-the-art performance compared to existing algorithms. In particular, our pre-processing method can a reach higher accuracy than prior pre-processing methods at low disparity levels.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑