用数学方法同时量化与解释不公平，揭示关键影响因素。
Shapley meets Rawls: an integrated framework for measuring and explaining unfairness
- 引入谢林值统一定义和解释不公平性
- 发现年龄、工时、婚姻状况导致性别不公平
- 计算速度比传统方法快，适合实际应用
可解释性与公平性长期以来被分开研究，近期有尝试解释不公平来源。本文表明，在标准群体公平性准则下，谢林值可用于定义和解释不公平性，从而构建一个整合框架，既能估计不公平程度，也能推断其成因。该框架可扩展至高效-对称-线性（ESL）值家族，部分成员提供更稳健的公平定义并显著缩短计算时间。在UCI机器学习库的人口收入数据集上进行验证，结果表明'年龄'、'工作时长'和'婚姻状况'是导致性别不公平的关键因素，且计算效率高于传统自助法检验。
原文摘要 · Abstract (English)
Explainability and fairness have mainly been considered separately, with recent exceptions trying the explain the sources of unfairness. This paper shows that the Shapley value can be used to both define and explain unfairness, under standard group fairness criteria. This offers an integrated framework to estimate and derive inference on unfairness as-well-as the features that contribute to it. Our framework can also be extended from Shapley values to the family of Efficient-Symmetric-Linear (ESL) values, some of which offer more robust definitions of fairness, and shorter computation times. An illustration is run on the Census Income dataset from the UCI Machine Learning Repository. Our approach shows that ``Age", ``Number of hours" and ``Marital status" generate gender unfairness, using shorter computation time than traditional Bootstrap tests.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。