期刊
2020 IEEE 36TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2020)
卷 -, 期 -, 页码 1918-1921出版社
IEEE COMPUTER SOC
DOI: 10.1109/ICDE48307.2020.00203
关键词
fairness in AI; AI and society; 80% rule; privacy
资金
- U.S. Department of Commerce, National Institute of Standards and Technology [60NANB18D227]
- [IIS 1850023]
We propose differential fairness, a multi-attribute definition of fairness in machine learning which is informed by intersectionality, a critical lens arising from the humanities literature, leveraging connections between differential privacy and legal notions of fairness. We show that our criterion behaves sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. We provide a learning algorithm which respects our differential fairness criterion. Experiments on the COMPAS criminal recidivism dataset and census data demonstrate the utility of our methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据