BriefGPT.xyz
Jun, 2020
从数据学习个体公平度量的两种简单方法
Two Simple Ways to Learn Individual Fairness Metrics from Data
HTML
PDF
Debarghya Mukherjee, Mikhail Yurochkin, Moulinath Banerjee, Yuekai Sun
TL;DR
本研究提出了两种简单的方法，从多种数据类型中学习公平指标，经实验证明使用学习到的指标进行公平训练可以在三种机器学习任务中有效减少性别和种族偏见，同时也提供了关于统计性能的理论保证。
Abstract
individual fairness
is an intuitive definition of
algorithmic fairness
that addresses some of the drawbacks of group fairness. Despite its benefits, it depends on a task specific
→