BriefGPT.xyz
May, 2023
机器学习中可配置公平解决方案的广义不平等影响
Generalized Disparate Impact for Configurable Fairness Solutions in ML
HTML
PDF
Luca Giuliani, Eleonora Misino, Michele Lombardi
TL;DR
该研究对AI公平性在连续保护属性上作出两个贡献：一是展示 Hirschfeld-Gebelein-Renyi (HGR)指标的价值，但存在一些关键限制；二是介绍一系列指标，并允许定义细粒度约束，扩展了关于连续保护属性的可用选项。
Abstract
We make two contributions in the field of
ai fairness
over
continuous protected attributes
. First, we show that the Hirschfeld-Gebelein-Renyi (HGR) indicator (the only one currently available for such a case) is
→