Fairness seen as global sensitivity analysis

被引：7

作者：

Benesse, Clement ^{[1
]}

Gamboa, Fabrice ^{[1
]}

Loubes, Jean-Michel ^{[1
]}

Boissin, Thibaut ^{[2
]}

机构：

[1] Inst Math Toulouse, Toulouse, France

[2] IRIT St Exupery, Toulouse, France

来源：

MACHINE LEARNING | 2024年 / 113卷 / 05期

关键词：

Global Sensitivity Analysis; Fairness; Sobol' indices; Cramer-von-Mises indices; Disparate Impact;

D O I：

10.1007/s10994-022-06202-y

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Ensuring that a predictor is not biased against a sensitive feature is the goal of fair learning. Meanwhile, Global Sensitivity Analysis (GSA) is used in numerous contexts to monitor the influence of any feature on an output variable. We merge these two domains, Global Sensitivity Analysis and Fairness, by showing how fairness can be defined using a special framework based on Global Sensitivity Analysis and how various usual indicators are common between these two fields. We also present new Global Sensitivity Analysis indices, as well as rates of convergence, that are useful as fairness proxies.

引用

页码：3205 / 3232

页数：28

共 48 条

[1]

Azadkia M., 2019, ARXIV PREPRINT ARXIV

[2]

Berlinet A., 2004, REPRODUCING KERNEL H, DOI [10.1007/978-1-4419-9096-9, DOI 10.1007/978-1-4419-9096-9]

[3] A Survey of Bias in Machine Learning Through the Prism of Statistical Parity [J].