A review of causality-based fairness machine learning

Cong Su, Guoxian Yu, J. Wang, Zhongmin Yan, Li-zhen Cui
{"title":"A review of causality-based fairness machine learning","authors":"Cong Su, Guoxian Yu, J. Wang, Zhongmin Yan, Li-zhen Cui","doi":"10.20517/ir.2022.17","DOIUrl":null,"url":null,"abstract":"With the wide application of machine learning driven automated decisions (e.g., education, loan approval, and hiring) in daily life, it is critical to address the problem of discriminatory behavior toward certain individuals or groups. Early studies focused on defining the correlation/association-based notions, such as statistical parity, equalized odds, etc. However, recent studies reflect that it is necessary to use causality to address the problem of fairness. This review provides an exhaustive overview of notions and methods for detecting and eliminating algorithmic discrimination from a causality perspective. The review begins by introducing the common causality-based definitions and measures for fairness. We then review causality-based fairness-enhancing methods from the perspective of pre-processing, in-processing and post-processing mechanisms, and conduct a comprehensive analysis of the advantages, disadvantages, and applicability of these mechanisms. In addition, this review also examines other domains where researchers have observed unfair outcomes and the ways they have tried to address them. There are still many challenges that hinder the practical application of causality-based fairness notions, specifically the difficulty of acquiring causal graphs and identifiability of causal effects. One of the main purposes of this review is to spark more researchers to tackle these challenges in the near future.","PeriodicalId":426514,"journal":{"name":"Intelligence & Robotics","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Intelligence & Robotics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.20517/ir.2022.17","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

With the wide application of machine learning driven automated decisions (e.g., education, loan approval, and hiring) in daily life, it is critical to address the problem of discriminatory behavior toward certain individuals or groups. Early studies focused on defining the correlation/association-based notions, such as statistical parity, equalized odds, etc. However, recent studies reflect that it is necessary to use causality to address the problem of fairness. This review provides an exhaustive overview of notions and methods for detecting and eliminating algorithmic discrimination from a causality perspective. The review begins by introducing the common causality-based definitions and measures for fairness. We then review causality-based fairness-enhancing methods from the perspective of pre-processing, in-processing and post-processing mechanisms, and conduct a comprehensive analysis of the advantages, disadvantages, and applicability of these mechanisms. In addition, this review also examines other domains where researchers have observed unfair outcomes and the ways they have tried to address them. There are still many challenges that hinder the practical application of causality-based fairness notions, specifically the difficulty of acquiring causal graphs and identifiability of causal effects. One of the main purposes of this review is to spark more researchers to tackle these challenges in the near future.
基于因果关系的公平机器学习综述
随着机器学习驱动的自动化决策(如教育、贷款审批和招聘)在日常生活中的广泛应用,解决对某些个人或群体的歧视行为问题至关重要。早期的研究侧重于定义相关/关联概念,如统计奇偶性、均等几率等。然而,最近的研究表明,有必要使用因果关系来解决公平问题。这篇综述提供了从因果关系角度检测和消除算法歧视的概念和方法的详尽概述。本文首先介绍了常见的基于因果关系的公平定义和衡量标准。然后,我们从前处理、中处理和后处理机制的角度回顾了基于因果关系的公平性增强方法,并对这些机制的优缺点和适用性进行了综合分析。此外,本综述还考察了研究人员观察到不公平结果的其他领域以及他们试图解决这些结果的方法。仍然有许多挑战阻碍了基于因果关系的公平概念的实际应用,特别是难以获得因果图和因果效应的可识别性。这篇综述的主要目的之一是激发更多的研究人员在不久的将来解决这些挑战。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信