关于公平观念和相关紧张关系的调查

IF 2.3 Q3 MANAGEMENT
Guilherme Alves , Fabien Bernier , Miguel Couceiro , Karima Makhlouf , Catuscia Palamidessi , Sami Zhioua
{"title":"关于公平观念和相关紧张关系的调查","authors":"Guilherme Alves ,&nbsp;Fabien Bernier ,&nbsp;Miguel Couceiro ,&nbsp;Karima Makhlouf ,&nbsp;Catuscia Palamidessi ,&nbsp;Sami Zhioua","doi":"10.1016/j.ejdp.2023.100033","DOIUrl":null,"url":null,"abstract":"<div><p>Automated decision systems are increasingly used to take consequential decisions in problems such as job hiring and loan granting with the hope of replacing subjective human decisions with objective machine learning (ML) algorithms. However, ML-based decision systems are prone to bias, which results in yet unfair decisions. Several notions of fairness have been defined in the literature to capture the different subtleties of this ethical and social concept (<em>e.g.,</em> statistical parity, equal opportunity, etc.). Fairness requirements to be satisfied while learning models created several types of tensions among the different notions of fairness and other desirable properties such as privacy and classification accuracy. This paper surveys the commonly used fairness notions and discusses the tensions among them with privacy and accuracy. Different methods to address the fairness-accuracy trade-off (classified into four approaches, namely, pre-processing, in-processing, post-processing, and hybrid) are reviewed. The survey is consolidated with experimental analysis carried out on fairness benchmark datasets to illustrate the relationship between fairness measures and accuracy in real-world scenarios.</p></div>","PeriodicalId":44104,"journal":{"name":"EURO Journal on Decision Processes","volume":null,"pages":null},"PeriodicalIF":2.3000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Survey on fairness notions and related tensions\",\"authors\":\"Guilherme Alves ,&nbsp;Fabien Bernier ,&nbsp;Miguel Couceiro ,&nbsp;Karima Makhlouf ,&nbsp;Catuscia Palamidessi ,&nbsp;Sami Zhioua\",\"doi\":\"10.1016/j.ejdp.2023.100033\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Automated decision systems are increasingly used to take consequential decisions in problems such as job hiring and loan granting with the hope of replacing subjective human decisions with objective machine learning (ML) algorithms. However, ML-based decision systems are prone to bias, which results in yet unfair decisions. Several notions of fairness have been defined in the literature to capture the different subtleties of this ethical and social concept (<em>e.g.,</em> statistical parity, equal opportunity, etc.). Fairness requirements to be satisfied while learning models created several types of tensions among the different notions of fairness and other desirable properties such as privacy and classification accuracy. This paper surveys the commonly used fairness notions and discusses the tensions among them with privacy and accuracy. Different methods to address the fairness-accuracy trade-off (classified into four approaches, namely, pre-processing, in-processing, post-processing, and hybrid) are reviewed. The survey is consolidated with experimental analysis carried out on fairness benchmark datasets to illustrate the relationship between fairness measures and accuracy in real-world scenarios.</p></div>\",\"PeriodicalId\":44104,\"journal\":{\"name\":\"EURO Journal on Decision Processes\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"EURO Journal on Decision Processes\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2193943823000067\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MANAGEMENT\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"EURO Journal on Decision Processes","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2193943823000067","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MANAGEMENT","Score":null,"Total":0}
引用次数: 0

摘要

自动化决策系统越来越多地被用于在招聘和贷款发放等问题上做出相应的决策,希望用客观的机器学习(ML)算法取代主观的人类决策。然而,基于ML的决策系统容易产生偏见,这导致了不公平的决策。文献中定义了几个公平概念,以捕捉这一伦理和社会概念的不同微妙之处(例如,统计平等、机会平等等)。在学习模型时需要满足的公平要求在不同的公平概念和其他期望属性(如隐私和分类准确性)之间产生了几种类型的紧张关系。本文调查了常用的公平概念,并讨论了它们之间的隐私和准确性之间的紧张关系。综述了解决公平-准确性权衡的不同方法(分为四种方法,即预处理、处理中、后处理和混合)。该调查与在公平基准数据集上进行的实验分析相结合,以说明现实世界场景中公平措施与准确性之间的关系。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Survey on fairness notions and related tensions

Automated decision systems are increasingly used to take consequential decisions in problems such as job hiring and loan granting with the hope of replacing subjective human decisions with objective machine learning (ML) algorithms. However, ML-based decision systems are prone to bias, which results in yet unfair decisions. Several notions of fairness have been defined in the literature to capture the different subtleties of this ethical and social concept (e.g., statistical parity, equal opportunity, etc.). Fairness requirements to be satisfied while learning models created several types of tensions among the different notions of fairness and other desirable properties such as privacy and classification accuracy. This paper surveys the commonly used fairness notions and discusses the tensions among them with privacy and accuracy. Different methods to address the fairness-accuracy trade-off (classified into four approaches, namely, pre-processing, in-processing, post-processing, and hybrid) are reviewed. The survey is consolidated with experimental analysis carried out on fairness benchmark datasets to illustrate the relationship between fairness measures and accuracy in real-world scenarios.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
2.70
自引率
10.00%
发文量
15
×
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:481959085
Book学术官方微信