Counterfactual Fairness

被引:0
作者
Kusner, Matt [1 ,2 ]
Loftus, Joshua [3 ]
Russell, Chris [1 ,4 ]
Silva, Ricardo [1 ,5 ]
机构
[1] Alan Turing Inst, London, England
[2] Univ Warwick, Coventry, W Midlands, England
[3] NYU, New York, NY 10003 USA
[4] Univ Surrey, Guildford, Surrey, England
[5] UCL, London, England
来源
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017) | 2017年 / 30卷
基金
英国工程与自然科学研究理事会;
关键词
RISK;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal inference. Our definition of counterfactual fairness captures the intuition that a decision is fair towards an individual if it the same in (a) the actual world and (b) a counterfactual world where the individual belonged to a different demographic group. We demonstrate our framework on a real-world problem of fair prediction of success in law school.
引用
收藏
页数:11
相关论文
共 50 条
[31]   Aerosol Geoengineering Deployment and Fairness [J].
Svoboda, Toby .
ENVIRONMENTAL VALUES, 2016, 25 (01) :51-68
[32]   Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML [J].
Nguyen, Giang ;
Biswas, Sumon ;
Rajan, Hridesh .
PROCEEDINGS OF THE 31ST ACM JOINT MEETING EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING, ESEC/FSE 2023, 2023, :502-514
[33]   The Lure of Counterfactual Curiosity: People Incur a Cost to Experience Regret [J].
FitzGibbon, Lily ;
Komiya, Asuka ;
Murayama, Kou .
PSYCHOLOGICAL SCIENCE, 2021, 32 (02) :241-255
[34]   Attributable fraction and related measures: Conceptual relations in the counterfactual framework [J].
Suzuki, Etsuji ;
Yamamoto, Eiji .
JOURNAL OF CAUSAL INFERENCE, 2023, 11 (01)
[35]   Deconstructing the smoking-preeclampsia paradox through a counterfactual framework [J].
Luque-Fernandez, Miguel Angel ;
Zoega, Helga ;
Valdimarsdottir, Unnur ;
Williams, Michelle A. .
EUROPEAN JOURNAL OF EPIDEMIOLOGY, 2016, 31 (06) :613-623
[36]   Algorithmic Fairness: Choices, Assumptions, and Definitions [J].
Mitchell, Shira ;
Potash, Eric ;
Barocas, Solon ;
D'Amour, Alexander ;
Lum, Kristian .
ANNUAL REVIEW OF STATISTICS AND ITS APPLICATION, VOL 8, 2021, 2021, 8 :141-163
[37]   One-Network Adversarial Fairness [J].
Adel, Tameem ;
Valera, Isabel ;
Ghahramani, Zoubin ;
Weller, Adrian .
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, :2412-2420
[38]   Wasserstein Robust Classification with Fairness Constraints [J].
Wang, Yijie ;
Nguyen, Viet Anh ;
Hanasusanto, Grani A. .
M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT, 2024, 26 (04) :1567-1585
[39]   Punishing the Lemon: The Ethics of Actuarial Fairness [J].
Jha, Saurabh .
JOURNAL OF THE AMERICAN COLLEGE OF RADIOLOGY, 2012, 9 (12) :887-893
[40]   Fair play in energy policy decisions: Procedural fairness, outcome fairness and acceptance of the decision to rebuild nuclear power plants [J].
Visschers, Vivianne H. M. ;
Siegrist, Michael .
ENERGY POLICY, 2012, 46 :292-300