Bias in data-driven artificial intelligence systems-An introductory survey

被引：476

作者：

Ntoutsi, Eirini ^{[1
,2
]}

Fafalios, Pavlos ^{[3
]}

Gadiraju, Ujwal ^{[1
,2
]}

Iosifidis, Vasileios ^{[1
,2
]}

Nejdl, Wolfgang ^{[1
,2
]}

Vidal, Maria-Esther ^{[4
]}

Ruggieri, Salvatore ^{[5
]}

Turini, Franco ^{[5
]}

Papadopoulos, Symeon ^{[6
]}

Krasanakis, Emmanouil ^{[6
]}

Kompatsiaris, Ioannis ^{[6
]}

Kinder-Kurlanda, Katharina ^{[7
]}

Wagner, Claudia ^{[7
]}

Karimi, Fariba ^{[7
]}

Fernandez, Miriam ^{[8
]}

Alani, Harith ^{[8
]}

Berendt, Bettina ^{[9
,10
]}

Kruegel, Tina ^{[11
]}

Heinze, Christian ^{[11
]}

Broelemann, Klaus ^{[12
]}

Kasneci, Gjergji ^{[12
]}

Tiropanis, Thanassis ^{[13
]}

Staab, Steffen ^{[1
,2
,13
,14
]}

机构：

[1] Leibniz Univ Hannover, L3S Res Ctr, Hannover, Germany

[2] Leibniz Univ Hannover, Fac Elect Engn & Comp Sci, Hannover, Germany

[3] FORTH, ICS, Iraklion, Greece

[4] TIB Leibniz Informat Ctr Sci & Tecnhnol, Hannover, Germany

[5] Univ Pisa, Dipartimento Informat, KDDLAB, Pisa, Italy

[6] CERTH, Informat Technol Inst, Thessaloniki, Greece

[7] GESIS Leibniz Inst Social Sci, Cologne, Germany

[8] Open Univ, Knowledge Media Inst, Milton Keynes, Bucks, England

[9] TU Berlin, Fac Elect Engn & Comp Sci, Berlin, Germany

[10] Katholieke Univ Leuven, Dept Comp Sci, Leuven, Belgium

[11] Leibniz Univ Hannover, Inst Legal Informat, Hannover, NH, Germany

[12] SCHUFA Holding AG, Innovat Lab, Wiesbaden, Germany

[13] Univ Southampton, Elect & Comp Sci, Southampton, Hants, England

[14] Univ Stuttgart, Inst Parallel & Distributed Syst, Stuttgart, Germany

来源：

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY | 2020年 / 10卷 / 03期

关键词：

fairness; fairness-aware AI; fairness-aware machine learning; interpretability; responsible AI; BLACK-BOX; DISCRIMINATION; CLASSIFICATION; CLASSIFIERS;

D O I：

10.1002/widm.1356

中图分类号：

TP18 [人工智能理论];

学科分类号：

140502 [人工智能];

摘要：

Artificial Intelligence (AI)-based systems are widely employed nowadays to make decisions that have far-reaching impact on individuals and society. Their decisions might affect everyone, everywhere, and anytime, entailing concerns about potential human rights issues. Therefore, it is necessary to move beyond traditional AI algorithms optimized for predictive performance and embed ethical and legal principles in their design, training, and deployment to ensure social good while still benefiting from the huge potential of the AI technology. The goal of this survey is to provide a broad multidisciplinary overview of the area of bias in AI systems, focusing on technical challenges and solutions as well as to suggest new research directions towards approaches well-grounded in a legal frame. In this survey, we focus on data-driven AI, as a large part of AI is powered nowadays by (big) data and powerful machine learning algorithms. If otherwise not specified, we use the general term bias to describe problems related to the gathering or processing of data that might result in prejudiced decisions on the bases of demographic features such as race, sex, and so forth. This article is categorized under: Commercial, Legal, and Ethical Issues > Fairness in Data Mining Commercial, Legal, and Ethical Issues > Ethical Considerations Commercial, Legal, and Ethical Issues > Legal Issues

引用

页数：14

共 94 条

[1]

Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) [J].

Adadi, Amina ;

Berrada, Mohammed .

IEEE ACCESS, 2018, 6 :52138-52160

[2]

Agarwal A, 2018, 35 INT C MACHINE LEA, V80

[3]

Angwin J., 2016, PROPUBLICA

[4]

Atzmueller Martin, 2017, DECLARATIVE PROGRAMM, P97

[5]

Bias on the Web [J].

Baeza-Yates, Ricardo .

COMMUNICATIONS OF THE ACM, 2018, 61 (06) :54-61

[6]

Big Data's Disparate Impact [J].

Barocas, Solon ;

Selbst, Andrew D. .

CALIFORNIA LAW REVIEW, 2016, 104 (03) :671-732

[7]

Optimal classification trees [J].

Bertsimas, Dimitris ;

Dunn, Jack .

MACHINE LEARNING, 2017, 106 (07) :1039-1082

[8]

Besnard Philippe, 2014, Foundations of Information and Knowledge Systems. 8th International Symposium, FoIKS 2014. Proceedings: LNCS 8367, P79, DOI 10.1007/978-3-319-04939-7_3

[9]

Bolukbasi T, 2016, ADV NEUR IN, V29

[10]

Borgesius F.Z, 2018, Discrimination, artificial intelligence and algorithmic decision making

← 1 2 3 4 5 6 7 8 9 10 →