第3期 邓蔚，等：公平性机器学习研究综述 ·585· tion for fair decision making[Cl//Symposium on Machine [29]Supreme Court of the United States.Ricci v.DeStefano [EB/OL] Learning and the Law at the 29th Conference on Neural (2009-06-29[2020-08-07刀.557U.S.557,https://supreme Information Processing Systems.Barcelona,Spain,2016:1. justia.com/cases/federal/us/557/557/.2009. [17]DWORK C,HARDT M.PITASSI T,et al.Fairness [30]Adult data[EB/OL].[2020-07-26].http://tinyurl.com/ through awareness[C]//Proceedings of the 3rd Innova- UCI-Adult.1996. tions in Theoretical Computer Science Conference.New [31]LICHMAN M.UCI machine learning repository[EB/OL]. York.USA.2012:214-226 (2013)[2020-07-26].http://archive.ics.uci.edu/ml,2013. [18]JOSEPH M,KEARNS M,MORGENSTERN J,et al. [32]ANGWIN J,LARSON J,MATTU S,et al.Machine bias. Rawlsian fairness for machine learning [DB/OL].(2017- risk assessments in criminal sentencing[EB/OL].(2016- 06-29)[2020-08-07 ]arXiv preprint arXiv:1610.09559V2, 05-23)[2020-07-26]https://www.propublica.org/article/ arxiv.org/abs/1610.09559v2.2016. machine-bias-risk-assessments-in-criminal-sentencing [19]LOUIZOS C.SWERSKY K,LI Yujia,et al.The vari- 2016. ational fair autoencoder[C]//Proceedings of the 4th Inter- [33]Bank Marketing Data Set [EB/OL].(2012-02-14)[2020- national Conference on Learning Representations.San 07-26]https://archive.ics.uci.edu/ml/datasets/Bank% Juan,Puerto Rico,2016. 2BMarketing,2012. [20]ZEMEL R,WU Yu,SWERSKY K,et al.Learning fair [34]KHADEMI A,LEE S,FOLEY D,et al.Fairness in al- representations[Cl//Proceedings of the 30th International gorithmic decision making:an excursion through the lens Conference on International Conference on Machine of causality[C]//The World Wide Web Conference.San Learning.Atlanta,USA,2013:325-333. Francisco.,USA,2019:2907-2914. [21]KIM M P.KOROLOVA A.ROTHBLUM G N.et al. [35]FELDMAN M,FRIEDLER S A,MOELLER J,et al.Cer- Preference-informed fairness[Cl//Proceedings of the 2020 tifying and removing disparate impact[C]//Proceedings of Conference on Fairness,Accountability,and Transpar- the 21th ACM SIGKDD International Conference on ency.New York,USA.2020:546. Knowledge Discovery and Data Mining.New York. [22]ZAFA M B.VALERA I.ROGRIGUEZ M G.et al.Fair- USA.2015:259-268. ness constraints:mechanisms for fair classification[Cl// [36]KAMIRAN F,CALDERS T.Data preprocessing tech- Proceedings of the 20th International Conference on Arti- niques for classification without discrimination[J].Know- ficial Intelligence and Statistics.Lille,France,2017: ledge and information systems,2012,33(1):1-33 962-970. [37]CALMON F P,WEI D,VINZAMURI B,et al.Optim- [23]ZAFAR M B,VALERA I,RODRIGUEZ M G,et al. ized pre-processing for discrimination prevention[C]//Pro- Fairness beyond disparate treatment disparate impact: ceedings of the 31st International Conference on Neural learning classification without disparate mistreat- Information Processing Systems.Red Hook,USA,2017: ment[C]//Proceedings of the 26th International Confer- 3995-4004. ence on World Wide Web.Perth.Australia.2017: [38]KAMISHIMA T.AKAHO S,ASOH H,et al.Fairness- 1171-1180 aware classifier with prejudice remover regularizer[M]// [24]BERETTA E,SANTANGELO A,LEPRI B,et al.The in- FLACH P A,DE BIE T,CRISTIANINI N.Machine visible power of fairness.How machine learning shapes Learning and Knowledge Discovery in Databases.Berlin: democracy[DB/OL].(2019-03-22)[2020-07-26]arXiv Springer,.2012:35-50. preprint arXiv:1903.09493v1,https://arxiv.org/ [39]CALDERS T,VERWER S.Three naive Bayes ap- abs/1903.09493,2019. proaches for discrimination-free classification[J].Data [25]CHOULDECHOVA A.Fair prediction with disparate im- mining and knowledge discovery,2010,21(2):277-292. pact:a study of bias in recidivism prediction instru- [40]BOSE A J.HAMILTON W.Compositional fairness con- ments[J].Big data,2017,5(2):153-163. straints for graph embeddings [DB/OL].(2019-07- [26]BAROCAS S,SELBST A D.Big data's disparate 16)[2020-07-07htps:///arxiv.org/abs/1905.10674,2019. impact[J].California law review,2016,104:671-732. [41]HARDT M,PRICE E,SREBRO N.Equality of opportun- [27]KEARNS M.ROTH A.WU Z S.Meritocratic fairness for ity in supervised learning[C]//Proceedings of the 30th In- cross-population selection[C]//Proceedings of the 34th In- ternational Conference on Neural Information Processing ternational Conference on Machine Learning.Sydney, Systems.Red Hook,USA,2016:3315-3323. Australia,2017:1828-1836. [42]KAMIRAN F,CALDERS T.Classifying without dis- [28]KLEINBERG J,MULLAINATHAN S,RAGHAVAN M. criminating[C]//Proceedings of 2009 2nd International Inherent trade-offs in the fair determination of risk Conference on Computer,Control and Communication. scores[C]//Proceedings of the 8th Innovations in Theoret- Karachi,Pakistan,2009 ical Computer Science Conference.Dagstuhl,Germany, [43]WOODWORTH B,GUNASEKAR S,OHANNESSIAN 2017. M I,et al.Learning non-discriminatory predic-tion for fair decision making[C]//Symposium on Machine Learning and the Law at the 29th Conference on Neural Information Processing Systems. Barcelona, Spain, 2016: 1. DWORK C, HARDT M, PITASSI T, et al. Fairness through awareness[C]//Proceedings of the 3rd Innova￾tions in Theoretical Computer Science Conference. New York, USA, 2012: 214−226. [17] JOSEPH M, KEARNS M, MORGENSTERN J, et al. Rawlsian fairness for machine learning [DB/OL]. (2017- 06-29)[2020-08-07] arXiv preprint arXiv:1610. 09559V2, arxiv.org/abs/1610.09559v2, 2016. [18] LOUIZOS C, SWERSKY K, LI Yujia, et al. The vari￾ational fair autoencoder[C]//Proceedings of the 4th Inter￾national Conference on Learning Representations. San Juan, Puerto Rico, 2016. [19] ZEMEL R, WU Yu, SWERSKY K, et al. Learning fair representations[C]//Proceedings of the 30th International Conference on International Conference on Machine Learning. Atlanta, USA, 2013: 325−333. [20] KIM M P, KOROLOVA A, ROTHBLUM G N, et al. Preference-informed fairness[C]//Proceedings of the 2020 Conference on Fairness, Accountability, and Transpar￾ency. New York, USA, 2020: 546. [21] ZAFA M B, VALERA I, ROGRIGUEZ M G, et al. Fair￾ness constraints: mechanisms for fair classification[C]// Proceedings of the 20th International Conference on Arti￾ficial Intelligence and Statistics. Lille, France, 2017: 962−970. [22] ZAFAR M B, VALERA I, RODRIGUEZ M G, et al. Fairness beyond disparate treatment & disparate impact: learning classification without disparate mistreat￾ment[C]//Proceedings of the 26th International Confer￾ence on World Wide Web. Perth, Australia, 2017: 1171−1180. [23] BERETTA E, SANTANGELO A, LEPRI B, et al. The in￾visible power of fairness. How machine learning shapes democracy [DB/OL]. (2019-03-22)[2020-07-26] arXiv preprint arXiv:1903.09493v1, https://arxiv.org/ abs/1903.09493, 2019. [24] CHOULDECHOVA A. Fair prediction with disparate im￾pact: a study of bias in recidivism prediction instru￾ments[J]. Big data, 2017, 5(2): 153–163. [25] BAROCAS S, SELBST A D. Big data’s disparate impact[J]. California law review, 2016, 104: 671–732. [26] KEARNS M, ROTH A, WU Z S. Meritocratic fairness for cross-population selection[C]//Proceedings of the 34th In￾ternational Conference on Machine Learning. Sydney, Australia, 2017: 1828−1836. [27] KLEINBERG J, MULLAINATHAN S, RAGHAVAN M. Inherent trade-offs in the fair determination of risk scores[C]//Proceedings of the 8th Innovations in Theoret￾ical Computer Science Conference. Dagstuhl, Germany, 2017. [28] Supreme Court of the United States. Ricci v. DeStefano [EB/OL]. (2009-06-29)[ 2020-08-07]. 557 U.S. 557,https://supreme. justia.com/cases/federal/us/557/557/, 2009. [29] Adult data[EB/OL]. [2020-07-26]. http://tinyurl.com/ UCI-Adult, 1996. [30] LICHMAN M. UCI machine learning repository[EB/OL]. (2013)[2020-07-26]. http://archive.ics.uci.edu/ml, 2013. [31] ANGWIN J, LARSON J, MATTU S, et al. Machine bias. risk assessments in criminal sentencing[EB/OL]. (2016- 05-23)[2020-07-26] https://www.propublica.org/article/ machine-bias-risk-assessments-in-criminal-sentencing, 2016. [32] Bank Marketing Data Set [EB/OL]. (2012-02-14) [2020- 07-26] https://archive.ics.uci.edu/ml/datasets/ Bank% 2BMarketing, 2012. [33] KHADEMI A, LEE S, FOLEY D, et al. Fairness in al￾gorithmic decision making: an excursion through the lens of causality[C]//The World Wide Web Conference. San Francisco, USA, 2019: 2907−2914. [34] FELDMAN M, FRIEDLER S A, MOELLER J, et al. Cer￾tifying and removing disparate impact[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA, 2015: 259−268. [35] KAMIRAN F, CALDERS T. Data preprocessing tech￾niques for classification without discrimination[J]. Know￾ledge and information systems, 2012, 33(1): 1–33. [36] CALMON F P, WEI D, VINZAMURI B, et al. Optim￾ized pre-processing for discrimination prevention[C]//Pro￾ceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, USA, 2017: 3995−4004. [37] KAMISHIMA T, AKAHO S, ASOH H, et al. Fairness￾aware classifier with prejudice remover regularizer[M]// FLACH P A, DE BIE T, CRISTIANINI N. Machine Learning and Knowledge Discovery in Databases. Berlin: Springer, 2012: 35−50. [38] CALDERS T, VERWER S. Three naive Bayes ap￾proaches for discrimination-free classification[J]. Data mining and knowledge discovery, 2010, 21(2): 277–292. [39] BOSE A J, HAMILTON W. Compositional fairness con￾straints for graph embeddings [DB/OL]. (2019-07- 16)[2020-07-07] https://arxiv.org/abs/1905.10674, 2019. [40] HARDT M, PRICE E, SREBRO N. Equality of opportun￾ity in supervised learning[C]//Proceedings of the 30th In￾ternational Conference on Neural Information Processing Systems. Red Hook, USA, 2016: 3315−3323. [41] KAMIRAN F, CALDERS T. Classifying without dis￾criminating[C]//Proceedings of 2009 2nd International Conference on Computer, Control and Communication. Karachi, Pakistan, 2009. [42] WOODWORTH B, GUNASEKAR S, OHANNESSIAN M I, et al. Learning non-discriminatory predic- [43] 第 3 期 邓蔚，等：公平性机器学习研究综述 ·585·