乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T19:43:51Z","timestamp":1725479031003},"reference-count":41,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGMOD Rec."],"published-print":{"date-parts":[[2020,9,4]]},"abstract":"Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflect discrimination, suggesting a database repair problem. Existing treatments of fairness rely on statistical correlations that can be fooled by anomalies, such as Simpson's paradox. Proposals for causality-based definitions of fairness can correctly model some of these situations, but they rely on background knowledge of the underlying causal models. In this paper, we formalize the situation as a database repair problem, proving sufficient conditions for fair classifiers in terms of admissible variables as opposed to a complete causal model. We show that these conditions correctly capture subtle fairness violations. We then use these conditions as the basis for database repair algorithms that provide provable fairness guarantees about classifiers trained on their training labels. We demonstrate the effectiveness of our proposed techniques with experimental results.<\/jats:p>","DOI":"10.1145\/3422648.3422657","type":"journal-article","created":{"date-parts":[[2020,9,4]],"date-time":"2020-09-04T10:09:28Z","timestamp":1599214168000},"page":"34-41","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["Database Repair Meets Algorithmic Fairness"],"prefix":"10.1145","volume":"49","author":[{"given":"Babak","family":"Salimi","sequence":"first","affiliation":[{"name":"University of Washington, WA, USA"}]},{"given":"Bill","family":"Howe","sequence":"additional","affiliation":[{"name":"University of Washington, WA, USA"}]},{"given":"Dan","family":"Suciu","sequence":"additional","affiliation":[{"name":"University of Washington, WA, USA"}]}],"member":"320","published-online":{"date-parts":[[2020,9,4]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/551350"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2371212"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-010-0190-x"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295155"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0047"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098095"},{"key":"e_1_2_1_7_1","first-page":"558","article-title":"the researchers striving to make algorithms fair","author":"Courtland Rachel","year":"2018","unstructured":"Rachel Courtland . Bias detectives : the researchers striving to make algorithms fair . Nature , 558 , 2018 . Rachel Courtland. Bias detectives: the researchers striving to make algorithms fair. Nature, 558, 2018.","journal-title":"Nature"},{"key":"e_1_2_1_8_1","volume-title":"Rpt-insight-amazon scraps secret ai recruiting tool that showed bias against women","author":"Dastin Jeffrey","year":"2018","unstructured":"Jeffrey Dastin . Rpt-insight-amazon scraps secret ai recruiting tool that showed bias against women . Reuters , 2018 . Jeffrey Dastin. Rpt-insight-amazon scraps secret ai recruiting tool that showed bias against women. Reuters, 2018."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106277"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157469"},{"key":"e_1_2_1_13_1","volume-title":"Bloomberg, 2016","author":"Ingold David","year":"2016","unstructured":"David Ingold and Spencer Soper . Amazon doesn't consider the race of its customers. should it ? Bloomberg, 2016 . www.bloomberg.com\/graphics\/ 2016 -amazon-same-day\/. David Ingold and Spencer Soper. Amazon doesn't consider the race of its customers. should it? Bloomberg, 2016. www.bloomberg.com\/graphics\/2016-amazon-same-day\/."},{"key":"e_1_2_1_14_1","first-page":"1","volume-title":"Control and Communication, 2009. IC4 2009. 2nd International Conference on","author":"Kamiran Faisal","year":"2009","unstructured":"Faisal Kamiran and Toon Calders . Classifying without discriminating. In Computer , Control and Communication, 2009. IC4 2009. 2nd International Conference on , pages 1 -- 6 . IEEE, 2009 . Faisal Kamiran and Toon Calders. Classifying without discriminating. In Computer, Control and Communication, 2009. IC4 2009. 2nd International Conference on, pages 1--6. IEEE, 2009."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_3"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380573"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294834"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295162"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295162"},{"key":"e_1_2_1_20_1","volume-title":"How we analyzed the compas recidivism algorithm. ProPublica (5","author":"Larson Jeff","year":"2016","unstructured":"Jeff Larson , Surya Mattu , Lauren Kirchner , and Julia Angwin . How we analyzed the compas recidivism algorithm. ProPublica (5 2016 ), 9, 2016. Jeff Larson, Surya Mattu, Lauren Kirchner, and Julia Angwin. How we analyzed the compas recidivism algorithm. ProPublica (5 2016), 9, 2016."},{"key":"e_1_2_1_21_1","volume-title":"Computing optimal repairs for functional dependencies. ACM Transactions on Database Systems (TODS), 45(1):1--46","author":"Livshits Ester","year":"2020","unstructured":"Ester Livshits , Benny Kimelfeld , and Sudeepa Roy . Computing optimal repairs for functional dependencies. ACM Transactions on Database Systems (TODS), 45(1):1--46 , 2020 . Ester Livshits, Benny Kimelfeld, and Sudeepa Roy. Computing optimal repairs for functional dependencies. ACM Transactions on Database Systems (TODS), 45(1):1--46, 2020."},{"key":"e_1_2_1_22_1","volume-title":"Causal reasoning for algorithmic fairness. arXiv preprint arXiv:1805.05859","author":"Loftus Joshua R","year":"2018","unstructured":"Joshua R Loftus , Chris Russell , Matt J Kusner , and Ricardo Silva . Causal reasoning for algorithmic fairness. arXiv preprint arXiv:1805.05859 , 2018 . Joshua R Loftus, Chris Russell, Matt J Kusner, and Ricardo Silva. Causal reasoning for algorithmic fairness. arXiv preprint arXiv:1805.05859, 2018."},{"key":"e_1_2_1_23_1","volume-title":"Carnegie-Mellon Univ Pittsburgh Pa School of Computer Science","author":"Margaritis Dimitris","year":"2003","unstructured":"Dimitris Margaritis . Learning bayesian network model structure from data. Technical report , Carnegie-Mellon Univ Pittsburgh Pa School of Computer Science , 2003 . Dimitris Margaritis. Learning bayesian network model structure from data. Technical report, Carnegie-Mellon Univ Pittsburgh Pa School of Computer Science, 2003."},{"key":"e_1_2_1_24_1","first-page":"1931","volume-title":"Proceedings of the... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"2018","author":"Nabi Razieh","unstructured":"Razieh Nabi and Ilya Shpitser . Fair inference on outcomes . In Proceedings of the... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence , volume 2018 , page 1931 . NIH Public Access, 2018. Razieh Nabi and Ilya Shpitser. Fair inference on outcomes. In Proceedings of the... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence, volume 2018, page 1931. NIH Public Access, 2018."},{"key":"e_1_2_1_25_1","volume-title":"Cambridge university press","author":"Pearl Judea","year":"2009","unstructured":"Judea Pearl . Causality. Cambridge university press , 2009 . Judea Pearl. Causality. Cambridge university press, 2009."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"issue":"396","key":"e_1_2_1_28_1","first-page":"961","article-title":"Statistics and causal inference: Comment: Which ifs have causal answers","volume":"81","author":"Rubin Donald B","year":"1986","unstructured":"Donald B Rubin . Statistics and causal inference: Comment: Which ifs have causal answers . Journal of the American Statistical Association , 81 ( 396 ): 961 -- 962 , 1986 . Donald B Rubin. Statistics and causal inference: Comment: Which ifs have causal answers. Journal of the American Statistical Association, 81(396):961--962, 1986.","journal-title":"Journal of the American Statistical Association"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295388"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196914"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389759"},{"key":"e_1_2_1_32_1","volume-title":"Capuchin: Causal database repair for algorithmic fairness. arXiv preprint arXiv:1902.08283","author":"Salimi Babak","year":"2019","unstructured":"Babak Salimi , Luke Rodriguez , Bill Howe , and Dan Suciu . Capuchin: Causal database repair for algorithmic fairness. arXiv preprint arXiv:1902.08283 , 2019 . Babak Salimi, Luke Rodriguez, Bill Howe, and Dan Suciu. Capuchin: Causal database repair for algorithmic fairness. arXiv preprint arXiv:1902.08283, 2019."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319901"},{"key":"e_1_2_1_34_1","first-page":"109","article-title":"Disparate impact in big data policing","volume":"52","author":"Selbst Andrew D","year":"2017","unstructured":"Andrew D Selbst . Disparate impact in big data policing . Ga. L. Rev. , 52 : 109 , 2017 . Andrew D Selbst. Disparate impact in big data policing. Ga. L. Rev., 52:109, 2017.","journal-title":"Ga. L. Rev."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1214\/17-AOAS1058"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174014"},{"key":"e_1_2_1_37_1","volume-title":"Wall Strreet Journal","author":"Weber Lauren","year":"2014","unstructured":"Lauren Weber and Elizabeth Dwoskin . Are workplace personality tests fair ? Wall Strreet Journal , 2014 . Lauren Weber and Elizabeth Dwoskin. Are workplace personality tests fair? Wall Strreet Journal, 2014."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/3468.895901"},{"key":"e_1_2_1_39_1","first-page":"1920","volume-title":"Proceedings of the 2017 Conference on Learning Theory","author":"Woodworth Blake","year":"2017","unstructured":"Blake Woodworth , Suriya Gunasekar , Mesrob I. Ohannessian , and Nathan Srebro . Learning non-discriminatory predictors . In Proceedings of the 2017 Conference on Learning Theory , pages 1920 -- 1953 , 2017 . Blake Woodworth, Suriya Gunasekar, Mesrob I. Ohannessian, and Nathan Srebro. Learning non-discriminatory predictors. In Proceedings of the 2017 Conference on Learning Theory, pages 1920--1953, 2017."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052660"},{"key":"e_1_2_1_41_1","first-page":"962","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","author":"Zafar Muhammad Bilal","year":"2017","unstructured":"Muhammad Bilal Zafar , Isabel Valera , Manuel Gomez Rogriguez , and Krishna P. Gummadi . Fairness Constraints: Mechanisms for Fair Classification . In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics , pages 962 -- 970 , 2017 . Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rogriguez, and Krishna P. Gummadi. Fairness Constraints: Mechanisms for Fair Classification. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, pages 962--970, 2017."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/3042817.3042973"}],"container-title":["ACM SIGMOD Record"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3422648.3422657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T00:07:49Z","timestamp":1672618069000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3422648.3422657"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,4]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,9,4]]}},"alternative-id":["10.1145\/3422648.3422657"],"URL":"https:\/\/doi.org\/10.1145\/3422648.3422657","relation":{},"ISSN":["0163-5808"],"issn-type":[{"value":"0163-5808","type":"print"}],"subject":[],"published":{"date-parts":[[2020,9,4]]},"assertion":[{"value":"2020-09-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}