{"type":"ScholarlyArticle","title":"Counterfactual Fairness: Unidentification, Bound and Algorithm","authors":[{"name":"Yongkai Wu","slug":"yongkai-wu","given":"Yongkai","family":"Wu","affiliation":"University of Arkansas"},{"name":"Lu Zhang","slug":"lu-zhang","given":"Lu","family":"Zhang","affiliation":"University of Arkansas"},{"name":"Xintao Wu","slug":"xintao-wu","given":"Xintao","family":"Wu","affiliation":"University of Arkansas"}],"abstract":"Fairness-aware learning studies the problem of building machine learning models that are subject to fairness requirements. Counterfactual fairness is a notion of fairness derived from Pearl's causal model, which considers a model is fair if for a particular individual or group its prediction in the real world is the same as that in the counterfactual world where the individual(s) had belonged to a different demographic group. However, an inherent limitation of counterfactual fairness is that it cannot be uniquely quantified from the observational data in certain situations, due to the unidentifiability of the counterfactual quantity. In this paper, we address this limitation by mathematically bounding the unidentifiable counterfactual quantity, and develop a theoretically sound algorithm for constructing counterfactually fair classifiers. We evaluate our method in the experiments using both synthetic and real-world datasets, as well as compare with existing methods. The results validate our theory and show the effectiveness of our method.","doi":"10.24963/ijcai.2019/199","url":"https://ijcai.org/proceedings/2019/199","pdf":"https://ijcai.org/proceedings/2019/0199.pdf","markdown":"https://ijcai.org/proceedings/2019/199.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/199","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Humans and AI","track":"Main track","number":199,"pages":{"first":1438,"last":1444},"keywords":["Knowledge Representation and Reasoning: Action, Change and Causality","Humans and AI: Ethical Issues in AI","Machine Learning: Classification"],"videos":[],"references":[{"position":1,"raw":"[Chiappa, 2019] Silvia Chiappa. Path-Specific Counterfac- tual Fairness. The Thirty-Third AAAI Conference on Arti- ficial Intelligence (AAAI-19), 2019.","title":"Path-Specific Counterfactual Fairness","authors":"Silvia Chiappa","year":"2019","venue":"The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Kilbertus et al., 2017] Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janz- ing, and Bernhard Schölkopf. Avoiding Discrimination through Causal Reasoning. Neural Information Process- ing Systems, 2017.","title":"Avoiding Discrimination through Causal Reasoning","authors":"Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, Bernhard Schölkopf","year":"2017","venue":"Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Kusner et al., 2017] Matt J. Kusner, Joshua R. Loftus, Chris Russell, and Ricardo Silva. Counterfactual Fairness. Neu- ral Information Processing Systems, 2017.","title":"Counterfactual Fairness. Neural Information Processing Systems","authors":"Matt J Kusner, Joshua R Loftus, Chris Russell, Ricardo Silva","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Li et al., 2017] Jiuyong Li, Jixue Liu, Lin Liu, Thuc Duy Le, Saisai Ma, and Yizhao Han. Discrimination detection by causal effect estimation. In 2017 IEEE International Conference on Big Data (Big Data), pages 1087-1094. IEEE, December 2017.","title":"Discrimination detection by causal effect estimation","authors":"Li","year":"2017","venue":"2017 IEEE International Conference on Big Data (Big Data)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Lichman, 2013] M Lichman. UCI Machine Learning Repository. http://archive.ics.uci.edu/ml, 2013.","title":"UCI Machine Learning Repository","authors":"Lichman","year":null,"venue":null,"doi":null,"url":"http://archive.ics.uci.edu/ml,2013","internal_url":null},{"position":6,"raw":"[Nabi and Shpitser, 2018] Razieh Nabi and Ilya Shpitser. Fair Inference On Outcomes. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), pages 1931-1940, 2018.","title":"Razieh Nabi and Ilya Shpitser. Fair Inference On Outcomes","authors":"Shpitser Nabi","year":"2018","venue":"The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Pearl, 2009] Judea Pearl. Causality: Models, Reasoning and Inference. Cambridge University Press, New York, NY, USA, 2nd edition, 2009.","title":"Judea Pearl. Causality: Models, Reasoning and Inference","authors":"Pearl","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Scheines et al., 1998] Richard Scheines, Peter Spirtes, Clark Glymour, Christopher Meek, and Thomas Richard- son. The TETRAD Project: Constraint Based Aids to Causal Model Specification. Multivariate Behavioral Re- search, 33(1):65-117, January 1998.","title":"The TETRAD Project: Constraint Based Aids to Causal Model Specification","authors":"Richard Scheines, Peter Spirtes, Clark Glymour, Christopher Meek, Thomas Richardson","year":"1998","venue":"Multivariate Behavioral Research","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Shpitser and Pearl, 2008] Ilya Shpitser and Judea Pearl. Complete Identification Methods for the Causal Hierar- chy. Journal of Machine Learning Research, 9:1941- 1979, 2008.","title":"Ilya Shpitser and Judea Pearl. Complete Identification Methods for the Causal Hierarchy","authors":"Pearl Shpitser","year":"2008","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Tian and Pearl, 2002] Jin Tian and Judea Pearl. A General Identification Condition for Causal Effects. Proceedings of the Eighteenth National Conference on Artificial Intelli- gence and Fourteenth Conference on Innovative Applica- tions of Artificial Intelligence (IAAI 2002), (August):567- 573, 2002.","title":"A General Identification Condition for Causal Effects","authors":"Pearl ; Tian, Jin Tian, Judea Pearl","year":"2002","venue":"Proceedings of the Eighteenth National Conference on Artificial Intelligence and Fourteenth Conference on Innovative Applications of Artificial Intelligence (IAAI 2002)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Zhang and Bareinboim, 2018] Junzhe Zhang and Elias Bareinboim. Fairness in Decision-Making -The Causal Explanation Formula. The Thirty-Second AAAI Confer- ence on Artificial Intelligence (AAAI-18), 2018.","title":"Fairness in Decision-Making -The Causal Explanation Formula","authors":"Bareinboim Zhang, Junzhe Zhang, Elias Bareinboim","year":"2018","venue":"The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Zhang et al., 2017a] Lu Zhang, Yongkai Wu, and Xintao Wu. Achieving Non-Discrimination in Data Release. In Proceedings of the 23rd ACM SIGKDD International Con- ference on Knowledge Discovery and Data Mining, Hali- fax, NS, Canada, August 13 -17, 2017, pages 1335-1344, New York, New York, USA, November 2017. ACM Press.","title":"Achieving Non-Discrimination in Data Release","authors":"Zhang","year":"2017","venue":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Zhang et al., 2017b] Lu Zhang, Yongkai Wu, and Xintao Wu. A Causal Framework for Discovering and Remov- ing Direct and Indirect Discrimination. In Proceedings of the Twenty-Sixth International Joint Conference on Artifi- cial Intelligence, IJCAI 2017, Melbourne, Australia, Au- gust 19-25, 2017, pages 3929-3935, California, August 2017. International Joint Conferences on Artificial Intelli- gence Organization.","title":"A Causal Framework for Discovering and Removing Direct and Indirect Discrimination","authors":"Zhang","year":"2017","venue":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017","doi":null,"url":null,"internal_url":"/proceedings/2017/549"},{"position":14,"raw":"[Zhang et al., 2018a] L. Zhang, Y. Wu, and X. Wu. Causal modeling-based discrimination discovery and removal: Criteria, bounds, and algorithms. IEEE Transactions on Knowledge and Data Engineering, pages 1-1, 2018.","title":"Causal modeling-based discrimination discovery and removal: Criteria, bounds, and algorithms","authors":"Zhang","year":"2018","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Zhang et al., 2018b] Lu Zhang, Yongkai Wu, and Xintao Wu. Achieving non-discrimination in prediction. In Pro- ceedings of the Twenty-Seventh International Joint Con- ference on Artificial Intelligence, IJCAI 2018, July 13-19, 2018, Stockholm, Sweden., pages 3097-3103, 2018.","title":"Achieving non-discrimination in prediction","authors":"Zhang","year":"2018","venue":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018","doi":null,"url":null,"internal_url":"/proceedings/2018/430"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}