{"type":"ScholarlyArticle","title":"A New Paradigm for Counterfactual Reasoning in Fairness and Recourse","authors":[{"name":"Lucius E.J. Bynum","slug":"lucius-e-j-bynum","given":"Lucius E.J.","family":"Bynum","affiliation":"New York University , Center for Data Science"},{"name":"Joshua R. Loftus","slug":"joshua-r-loftus","given":"Joshua R.","family":"Loftus","affiliation":"London School of Economics , Department of Statistics"},{"name":"Julia Stoyanovich","slug":"julia-stoyanovich","given":"Julia","family":"Stoyanovich","affiliation":"New York University , Center for Data Science; New York University , Tandon School of Engineering"}],"abstract":"Counterfactuals underpin numerous techniques for auditing and understanding artificial intelligence (AI) systems. The traditional paradigm for counterfactual reasoning in this literature is the interventional counterfactual, where hypothetical interventions are imagined and simulated. For this reason, the starting point for causal reasoning about legal protections and demographic data in AI is an imagined intervention on a legally-protected characteristic, such as ethnicity, race, gender, disability, age, etc. We ask, for example, what would have happened had your race been different? An inherent limitation of this paradigm is that some demographic interventions — like interventions on race — may not be well-defined or translate into the formalisms of interventional counterfactuals. In this work, we explore a new paradigm based instead on the backtracking counterfactual, where rather than imagine hypothetical interventions on legally-protected characteristics, we imagine alternate initial conditions while holding these characteristics fixed. We ask instead, what would explain a counterfactual outcome for you as you actually are or could be? This alternate framework allows us to address many of the same social concerns, but to do so while asking fundamentally different questions that do not rely on demographic interventions.","doi":"10.24963/ijcai.2024/784","url":"https://ijcai.org/proceedings/2024/784","pdf":"https://ijcai.org/proceedings/2024/0784.pdf","markdown":"https://ijcai.org/proceedings/2024/784.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/784","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Uncertainty in AI","track":"Main Track","number":784,"pages":{"first":7092,"last":7100},"keywords":["AI Ethics, Trust, Fairness: ETF: Moral decision making","Uncertainty in AI: UAI: Causality, structural causal models and causal inference","Machine Learning: ML: Causality","AI Ethics, Trust, Fairness: ETF: Fairness and diversity"],"videos":[],"references":[{"position":1,"raw":"[Balke and Pearl, 1994] Alexander Balke and Judea Pearl. Probabilistic evaluation of counterfactual queries. Prob- abilistic and Causal Inference, 1994.","title":"Probabilistic evaluation of counterfactual queries","authors":"Pearl ; Balke, Alexander Balke, Judea Pearl","year":"1994","venue":"Probabilistic and Causal Inference","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Barocas et al., 2023] Solon Barocas, Moritz Hardt, and Arvind Narayanan. Fairness and Machine Learning: Lim- itations and Opportunities. MIT Press, 2023.","title":"Fairness and Machine Learning: Limitations and Opportunities","authors":"Solon Barocas, Moritz Hardt, Arvind Narayanan","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Benthall and Haynes, 2019] Sebastian Benthall and Bruce D. Haynes. Racial categories in machine learning. In Proceedings of the Conference on Fairness, Account- ability, and Transparency, FAT* '19, page 289-298, New York, NY, USA, 2019. Association for Computing Machinery.","title":"Racial categories in machine learning","authors":"Sebastian Benthall, Bruce D Haynes","year":"2019","venue":"Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* '19","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bynum et al., 2021] Lucius E.J. Bynum, Joshua R. Loftus, and Julia Stoyanovich. Disaggregated interventions to re- duce inequality. Equity and Access in Algorithms, Mecha- nisms, and Optimization, 2021.","title":"Disaggregated interventions to reduce inequality","authors":"E J Lucius, Joshua R Bynum, Julia Loftus, Stoyanovich","year":"2021","venue":"Equity and Access in Algorithms, Mechanisms, and Optimization","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bynum et al., 2023] Lucius E. J. Bynum, Joshua R. Loftus, and Julia Stoyanovich. Counterfactuals for the future. Pro- ceedings of the AAAI Conference on Artificial Intelligence, 37(12):14144-14152, Jun. 2023.","title":"Counterfactuals for the future","authors":"E J Lucius, Joshua R Bynum, Julia Loftus, Stoyanovich","year":"2023","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Carey and Wu, 2022] Alycia N. Carey and Xintao Wu. The causal fairness field guide: Perspectives from social and formal sciences. Frontiers in Big Data, 5, 2022.","title":"The causal fairness field guide: Perspectives from social and formal sciences","authors":"Alycia N Carey, Xintao Wu","year":"2022","venue":"Frontiers in Big Data","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chiappa, 2018] Silvia Chiappa. Path-specific counterfactual fairness. In AAAI Conference on Artificial Intelligence, 2018.","title":"Path-specific counterfactual fairness","authors":"Silvia Chiappa","year":"2018","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ehyaei et al., 2023] Ahmad Reza Ehyaei, Amir-Hossein Karimi, Bernhard Schölkopf, and Setareh Maghsudi. Ro- bustness implies fairness in causal algorithmic recourse. Proceedings of the 2023 ACM Conference on Fairness, Ac- countability, and Transparency, 2023.","title":"Robustness implies fairness in causal algorithmic recourse","authors":"Reza Ahmad, Ehyaei, Amir-Hossein, Bernhard Karimi, Setareh Schölkopf, Maghsudi","year":"2023","venue":"Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hanna et al., 2020] Alex Hanna, Emily Denton, Andrew Smart, and Jamila Smith-Loud. Towards a critical race methodology in algorithmic fairness. In Proceedings of the 2020 Conference on Fairness, Accountability, and Trans- parency, FAT* '20, page 501-512, New York, NY, USA, 2020. Association for Computing Machinery.","title":"Towards a critical race methodology in algorithmic fairness","authors":"Alex Hanna, Emily Denton, Andrew Smart, Jamila Smith, -Loud","year":"2020","venue":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, FAT* '20","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Holland, 1986] Paul W. Holland. Statistics and causal in- ference. Journal of the American Statistical Association, 81(396):945-960, 1986.","title":"Statistics and causal inference","authors":"Paul W Holland","year":"1986","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hu and Kohler-Hausmann, 2020] Lily Hu and Issa Kohler- Hausmann. What's sex got to do with machine learning? In Proceedings of the 2020 Conference on Fairness, Ac- countability, and Transparency, FAT* '20, page 513, New York, NY, USA, 2020. Association for Computing Ma- chinery.","title":"What's sex got to do with machine learning?","authors":"Kohler-Hausmann ; Hu, Lily Hu, Issa Kohler-Hausmann","year":"2020","venue":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, FAT* '20","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Jacobs and Wallach, 2021] Abigail Z. Jacobs and Hanna Wallach. Measurement and Fairness, page 375-385. As- sociation for Computing Machinery, New York, NY, USA, 2021.","title":"Measurement and Fairness","authors":"Abigail Z Jacobs, Hanna Wallach","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Karimi et al., 2022] Amirhossein Karimi, Gilles Barthe, Bernhard Scholkopf, and Isabel Valera. A survey of al- gorithmic recourse: Contrastive explanations and conse- quential recommendations. ACM Computing Surveys, 55:1 -29, 2022.","title":"A survey of algorithmic recourse: Contrastive explanations and consequential recommendations","authors":"Karimi","year":"2022","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kasirzadeh and Smart, 2021] Atoosa Kasirzadeh and An- drew Smart. The use and misuse of counterfactuals in ethical machine learning. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Trans- parency, FAccT '21, page 228-236, New York, NY, USA, 2021. Association for Computing Machinery.","title":"Atoosa Kasirzadeh and Andrew Smart. The use and misuse of counterfactuals in ethical machine learning","authors":"Smart Kasirzadeh","year":"2021","venue":"Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, FAccT '21","doi":null,"url":null,"internal_url":null},{"position":15,"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. Advances in neural information processing systems, 30, 2017.","title":"Avoiding discrimination through causal reasoning","authors":"Niki Kilbertus, Mateo Rojas Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, Bernhard Schölkopf","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kusner et al., 2017] Matt J. Kusner, Joshua R. Loftus, Chris Russell, and Ricardo Silva. Counterfactual fairness. In Advances in neural information processing systems, 2017.","title":"Counterfactual fairness","authors":"Matt J Kusner, Joshua R Loftus, Chris Russell, Ricardo Silva","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Loftus et al., 2018] Joshua R. Loftus, Chris Russell, Matt J. Kusner, and Ricardo Silva. Causal reasoning for algorith- mic fairness. ArXiv, abs/1805.05859, 2018.","title":"Causal reasoning for algorithmic fairness","authors":"Joshua R Loftus, Chris Russell, Matt J Kusner, Ricardo Silva","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nabi and Shpitser, 2017] Razieh Nabi and Ilya Shpitser. Fair inference on outcomes. Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence, 2018:1931-1940, 2017.","title":"Razieh Nabi and Ilya Shpitser. Fair inference on outcomes","authors":"Shpitser Nabi","year":"2017","venue":"AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Pearl, 2000] Judea Pearl. Causality: Models, reasoning and inference. 2000.","title":"Judea Pearl. Causality: Models, reasoning and inference","authors":"Pearl","year":"2000","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Plecko and Bareinboim, 2022] Drago Plecko and Elias Bareinboim. Causal fairness analysis. ArXiv, abs/2207.11385, 2022.","title":"Causal fairness analysis","authors":"Drago Plecko, Elias Bareinboim","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sen and Wasow, 2016] M. Sen and Omar Wasow. Race as a Bundle of Sticks: Designs that Estimate Effects of Seem- ingly Immutable Characteristics. Annual Review of Politi- cal Science, 19:499-522, 2016.","title":"Race as a Bundle of Sticks: Designs that Estimate Effects of Seemingly Immutable Characteristics","authors":"M Sen, Omar Wasow","year":"2016","venue":"Annual Review of Political Science","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Von Kügelgen et al., 2022] Julius Von Kügelgen, Amir- Hossein Karimi, Umang Bhatt, Isabel Valera, Adrian Weller, and Bernhard Schölkopf. On the fairness of causal algorithmic recourse. In Proceedings of the AAAI con- ference on artificial intelligence, volume 36, pages 9584- 9594, 2022.","title":"On the fairness of causal algorithmic recourse","authors":"Von Kügelgen","year":"2022","venue":"Proceedings of the AAAI conference on artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Von Kügelgen et al., 2023] Julius Von Kügelgen, Abdirisak Mohamed, and Sander Beckers. Backtracking counterfac- tuals. In Conference on Causal Learning and Reasoning, pages 177-196. PMLR, 2023.","title":"Julius Von Kügelgen, Abdirisak Mohamed, and Sander Beckers. Backtracking counterfactuals","authors":"Von Kügelgen","year":"2023","venue":"Conference on Causal Learning and Reasoning","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wightman, 1998] Linda F. Wightman. Lsac national longi- tudinal bar passage study. lsac research report series. 1998.","title":"Lsac national longitudinal bar passage study","authors":"Linda F Wightman","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wu et al., 2019] Yongkai Wu, Lu Zhang, Xintao Wu, and Hanghang Tong. Pc-fairness: A unified framework for measuring causality-based fairness. In Neural Information Processing Systems, 2019.","title":"Pc-fairness: A unified framework for measuring causality-based fairness","authors":"Yongkai Wu, Lu Zhang, Xintao Wu, Hanghang Tong","year":"2019","venue":"Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang and Bareinboim, 2018] Junzhe Zhang and Elias Bareinboim. Fairness in decision-making -the causal explanation formula. In AAAI Conference on Artificial Intelligence, 2018.","title":"Fairness in decision-making -the causal explanation formula","authors":"Bareinboim Zhang, Junzhe Zhang, Elias Bareinboim","year":"2018","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}