On the Fairness of Causal Algorithmic Recourse
Open accessAbstract
Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we investigate fairness from the perspective of recourse actions suggested to individuals to remedy an unfavourable classification. We propose two new fair-ness criteria at the group and individual level, which—unlike prior work on equalising the average group-wise distance from the decision boundary—explicitly account for causal relationships between features, thereby capturing downstream effects of recourse actions performed in the physical world. We explore how our criteria relate to others, such as counterfactual fairness, and show that fairness of recourse is complementary to fairness of prediction. We study theoretically and empirically how to enforce fair causal recourse by altering the classifier and perform a case study on the Adult dataset. Finally, we discuss whether fairness violations in the data generating process revealed by our criteria may be better addressed by societal interventions as opposed to constraints on the classifier.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The recourse literature has evolved significantly, with work investigating robustness, fairness, and privacy risks of recourse.
“The recourse literature has evolved significantly over the years (Karimi et al. 2022), with work investigating the robustness (Upadhyay, Joshi, and Lakkaraju 2021;König et al. 2025), fairness (Von Kügelgen et al. 2022), and privacy risks (Pawelczyk, Lakkaraju, and Neel 2023) of recourse.”
From Explainable AI Isn't Enough! Rethinking Algorithmic Contestability (2026) · cites this paper as Von Kügelgen et al. 2022
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Fair prediction with disparate impact: a study of bias in recidivism prediction instruments
Chouldechova, A. (2017) · Big Data · doi:10.1089/big.2016.0047 · Cited by 2,159 · see citing works
Avoiding Discrimination through Causal Reasoning
Kilbertus, N., Rojas-Carulla, M., Parascandolo, G., Hardt, M., Janzing, D., & Schölkopf, B. (2017) · arXiv · doi:10.48550/arxiv.1706.02744 · Cited by 358 · see citing works
Self-citationSharma, S., Henderson, J., & Ghosh, J. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375812 · Cited by 226 · see citing works
Nabi, R., & Shpitser, I. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11553 · Cited by 20 · see citing works
Flagged first, then by citations
Research works printed but not linked: 41
- Arneson, R. 2015. Equality of Opportunity. In Zalta, E. N., ed., The Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University, Summer 2015 edition.
- Barocas, S.; Selbst, A. D.; and Raghavan, M. 2020. The hidden assumptions behind counterfactual explanations and principal reasons. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 80-89.
- Chiappa, S. 2019. Path-specific counterfactual fairness. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, 7801-7808.
- Dwork, C.; Hardt, M.; Pitassi, T.; Reingold, O.; and Zemel, R. 2012. Fairness through awareness. In Proceedings of the 3rd innovations in theoretical computer science conference, 214-226.
- Gretton, A.; Borgwardt, K. M.; Rasch, M. J.; Schölkopf, B.; and Smola, A. 2012. A kernel two-sample test. The Journal of Machine Learning Research, 13(1): 723-773.
- Grgić-Hlača, N.; Zafar, M. B.; Gummadi, K.; and Weller, A. 2017. On Fairness, Diversity, and Randomness in Al- gorithmic Decision Making. In 4th Workshop on Fairness, Accountability, and Transparency in Machine Learning.
- Gupta, V.; Nokhiz, P.; Roy, C. D.; and Venkatasubramanian, S. 2019. Equalizing Recourse across Groups. arXiv preprint arXiv:1909.03166. · arXiv
- Hardt, M.; Price, E.; and Srebro, N. 2016. Equality of oppor- tunity in supervised learning. In Advances in neural informa- tion processing systems, 3315-3323.
- Heckman, J. J. 2010. Building bridges between structural and program evaluation approaches to evaluating policy. Journal of Economic literature, 48(2): 356-98.
- Heckman, J. J.; and Vytlacil, E. 2005. Structural equa- tions, treatment effects, and econometric policy evaluation 1. Econometrica, 73(3): 669-738.
- Joshi, S.; Koyejo, O.; Vijitbenjaronk, W.; Kim, B.; and Ghosh, J. 2019. Towards realistic individual recourse and actionable explanations in black-box decision making systems. arXiv preprint arXiv:1907.09615. · arXiv
- Karimi, A.-H.; Barthe, G.; Balle, B.; and Valera, I. 2020a. Model-agnostic counterfactual explanations for consequen- tial decisions. In International Conference on Artificial Intel- ligence and Statistics, 895-905.
- Karimi, A.-H.; Barthe, G.; Schölkopf, B.; and Valera, I. 2020b. A survey of algorithmic recourse: definitions, formulations, solutions, and prospects. arXiv preprint arXiv:2010.04050. · arXiv
- Karimi, A.-H.; Schölkopf, B.; and Valera, I. 2021. Algo- rithmic recourse: from counterfactual explanations to inter- ventions. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 353-362.
- Karimi, A.-H.; von Kügelgen, J.; Schölkopf, B.; and Valera, I. 2020c. Algorithmic recourse under imperfect causal knowl- edge: a probabilistic approach. In Advances in Neural Infor- mation Processing Systems, volume 33, 265-277.
- Kingma, D. P.; and Welling, M. 2014. Auto-Encoding Varia- tional Bayes. In 2nd International Conference on Learning Representations.
- Kusner, M. J.; Loftus, J.; Russell, C.; and Silva, R. 2017. Counterfactual fairness. In Advances in Neural Information Processing Systems, 4066-4076.
- Loftus, J. R.; Russell, C.; Kusner, M. J.; and Silva, R. 2018. Causal reasoning for algorithmic fairness. arXiv preprint arXiv:1805.05859. · arXiv
- Mahajan, D.; Tan, C.; and Sharma, A. 2019. Preserving Causal Constraints in Counterfactual Explanations for Ma- chine Learning Classifiers. arXiv preprint arXiv:1912.03277. · arXiv
- Mothilal, R. K.; Sharma, A.; and Tan, C. 2020. Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 607-617.
- Nabi, R.; Malinsky, D.; and Shpitser, I. 2019. Learning optimal fair policies. In International Conference on Machine Learning, 4674-4682. PMLR.
- Pearl, J. 2009. Causality. Cambridge University Press.
- Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; et al. 2011. Scikit-learn: Machine learn- ing in Python. Journal of Machine Learning Research, 12: 2825-2830.
- Peters, J.; Janzing, D.; and Schölkopf, B. 2017. Elements of causal inference. MIT Press.
- Rezende, D. J.; Mohamed, S.; and Wierstra, D. 2014. Stochas- tic backpropagation and approximate inference in deep gen- erative models. In International Conference on Machine Learning, 1278-1286.
- PMLR.
- Russell, C.; Kusner, M. J.; Loftus, J.; and Silva, R. 2017. When worlds collide: integrating different counterfactual as- sumptions in fairness. In Advances in Neural Information Processing Systems, 6414-6423.
- Salimi, B.; Rodriguez, L.; Howe, B.; and Suciu, D. 2019. Interventional fairness: Causal database repair for algorithmic fairness. In Proceedings of the 2019 International Conference on Management of Data, 793-810.
- Schölkopf, B.; and Smola, A. J. 2002. Learning with Kernels. Cambridge, MA, USA: MIT Press.
- Sharma, S.; Henderson, J.; and Ghosh, J. 2019. CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models. arXiv preprint arXiv:1905.07857. · arXiv
- Sohn, K.; Lee, H.; and Yan, X. 2015. Learning structured output representation using deep conditional generative mod- els. Advances in Neural Information Processing Systems, 28: 3483-3491.
- Upadhyay, S.; Joshi, S.; and Lakkaraju, H. 2021. Towards Robust and Reliable Algorithmic Recourse. In Thirty-Fifth Conference on Neural Information Processing Systems.
- Ustun, B.; Spangher, A.; and Liu, Y. 2019. Actionable re- course in linear classification. In Proceedings of the Confer- ence on Fairness, Accountability, and Transparency, 10-19.
- Venkatasubramanian, S.; and Alfano, M. 2020. The philo- sophical basis of algorithmic recourse. In Proceedings of the 2020 Conference on Fairness, Accountability, and Trans- parency, 284-293.
- Wachter, S.; Mittelstadt, B.; and Russell, C. 2017. Counter- factual explanations without opening the black box: Auto- mated decisions and the GDPR. Harvard Journal of Law & Technology, 31(2).
- Wu, Y.; Zhang, L.; and Wu, X. 2019. Counterfactual fairness: Unidentification, bound and algorithm. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence.
- Wu, Y.; Zhang, L.; Wu, X.; and Tong, H. 2019. Pc-fairness: A unified framework for measuring causality-based fairness. In Advances in Neural Information Processing Systems, 3404- 3414.
- Zafar, M. B.; Valera, I.; Gomez Rodriguez, M.; and Gum- madi, K. P. 2017a. Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In Proceedings of the 26th International Con- ference on World Wide Web, 1171-1180.
- PMLR. Zemel, R.; Wu, Y.; Swersky, K.; Pitassi, T.; and Dwork, C. 2013. Learning fair representations. In International Confer- ence on Machine Learning, 325-333.
- Zhang, J.; and Bareinboim, E. 2018a. Equality of opportunity in classification: A causal approach. In Advances in Neural Information Processing Systems, 3671-3681.
- Zhang, J.; and Bareinboim, E. 2018b. Fairness in decision- making-the causal explanation formula. In Proceedings of the AAAI Conference on Artificial Intelligence.
Cited by
Sorted by citations
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
Verma, S., Boonsanong, V., Hoang, M., Hines, K. E., Dickerson, J. P., & Shah, C. (2020) · arXiv · doi:10.48550/arxiv.2010.10596 · Cited by 267 · see citing works
Explainable AI Isn't Enough! Rethinking Algorithmic Contestability
Freiesleben, T., Meding, K., & König, G. (2026) · arXiv · doi:10.48550/arxiv.2605.16041
- Authors
- Kügelgen, J. V., Karimi, A.-H., Bhatt, U., Valera, I., Weller, A., & Schölkopf, B.
- Affiliations
- University of Cambridge (GB)
- ETH Zurich (CH)
- Saarland University (DE)
- Max Planck Institute for Intelligent Systems (DE)
- ORCID
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2022-06-28
- Volume
- 36
- Issue
- 9
- Pages
- 9584-9594
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W3093469769
- Cited by
- 58
- References
- 4
- Citations by year
- 2026: 11 · 2025: 8 · 2024: 12 · 2023: 9 · 2022: 9 · 2021: 7 · 2020: 2
- FWCI
- 8.69
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Alan Turing Institute (EP/N510129/1., TU/B/000074, N510129)
- DeepMind
- Leverhulme Trust
- Bundesministerium für Bildung und Forschung (01IS18039B, FKZ: 01IS18039B)
- Mozilla Foundation
- Natural Sciences and Engineering Research Council of Canada
- Engineering and Physical Sciences Research Council (N510129, EP/N510129/, EP/N510129/1, TU/B/000074, EPSRC grant EP/N510129/1, 390727645)
- Topics
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- algorithmic fairness, algorithmic recourse, counterfactual fairness, fairness criteria, Adult dataset
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
