On the (In)Compatibility between Group Fairness and Individual Fairness (2401.07174v1)
Abstract: We study the compatibility between the optimal statistical parity solutions and individual fairness. While individual fairness seeks to treat similar individuals similarly, optimal statistical parity aims to provide similar treatment to individuals who share relative similarity within their respective sensitive groups. The two fairness perspectives, while both desirable from a fairness perspective, often come into conflict in applications. Our goal in this work is to analyze the existence of this conflict and its potential solution. In particular, we establish sufficient (sharp) conditions for the compatibility between the optimal (post-processing) statistical parity $L2$ learning and the ($K$-Lipschitz or $(\epsilon,\delta)$) individual fairness requirements. Furthermore, when there exists a conflict between the two, we first relax the former to the Pareto frontier (or equivalently the optimal trade-off) between $L2$ error and statistical disparity, and then analyze the compatibility between the frontier and the individual fairness requirements. Our analysis identifies regions along the Pareto frontier that satisfy individual fairness requirements. (Lastly, we provide individual fairness guarantees for the composition of a trained model and the optimal post-processing step so that one can determine the compatibility of the post-processed model.) This provides practitioners with a valuable approach to attain Pareto optimality for statistical parity while adhering to the constraints of individual fairness.
- M. Agueh and G. Carlier. Barycenters in the Wasserstein space. SIAM Journal on Mathematical Analysis, 43(2):904–924, 2011.
- A convex framework for fair regression. arXiv preprint arXiv:1706.02409, 2017.
- R. Binns. On the apparent conflict between individual and group fairness. In Proceedings of the 2020 conference on fairness, accountability, and transparency, pages 514–524, 2020.
- Y. Brenier. Polar factorization and monotone rearrangement of vector-valued functions. Communications on pure and applied mathematics, 44(4):375–417, 1991.
- Optimized pre-processing for discrimination prevention. Advances in neural information processing systems, 30, 2017.
- A. Chouldechova and A. Roth. The frontiers of fairness in machine learning. arXiv preprint arXiv:1810.08810, 2018.
- Fair regression with Wasserstein barycenters. Advances in Neural Information Processing Systems, 33:7321–7331, 2020.
- S. Corbett-Davies and S. Goel. The measure and mismeasure of fairness: A critical review of fair machine learning. arXiv preprint arXiv:1808.00023, 2018.
- Fairness through awareness. In Proceedings of the 3rd innovations in theoretical computer science conference, pages 214–226, 2012.
- W. Fleisher. What’s fair about individual fairness? In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pages 480–490, 2021.
- The (im) possibility of fairness: Different value systems require different mechanisms for fair decision making. Communications of the ACM, 64(4):136–143, 2021.
- W. Gangbo and A. Swiech. Optimal maps for the multidimensional monge-kantorovich problem. Communications on Pure and Applied Mathematics: A Journal Issued by the Courant Institute of Mathematical Sciences, 51(1):23–45, 1998.
- Projection to fairness in statistical learning. arXiv preprint arXiv:2005.11720, 2020.
- Equality of opportunity in supervised learning. Advances in neural information processing systems, 29, 2016.
- Multicalibration: Calibration for the (computationally-identifiable) masses. In International Conference on Machine Learning, pages 1939–1948. PMLR, 2018.
- Wasserstein fair classification. In Uncertainty in artificial intelligence, pages 862–872. PMLR, 2020.
- Fairness in learning: Classic and contextual bandits. Advances in neural information processing systems, 29, 2016.
- F. Kamiran and T. Calders. Data preprocessing techniques for classification without discrimination. Knowledge and information systems, 33(1):1–33, 2012.
- Preventing fairness gerrymandering: Auditing and learning for subgroup fairness. In International conference on machine learning, pages 2564–2572. PMLR, 2018.
- T. Le Gouic and J.-M. Loubes. Existence and consistency of Wasserstein barycenters. Probability Theory and Related Fields, 168:901–917, 2017.
- Bias mitigation post-processing for individual and group fairness. In Icassp 2019-2019 ieee international conference on acoustics, speech and signal processing (icassp), pages 2847–2851. IEEE, 2019.
- R. J. McCann. A convexity principle for interacting gases. Advances in mathematics, 128(1):153–179, 1997.
- Minimum width for universal approximation. arXiv preprint arXiv:2006.08859, 2020.
- M. Redmond and A. Baveja. A data-driven software tool for enabling cooperative information sharing among police departments. European Journal of Operational Research, 141(3):660–678, 2002.
- F. Santambrogio. Optimal transport for applied mathematicians. Birkäuser, NY, 55(58-63):94, 2015.
- A general approach to fairness with optimal transport. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34(04), pages 3633–3640, 2020.
- L. F. Wightman. LSAC National Longitudinal Bar Passage Study. LSAC Research Report Series. 1998.
- S. Xu and T. Strohmer. Fair data representation for machine learning at the Pareto frontier. Journal of Machine Learning Research, 24(331):1–63, 2023. URL http://jmlr.org/papers/v24/22-0005.html.
- Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In Proceedings of the 26th international conference on world wide web, pages 1171–1180, 2017.
- Learning fair representations. In International conference on machine learning, pages 325–333. PMLR, 2013.
- H. Zhao and G. J. Gordon. Inherent tradeoffs in learning fair representations. The Journal of Machine Learning Research, 23(1):2527–2552, 2022.
- W. Zhou. Group vs. individual algorithmic fairness. PhD thesis, University of Southampton, 2022.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.