Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Bounding and Approximating Intersectional Fairness through Marginal Fairness (2206.05828v2)

Published 12 Jun 2022 in stat.ML and cs.LG

Abstract: Discrimination in machine learning often arises along multiple dimensions (a.k.a. protected attributes); it is then desirable to ensure \emph{intersectional fairness} -- i.e., that no subgroup is discriminated against. It is known that ensuring \emph{marginal fairness} for every dimension independently is not sufficient in general. Due to the exponential number of subgroups, however, directly measuring intersectional fairness from data is impossible. In this paper, our primary goal is to understand in detail the relationship between marginal and intersectional fairness through statistical analysis. We first identify a set of sufficient conditions under which an exact relationship can be obtained. Then, we prove bounds (easily computable through marginal fairness and other meaningful statistical quantities) in high-probability on intersectional fairness in the general case. Beyond their descriptive value, we show that these theoretical bounds can be leveraged to derive a heuristic improving the approximation and bounds of intersectional fairness by choosing, in a relevant manner, protected attributes for which we describe intersectional subgroups. Finally, we test the performance of our approximations and bounds on real and synthetic data-sets.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. Equal Credit Opportunity Act, 1974.
  2. Code du Travail. Chapitre II : Principe de non-discrimination, 2020.
  3. Bayesian entropy estimation for countable discrete distributions. Journal of Machine Learning Research, 15(1):2833–2868, 2014.
  4. Fairness and Machine Learning. fairmlbook.org, 2019. http://www.fairmlbook.org.
  5. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency (FAT*), volume 81, pages 77–91, 2018.
  6. Estimating total correlation with mutual information bounds. Available as arXiv:2011.04794, 2020.
  7. Alexandra Chouldechova. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big data, 5 2:153–163, 2017.
  8. Kimberle Crenshaw. Demarginalizing the intersection of race and sex: A black feminist critique of antidiscrimination doctrine, feminist theory and antiracist policies. University of Chicago Legal Forum, 1989(1):139–167, 1989.
  9. A. Dembo and O. Zeitouni. Large Deviations Techniques and Applications. Stochastic Modelling and Applied Probability. Springer Berlin Heidelberg, 2009.
  10. Minimax group fairness: Algorithms and experiments. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society (AIES), page 66–76, 2021.
  11. Uci machine learning repository, 2017.
  12. Fairness through awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference (ITCS), page 214–226, 2012.
  13. Bayesian modeling of intersectional fairness: The variance of bias. In Proceedings of the SIAM International Conference on Data Mining (SDM), 2020.
  14. An intersectional definition of fairness. In Proceedings of the 2020 IEEE 36th International Conference on Data Engineering (ICDE), pages 1918–1921, 2020.
  15. Minimax estimation of divergences between discrete distributions. IEEE Journal on Selected Areas in Information Theory, 1(3):814–823, 2020.
  16. Equality of opportunity in supervised learning. In Proceedings of the Thirtieth Conference on Neural Information Processing Systems (NeurIPS), 2016.
  17. Multicalibration: Calibration for the (Computationally-identifiable) masses. In Proceedings of the 35th International Conference on Machine Learning (ICML), pages 1939–1948, 2018.
  18. Can i trust my fairness metric? assessing fairness with unlabeled data and bayesian inference. In Proceedings of the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), pages 18600–18612, 2020.
  19. Minimax estimation of functionals of discrete distributions. IEEE Trans. Inf. Theor., 61(5):2835–2885, 2015.
  20. Maximum likelihood estimation of functionals of discrete distributions. IEEE Transactions on Information Theory, 63(10):6774–6798, 2017.
  21. Preventing fairness gerrymandering: Auditing and learning for subgroup fairness. In Proceedings of the 35th International Conference on Machine Learning (ICML), pages 2564–2572, 2018.
  22. An empirical study of rich subgroup fairness for machine learning. In Proceedings of the Conference on Fairness, Accountability, and Transparency (FAT*), page 100–109, 2019.
  23. Elena Kosygina. Introductory examples and definitions. cramér’s theorem, 2018. https://sites.math.northwestern.edu/~auffing/SNAP/Notes1.pdf.
  24. Minimax pareto fairness: A multi objective perspective. In Proceedings of the 37th International Conference on Machine Learning (ICML), pages 6755–6764, 2020.
  25. Fairness-aware learning for continuous attributes and treatments. In Proceedings of the 36th International Conference on Machine Learning (ICML), pages 4382–4391, 2019.
  26. Entropy and inference, revisited. In Proceedings of the Conference on Neural Information Processing Systems (NIPS), 2001.
  27. Liam Paninski. Estimation of entropy and mutual information. In Neural Computation, volume 15, pages 1191–1253, 2003.
  28. Achieving equalized odds by resampling sensitive attributes. In Proceedings of the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), pages 361–371, 2020.
  29. Satosi Watanabe. Information theoretical analysis of multivariate correlation. In IBM Journal of Research and Development, volume 4, pages 66–82, 1960.
  30. Learning non-discriminatory predictors. In Proceedings of the 2017 Conference on Learning Theory (COLT), pages 1920–1953, 2017.
  31. Fairness with overlapping groups; a probabilistic perspective. In Proceedings of the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), pages 4067–4078, 2020.
  32. Causal Intersectionality and Fair Ranking. In Proceedings of the 2nd Symposium on Foundations of Responsible Computing (FORC), pages 7:1–7:20, 2021.
  33. Fairness Constraints: Mechanisms for Fair Classification. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), pages 962–970, 2017.
  34. Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In Proceedings of the 26th International Conference on World Wide Web (WWW), page 1171–1180, 2017.
  35. Yiliang Zhang and Qi Long. Assessing fairness in the presence of missing data. In Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), pages 16007–16019, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Mathieu Molina (6 papers)
  2. Patrick Loiseau (44 papers)
Citations (7)
View on Semantic Scholar