Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk Minimization Framework (2309.11682v1)

Published 20 Sep 2023 in cs.LG, cs.AI, cs.CY, and stat.ML

Abstract: While training fair machine learning models has been studied extensively in recent years, most developed methods rely on the assumption that the training and test data have similar distributions. In the presence of distribution shifts, fair models may behave unfairly on test data. There have been some developments for fair learning robust to distribution shifts to address this shortcoming. However, most proposed solutions are based on the assumption of having access to the causal graph describing the interaction of different features. Moreover, existing algorithms require full access to data and cannot be used when small batches are used (stochastic/batch implementation). This paper proposes the first stochastic distributionally robust fairness framework with convergence guarantees that do not require knowledge of the causal graph. More specifically, we formulate the fair inference in the presence of the distribution shift as a distributionally robust optimization problem under $L_p$ norm uncertainty sets with respect to the Exponential Renyi Mutual Information (ERMI) as the measure of fairness violation. We then discuss how the proposed method can be implemented in a stochastic fashion. We have evaluated the presented framework's performance and efficiency through extensive experiments on real datasets consisting of distribution shifts.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (77)
  1. Convolutional neural networks for speech recognition. IEEE/ACM Transactions on audio, speech, and language processing, 22(10):1533–1545, 2014.
  2. C. R. Act. Civil rights act of 1964. Title VII, Equal Employment Opportunities, 1964.
  3. Transferring fairness under distribution shifts via fair consistency regularization. arXiv preprint arXiv:2206.12796, 2022.
  4. Machine bias. In Ethics of Data and Analytics, pages 254–264. Auerbach Publications, 2016.
  5. Rényi fair inference. In International Conference on Learning Representations, 2019.
  6. RIFLE: Imputation and robust inference from low order marginals. Transactions on Machine Learning Research, 2023. ISSN 2835-8856. URL https://openreview.net/forum?id=oud7Ny0KQy.
  7. Analysis of representations for domain adaptation. Advances in neural information processing systems, 19, 2006.
  8. A theory of learning from different domains. Machine learning, 79(1):151–175, 2010.
  9. Data-driven optimal transport cost selection for distributionally robust optimization. In 2019 winter simulation conference (WSC), pages 3740–3751. IEEE, 2019.
  10. J. Buolamwini and T. Gebru. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency, pages 77–91. PMLR, 2018.
  11. A fair classifier using kernel density estimation. Advances in neural information processing systems, 33:15088–15099, 2020.
  12. Flexibly fair representation learning by disentanglement. In International conference on machine learning, pages 1436–1445. PMLR, 2019.
  13. J. Dai and S. M. Brown. Label bias, label shift: Fair machine learning with unreliable labels. In NeurIPS 2020 Workshop on Consequential Decision Making in Dynamic Environments, volume 12, 2020.
  14. The complexity of constrained min-max optimization. In Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing, pages 1466–1478, 2021.
  15. E. Delage and Y. Ye. Distributionally robust optimization under moment uncertainty with application to data-driven problems. Operations research, 58(3):595–612, 2010.
  16. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018.
  17. Retiring adult: New datasets for fair machine learning. Advances in Neural Information Processing Systems, 34:6478–6490, 2021.
  18. Empirical risk minimization under fairness constraints. Advances in Neural Information Processing Systems, 31, 2018.
  19. W. Du and X. Wu. Fair and robust classification under sample selection bias. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pages 2999–3003, 2021.
  20. D. Dua and C. Graff. UCI machine learning repository, 2017. URL http://archive.ics.uci.edu/ml.
  21. Fairness through awareness. In Proceedings of the 3rd innovations in theoretical computer science conference, pages 214–226, 2012.
  22. Rethinking importance weighting for deep learning under distribution shift. Advances in Neural Information Processing Systems, 33:11996–12007, 2020.
  23. R. Gao and A. J. Kleywegt. Distributionally robust stochastic optimization with dependence structure. arXiv preprint arXiv:1701.04200, 2017.
  24. H. Gebelein. Das statistische problem der korrelation als variations-und eigenwertproblem und sein zusammenhang mit der ausgleichsrechnung. ZAMM-Journal of Applied Mathematics and Mechanics/Zeitschrift für Angewandte Mathematik und Mechanik, 21(6):364–379, 1941.
  25. Fairness-aware neural r\\\backslash\’eyni minimization for continuous features. arXiv preprint arXiv:1911.04929, 2019.
  26. Equality of opportunity in supervised learning. Advances in neural information processing systems, 29, 2016.
  27. H. O. Hirschfeld. A connection between correlation and contingency. In Mathematical Proceedings of the Cambridge Philosophical Society, volume 31, pages 520–524. Cambridge University Press, 1935.
  28. What is local optimality in nonconvex-nonconcave minimax optimization? In International conference on machine learning, pages 4880–4889. PMLR, 2020.
  29. Towards fair knowledge transfer for imbalanced domain adaptation. IEEE Transactions on Image Processing, 30:8200–8211, 2021.
  30. From gradient flow on population loss to learning with stochastic gradient descent. arXiv preprint arXiv:2210.06705, 2022.
  31. M. Khalafi and D. Boob. Accelerated primal-dual methods for convex-strongly-concave saddle point problems. In A. Krause, E. Brunskill, K. Cho, B. Engelhardt, S. Sabato, and J. Scarlett, editors, Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages 16250–16270. PMLR, 23–29 Jul 2023.
  32. Multiaccuracy: Black-box post-processing for fairness in classification. In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pages 247–254, 2019.
  33. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90, 2017.
  34. Wasserstein distributionally robust optimization: Theory and applications in machine learning. In Operations research & management science in the age of analytics, pages 130–166. Informs, 2019.
  35. Impossibility results for fair representations. arXiv preprint arXiv:2107.03483, 2021.
  36. First-order methods almost always avoid strict saddle points. Mathematical programming, 176(1):311–337, 2019.
  37. Large-scale methods for distributionally robust optimization. Advances in Neural Information Processing Systems, 33:8847–8860, 2020.
  38. Overfitting of neural nets under class imbalance: Analysis and improvements for segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 402–410. Springer, 2019.
  39. Distributionally robust optimization: A review on theory and applications. Numerical Algebra, Control & Optimization, 12(1):159, 2022.
  40. 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.
  41. A stochastic optimization framework for fair risk minimization. Transaction on Machine Learning Research (TMLR), 2022.
  42. Fairness-aware learning for continuous attributes and treatments. In International Conference on Machine Learning, pages 4382–4391. PMLR, 2019.
  43. A unifying view on dataset shift in classification. Pattern recognition, 45(1):521–530, 2012.
  44. A. Narayanan. Translation tutorial: 21 fairness definitions and their politics. In Proc. Conf. Fairness Accountability Transp., New York, USA, volume 1170, page 3, 2018.
  45. Explainable program synthesis by localizing specifications. Proceedings of the ACM on Programming Languages, 2023.
  46. Robust stochastic approximation approach to stochastic programming. SIAM Journal on optimization, 19(4):1574–1609, 2009.
  47. Exploiting mmd and sinkhorn divergences for fair and transferable representation learning. Advances in Neural Information Processing Systems, 33:15360–15370, 2020.
  48. B. T. Polyak. New stochastic approximation type procedures. Automat. i Telemekh, 7(98-107):2, 1990.
  49. Toward a better trade-off between performance and fairness with kernel-based distribution matching. arXiv preprint arXiv:1910.11779, 2019.
  50. H. Rahimian and S. Mehrotra. Distributionally robust optimization: A review. arXiv preprint arXiv:1908.05659, 2019.
  51. Nonconvex min-max optimization: Applications, challenges, and recent theoretical advances. IEEE Signal Processing Magazine, 37(5):55–66, 2020.
  52. Do cifar-10 classifiers generalize to cifar-10? arXiv preprint arXiv:1806.00451, 2018.
  53. Do imagenet classifiers generalize to imagenet? In International Conference on Machine Learning, pages 5389–5400. PMLR, 2019.
  54. A. Rényi. On measures of dependence. Acta mathematica hungarica, 10(3-4):441–451, 1959.
  55. Fairness for robust log loss classification. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 5511–5518, 2020.
  56. Robust fairness under covariate shift. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 9419–9427, 2021.
  57. Optimization of conditional value-at-risk. Journal of risk, 2:21–42, 2000.
  58. Fr-train: A mutual information-based approach to fair and robust training. In International Conference on Machine Learning, pages 8147–8157. PMLR, 2020.
  59. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. arXiv preprint arXiv:1911.08731, 2019.
  60. Automated identification of social media bots using deepfake text detection. In International Conference on Information Systems Security, pages 111–123. Springer, 2021.
  61. Maintaining fairness across distribution shift: do we have viable solutions for real-world applications? arXiv preprint arXiv:2202.01034, 2022.
  62. Lectures on stochastic programming: modeling and theory. SIAM, 2021.
  63. Fair predictors under distribution shift. In NeurIPS Workshop on Fair ML for Health, 2019.
  64. M. Sion. On general minimax theorems. Pacific Journal of mathematics, 8(1):171–176, 1958.
  65. Efficientdet: Scalable and efficient object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10781–10790, 2020.
  66. A distributionally robust approach to fair classification. arXiv preprint arXiv:2007.09530, 2020.
  67. Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474, 2014.
  68. Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models. In Chi conference on human factors in computing systems extended abstracts, pages 1–7, 2022.
  69. How robust is your fairness? evaluating and sustaining fairness under unseen distribution shifts. arXiv preprint arXiv:2207.01168, 2022.
  70. Distributionally robust convex optimization. Operations Research, 62(6):1358–1376, 2014.
  71. H. S. Witsenhausen. On sequences of pairs of dependent random variables. SIAM Journal on Applied Mathematics, 28(1):100–113, 1975.
  72. Robustness and regularization of support vector machines. Journal of machine learning research, 10(7), 2009.
  73. From parity to preference-based notions of fairness in classification. Advances in Neural Information Processing Systems, 30, 2017a.
  74. Fairness constraints: Mechanisms for fair classification. In Artificial intelligence and statistics, pages 962–970. PMLR, 2017b.
  75. Learning fair representations. In International conference on machine learning, pages 325–333. PMLR, 2013.
  76. Examining and combating spurious features under distribution shift. In International Conference on Machine Learning, pages 12857–12867. PMLR, 2021.
  77. Distributionally robust joint chance constraints with second-order moment information. Mathematical Programming, 137(1):167–198, 2013.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Sina Baharlouei (8 papers)
  2. Meisam Razaviyayn (76 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now