Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 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

Monotone Individual Fairness (2403.06812v1)

Published 11 Mar 2024 in cs.LG, cs.CY, and stat.ML

Abstract: We revisit the problem of online learning with individual fairness, where an online learner strives to maximize predictive accuracy while ensuring that similar individuals are treated similarly. We first extend the frameworks of Gillen et al. (2018); Bechavod et al. (2020), which rely on feedback from human auditors regarding fairness violations, as we consider auditing schemes that are capable of aggregating feedback from any number of auditors, using a rich class we term monotone aggregation functions. We then prove a characterization for such auditing schemes, practically reducing the analysis of auditing for individual fairness by multiple auditors to that of auditing by (instance-specific) single auditors. Using our generalized framework, we present an oracle-efficient algorithm achieving an upper bound frontier of $(\mathcal{O}(T{1/2+2b}),\mathcal{O}(T{3/4-b}))$ respectively for regret, number of fairness violations, for $0\leq b \leq 1/4$. We then study an online classification setting where label feedback is available for positively-predicted individuals only, and present an oracle-efficient algorithm achieving an upper bound frontier of $(\mathcal{O}(T{2/3+2b}),\mathcal{O}(T{5/6-b}))$ for regret, number of fairness violations, for $0\leq b \leq 1/6$. In both settings, our algorithms improve on the best known bounds for oracle-efficient algorithms. Furthermore, our algorithms offer significant improvements in computational efficiency, greatly reducing the number of required calls to an (offline) optimization oracle per round, to $\tilde{\mathcal{O}}(\alpha{-2})$ in the full information setting, and $\tilde{\mathcal{O}}(\alpha{-2} + k2T{1/3})$ in the partial information setting, where $\alpha$ is the sensitivity for reporting fairness violations, and $k$ is the number of individuals in a round.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (54)
  1. A reductions approach to fair classification. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, pages 60–69.
  2. Metric-free individual fairness in online learning. In Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H., editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
  3. Individually fair learning with one-sided feedback. In Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., and Scarlett, J., editors, International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedings of Machine Learning Research, pages 1954–1977. PMLR.
  4. Online convex optimization with time-varying constraints and bandit feedback. IEEE Trans. Autom. Control., 64(7):2665–2680.
  5. A unifying framework for online optimization with long-term constraints. In Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., and Oh, A., editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022.
  6. How to use expert advice. J. ACM, 44(3):427–485.
  7. Bandit convex optimization for scalable and dynamic iot management. IEEE Internet Things J., 6(1):1276–1286.
  8. An online convex optimization approach to proactive network resource allocation. IEEE Trans. Signal Process., 65(24):6350–6364.
  9. Condorcet, N. d. (2014). Essai sur l’application de l’analyse à la probabilité des décisions rendues à la pluralité des voix. Cambridge Library Collection - Mathematics. Cambridge University Press.
  10. Characterizing fairness over the set of good models under selective labels. In Meila, M. and Zhang, T., editors, Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, volume 139 of Proceedings of Machine Learning Research, pages 2144–2155. PMLR.
  11. Learning under selective labels in the presence of expert consistency. CoRR, abs/1807.00905.
  12. The causes and consequences of test score manipulation: Evidence from the new york regents examinations. American Economic Journal: Applied Economics, 11(3):382–423.
  13. Is more information better? the effects of “report cards” on health care providers. Journal of Political Economy, 111(3):555–588.
  14. Fairness through awareness. In Goldwasser, S., editor, Innovations in Theoretical Computer Science 2012, Cambridge, MA, USA, January 8-10, 2012, pages 214–226. ACM.
  15. Runaway feedback loops in predictive policing. In Friedler, S. A. and Wilson, C., editors, Proceedings of the 1st Conference on Fairness, Accountability and Transparency, volume 81 of Proceedings of Machine Learning Research, pages 160–171. PMLR.
  16. Decision making with limited feedback. In Janoos, F., Mohri, M., and Sridharan, K., editors, Proceedings of Algorithmic Learning Theory, volume 83 of Proceedings of Machine Learning Research, pages 359–367. PMLR.
  17. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci., 55(1):119–139.
  18. Online learning with an unknown fairness metric. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3-8 December 2018, Montréal, Canada., pages 2605–2614.
  19. Slippery Fish: Enforcing Regulation under Subversive Adaptation. IZA Discussion Papers 12179, Institute of Labor Economics (IZA).
  20. Can technology solve the principal-agent problem? evidence from china’s war on air pollution. SSRN Electronic Journal.
  21. Individual fairness in hindsight. Journal of Machine Learning Research, 22(144):1–35.
  22. Apple tasting. Inf. Comput., 161(2):85–139.
  23. Ilvento, C. (2020). Metric learning for individual fairness. In Roth, A., editor, 1st Symposium on Foundations of Responsible Computing, FORC 2020, June 1-3, 2020, Harvard University, Cambridge, MA, USA (virtual conference), volume 156 of LIPIcs, pages 2:1–2:11. Schloss Dagstuhl - Leibniz-Zentrum für Informatik.
  24. Adaptive algorithms for online convex optimization with long-term constraints. In Balcan, M. F. and Weinberger, K. Q., editors, Proceedings of The 33rd International Conference on Machine Learning, volume 48 of Proceedings of Machine Learning Research, pages 402–411, New York, New York, USA. PMLR.
  25. Meritocratic fairness for infinite and contextual bandits. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, AIES 2018, New Orleans, LA, USA, February 02-03, 2018, pages 158–163.
  26. Fairness in learning: Classic and contextual bandits. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain, pages 325–333.
  27. An algorithmic framework for fairness elicitation. In Ligett, K. and Gupta, S., editors, 2nd Symposium on Foundations of Responsible Computing, FORC 2021, June 9-11, 2021, Virtual Conference, volume 192 of LIPIcs, pages 2:1–2:19. Schloss Dagstuhl - Leibniz-Zentrum für Informatik.
  28. Fairness through computationally-bounded awareness. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3-8 December 2018, Montréal, Canada, pages 4847–4857.
  29. Operationalizing individual fairness with pairwise fair representations. Proc. VLDB Endow., 13(4):506–518.
  30. The selective labels problem: Evaluating algorithmic predictions in the presence of unobservables. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada, August 13 - 17, 2017, pages 275–284. ACM.
  31. Learning cost-effective and interpretable treatment regimes. In Singh, A. and Zhu, X. J., editors, Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017, 20-22 April 2017, Fort Lauderdale, FL, USA, volume 54 of Proceedings of Machine Learning Research, pages 166–175. PMLR.
  32. Cautious regret minimization: Online optimization with long-term budget constraints. In Chaudhuri, K. and Salakhutdinov, R., editors, Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pages 3944–3952. PMLR.
  33. The weighted majority algorithm. Inf. Comput., 108(2):212–261.
  34. Trading regret for efficiency: Online convex optimization with long term constraints. Journal of Machine Learning Research, 13(81):2503–2528.
  35. Online learning with sample path constraints. J. Mach. Learn. Res., 10:569–590.
  36. Two simple ways to learn individual fairness metrics from data. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, volume 119 of Proceedings of Machine Learning Research, pages 7097–7107. PMLR.
  37. How to use heuristics for differential privacy. In Zuckerman, D., editor, 60th IEEE Annual Symposium on Foundations of Computer Science, FOCS 2019, Baltimore, Maryland, USA, November 9-12, 2019, pages 72–93. IEEE Computer Society.
  38. Frequency of monotonicity failure under instant runoff voting: Estimates based on a spatial model of elections. Public Choice, 161.
  39. Probably approximately metric-fair learning. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, pages 5666–5674.
  40. Safety-aware algorithms for adversarial contextual bandit. In Precup, D. and Teh, Y. W., editors, Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 3280–3288. PMLR.
  41. Efficient algorithms for adversarial contextual learning. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016, pages 2159–2168.
  42. Individually fair gradient boosting. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021.
  43. Vovk, V. G. (1990). Aggregating strategies. In Fulk, M. A. and Case, J., editors, Proceedings of the Third Annual Workshop on Computational Learning Theory, COLT 1990, University of Rochester, Rochester, NY, USA, August 6-8, 1990, pages 371–386. Morgan Kaufmann.
  44. Online primal-dual mirror descent under stochastic constraints. Proc. ACM Meas. Anal. Comput. Syst., 4(2).
  45. Woodall, D. R. (1997). Monotonicity of single-seat preferential election rules. Discrete Applied Mathematics, 77(1):81–98.
  46. Distributed online convex optimization with time-varying coupled inequality constraints. IEEE Trans. Signal Process., 68:731–746.
  47. A low complexity algorithm with o(T𝑇\sqrt{T}square-root start_ARG italic_T end_ARG) regret and o(1) constraint violations for online convex optimization with long term constraints. Journal of Machine Learning Research, 21(1):1–24.
  48. Online convex optimization with stochastic constraints. In Guyon, I., von Luxburg, U., Bengio, S., Wallach, H. M., Fergus, R., Vishwanathan, S. V. N., and Garnett, R., editors, Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 1428–1438.
  49. Online convex optimization for cumulative constraints. In Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., and Garnett, R., editors, Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc.
  50. Training individually fair ML models with sensitive subspace robustness. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net.
  51. Sensei: Sensitive set invariance for enforcing individual fairness. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021.
  52. Interpretable classification models for recidivism prediction. Journal of the Royal Statistical Society Series A, 180(3):689–722.
  53. Matrix estimation for individual fairness. In Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., and Scarlett, J., editors, International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedings of Machine Learning Research, pages 40871–40887. PMLR.
  54. Zinkevich, M. (2003). Online convex programming and generalized infinitesimal gradient ascent. In Fawcett, T. and Mishra, N., editors, Machine Learning, Proceedings of the Twentieth International Conference (ICML 2003), August 21-24, 2003, Washington, DC, USA, pages 928–936. AAAI Press.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (1)
  1. Yahav Bechavod (7 papers)

Summary

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

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

Tweets