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

Striking a Balance in Fairness for Dynamic Systems Through Reinforcement Learning (2401.06318v1)

Published 12 Jan 2024 in cs.LG and cs.AI

Abstract: While significant advancements have been made in the field of fair machine learning, the majority of studies focus on scenarios where the decision model operates on a static population. In this paper, we study fairness in dynamic systems where sequential decisions are made. Each decision may shift the underlying distribution of features or user behavior. We model the dynamic system through a Markov Decision Process (MDP). By acknowledging that traditional fairness notions and long-term fairness are distinct requirements that may not necessarily align with one another, we propose an algorithmic framework to integrate various fairness considerations with reinforcement learning using both pre-processing and in-processing approaches. Three case studies show that our method can strike a balance between traditional fairness notions, long-term fairness, and utility.

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 (42)
  1. K. D. Johnson, D. P. Foster, and R. A. Stine, “Impartial predictive modeling: Ensuring fairness in arbitrary models,” Statistical Science, p. 1, 2016.
  2. R. S. Baker and A. Hawn, “Algorithmic bias in education,” International Journal of Artificial Intelligence in Education, pp. 1–41, 2021.
  3. L. Zhang, Y. Wu, and X. Wu, “Achieving non-discrimination in data release,” Proceedings of ACM SIGKDD’17, 2017.
  4. M. S. A. Lee and L. Floridi, “Algorithmic fairness in mortgage lending: from absolute conditions to relational trade-offs,” Minds and Machines, vol. 31, no. 1, pp. 165–191, 2021.
  5. C. Schumann, J. Foster, N. Mattei, and J. Dickerson, “We need fairness and explainability in algorithmic hiring,” in International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2020.
  6. R. Berk, H. Heidari, S. Jabbari, M. Kearns, and A. Roth, “Fairness in criminal justice risk assessments: The state of the art,” Sociological Methods & Research, vol. 50, no. 1, pp. 3–44, 2021.
  7. Y. Li, H. Chen, S. Xu, Y. Ge, J. Tan, S. Liu, and Y. Zhang, “Fairness in recommendation: A survey,” arXiv preprint arXiv:2205.13619, 2022.
  8. Z. Tang, J. Zhang, and K. Zhang, “What-is and how-to for fairness in machine learning: A survey, reflection, and perspective,” arXiv preprint arXiv:2206.04101, 2022.
  9. D. Pessach and E. Shmueli, “A review on fairness in machine learning,” ACM Computing Surveys (CSUR), vol. 55, no. 3, pp. 1–44, 2022.
  10. G. Alves, F. Bernier, M. Couceiro, K. Makhlouf, C. Palamidessi, and S. Zhioua, “Survey on fairness notions and related tensions,” EURO Journal on Decision Processes, p. 100033, 2023.
  11. L. T. Liu, S. Dean, E. Rolf, M. Simchowitz, and M. Hardt, “Delayed impact of fair machine learning,” in Proceedings of ICML’18, ser. Proceedings of Machine Learning Research, J. G. Dy and A. Krause, Eds., vol. 80.   PMLR, 2018, pp. 3156–3164.
  12. D. Ensign, S. A. Friedler, S. Neville, C. Scheidegger, and S. Venkatasubramanian, “Runaway feedback loops in predictive policing,” in Conference on Fairness, Accountability and Transparency.   PMLR, 2018, pp. 160–171.
  13. L. T. Liu, S. Dean, E. Rolf, M. Simchowitz, and M. Hardt, “Delayed impact of fair machine learning,” in International Conference on Machine Learning.   PMLR, 2018, pp. 3150–3158.
  14. X. Zhang, R. Tu, Y. Liu, M. Liu, H. Kjellstrom, K. Zhang, and C. Zhang, “How do fair decisions fare in long-term qualification?” Advances in Neural Information Processing Systems, vol. 33, pp. 18 457–18 469, 2020.
  15. S. Jabbari, M. Joseph, M. Kearns, J. Morgenstern, and A. Roth, “Fairness in reinforcement learning,” in International Conference on Machine Learning.   PMLR, 2017, pp. 1617–1626.
  16. A. D’Amour, H. Srinivasan, J. Atwood, P. Baljekar, D. Sculley, and Y. Halpern, “Fairness is not static: deeper understanding of long term fairness via simulation studies,” in Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 2020, pp. 525–534.
  17. J. Atwood, H. Srinivasan, Y. Halpern, and D. Sculley, “Fair treatment allocations in social networks,” arXiv preprint arXiv:1911.05489, 2019.
  18. E. Y. Yu, Z. Qin, M. K. Lee, and S. Gao, “Policy optimization with advantage regularization for long-term fairness in decision systems,” NeurIPS, 2022.
  19. M. Wen, O. Bastani, and U. Topcu, “Algorithms for fairness in sequential decision making,” in International Conference on Artificial Intelligence and Statistics.   PMLR, 2021, pp. 1144–1152.
  20. L. Hu and Y. Chen, “A short-term intervention for long-term fairness in the labor market,” in Proceedings of the 2018 World Wide Web Conference, 2018, pp. 1389–1398.
  21. F. Kamiran and T. Calders, “Classifying without discriminating,” in 2009 2nd international conference on computer, control and communication.   IEEE, 2009, pp. 1–6.
  22. A. Bower, S. N. Kitchen, L. Niss, M. J. Strauss, A. Vargas, and S. Venkatasubramanian, “Fair pipelines,” arXiv preprint arXiv:1707.00391, 2017.
  23. C. Dwork and C. Ilvento, “Fairness under composition,” arXiv preprint arXiv:1806.06122, 2018.
  24. E. Creager, D. Madras, T. Pitassi, and R. Zemel, “Causal modeling for fairness in dynamical systems,” in International Conference on Machine Learning.   PMLR, 2020, pp. 2185–2195.
  25. Y. Hu, Y. Wu, L. Zhang, and X. Wu, “Fair multiple decision making through soft interventions,” Advances in Neural Information Processing Systems, vol. 33, pp. 17 965–17 975, 2020.
  26. Y. Hu and L. Zhang, “Achieving long-term fairness in sequential decision making,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, 2022, pp. 9549–9557.
  27. Y. Ge, S. Liu, R. Gao, Y. Xian, Y. Li, X. Zhao, C. Pei, F. Sun, J. Ge, W. Ou et al., “Towards long-term fairness in recommendation,” in Proceedings of the 14th ACM International Conference on Web Search and Data Mining, 2021, pp. 445–453.
  28. F. Kamiran and T. Calders, “Data preprocessing techniques for classification without discrimination,” Knowledge and Information Systems, vol. 33, no. 1, pp. 1–33, 2012.
  29. M. Feldman, S. A. Friedler, J. Moeller, C. Scheidegger, and S. Venkatasubramanian, “Certifying and removing disparate impact,” in proceedings of ACM SIGKDD’15, 2015, pp. 259–268.
  30. D. Xu, S. Yuan, L. Zhang, and X. Wu, “Fairgan: Fairness-aware generative adversarial networks,” in 2018 IEEE International Conference on Big Data (Big Data).   IEEE, 2018, pp. 570–575.
  31. N. Quadrianto and V. Sharmanska, “Recycling privileged learning and distribution matching for fairness,” Advances in neural information processing systems, vol. 30, 2017.
  32. M. P. Kim, A. Korolova, G. N. Rothblum, and G. Yona, “Preference-informed fairness,” arXiv preprint arXiv:1904.01793, 2019.
  33. M. B. Zafar, I. Valera, M. Rodriguez, K. Gummadi, and A. Weller, “From parity to preference-based notions of fairness in classification,” Advances in neural information processing systems, vol. 30, 2017.
  34. M. Hardt, E. Price, and N. Srebro, “Equality of opportunity in supervised learning,” in NIPS, 2016.
  35. S. Corbett-Davies, E. Pierson, A. Feller, S. Goel, and A. Huq, “Algorithmic decision making and the cost of fairness,” in Proceedings of the 23rd acm sigkdd international conference on knowledge discovery and data mining, 2017, pp. 797–806.
  36. A. K. Menon and R. C. Williamson, “The cost of fairness in binary classification,” in Conference on Fairness, accountability and transparency.   PMLR, 2018, pp. 107–118.
  37. J. Schulman, P. Moritz, S. Levine, M. Jordan, and P. Abbeel, “High-dimensional continuous control using generalized advantage estimation,” arXiv preprint arXiv:1506.02438, 2015.
  38. R. S. Sutton, D. McAllester, S. Singh, and Y. Mansour, “Policy gradient methods for reinforcement learning with function approximation,” Advances in neural information processing systems, vol. 12, 1999.
  39. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” arXiv preprint arXiv:1707.06347, 2017.
  40. J. Schulman, S. Levine, P. Abbeel, M. Jordan, and P. Moritz, “Trust region policy optimization,” in International conference on machine learning.   PMLR, 2015, pp. 1889–1897.
  41. S. Barocas, M. Hardt, and A. Narayanan, “Fairness in machine learning,” Nips tutorial, vol. 1, p. 2017, 2017.
  42. M. Girvan and M. E. Newman, “Community structure in social and biological networks,” Proceedings of the national academy of sciences, vol. 99, no. 12, pp. 7821–7826, 2002.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Yaowei Hu (4 papers)
  2. Jacob Lear (2 papers)
  3. Lu Zhang (373 papers)
Citations (1)
View on Semantic Scholar