mlsanityData to 7 Oct 2026

Designing Long-term Group Fair Policies in Dynamical Systems

arXiv 2311.12447 ↗First posted 21 Nov 2023cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Neglecting the effect that decisions have on individuals (and thus, on the underlying data distribution) when designing algorithmic decision-making policies may increase inequalities and unfairness in the long term - even if fairness considerations were taken in the policy design process. In this paper, we propose a novel framework for achieving long-term group fairness in dynamical systems, in which current decisions may affect an individual's features in the next step, and thus, future decisions. Specifically, our framework allows us to identify a time-independent policy that converges, if deployed, to the targeted fair stationary state of the system in the long term, independently of the initial data distribution. We model the system dynamics with a time-homogeneous Markov chain and optimize the policy leveraging the Markov chain convergence theorem to ensure unique convergence. We provide examples of different targeted fair states of the system, encompassing a range of long-term goals for society and policymakers. Furthermore, we show how our approach facilitates the evaluation of different long-term targets by examining their impact on the group-conditional population distribution in the long term and how it evolves until convergence.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 53 of its 97 references that are in the map. First posted on arXiv 21 Nov 2023.

Builds on

53 of 97 references.

References · 53

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  3. 2017Counterfactual Fairnesscited by 802
  4. 2017Deep Reinforcement Learning that Matterscited by 727
  5. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  6. 2018A Reductions Approach to Fair Classificationcited by 585
  7. 2020Learning under Concept Drift: A Reviewcited by 470
  8. 2017Algorithmic decision making and the cost of fairnesscited by 402
  9. 2016Learning to reinforcement learncited by 369
  10. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  11. 2020Performative Predictioncited by 318
  12. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
38 more
  1. 2015Strategic Classificationcited by 256
  2. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  3. 2018Delayed Impact of Fair Machine Learningcited by 183
  4. 2018Path-Specific Counterfactual Fairnesscited by 179
  5. 2016Fairness in Learning: Classic and Contextual Banditscited by 167
  6. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 152
  7. 2020Algorithmic Fairnesscited by 143
  8. 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 139
  9. 2018An Intersectional Definition of Fairnesscited by 126
  10. 2020Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimizationcited by 120
  11. 2017How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utilitycited by 116
  12. 2016Fairness in Reinforcement Learningcited by 93
  13. 2020On the Fairness of Causal Algorithmic Recoursecited by 69
  14. 2020How Do Fair Decisions Fare in Long-term Qualification?cited by 59
  15. 2019Algorithms for Fairness in Sequential Decision Makingcited by 53
  16. 2019Simulation-based reinforcement learning for real-world autonomous drivingcited by 51
  17. 2019α-Rank: Multi-Agent Evaluation by Evolutioncited by 50
  18. 2019On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learningcited by 48
  19. 2019Causal Modeling for Fairness in Dynamical Systemscited by 46
  20. 2022Diagnosing failures of fairness transfer across distribution shift in real-world medical settingscited by 45
  21. 2022Multiplayer Performative Prediction: Learning in Decision-Dependent Gamescited by 42
  22. 2019Fair Contextual Multi-Armed Bandits: Theory and Experimentscited by 41
  23. 2020What's Sex Got To Do With Fair Machine Learning?cited by 37
  24. 2018From Fair Decision Making to Social Equalitycited by 36
  25. 2019The Sensitivity of Counterfactual Fairness to Unmeasured Confoundingcited by 35
  26. 2019Equal Opportunity in Online Classification with Partial Feedbackcited by 34
  27. 2022Multi-agent Performative Prediction: From Global Stability and Optimality to Chaoscited by 33
  28. 2020Fairness and Robustness in Invariant Learning: A Case Study in Toxicity Classificationcited by 32
  29. 2023Long-Term Fairness with Unknown Dynamicscited by 25
  30. 2018Deep Generative Markov State Modelscited by 19
  31. 2021Unintended Selection: Persistent Qualification Rate Disparities and Interventionscited by 18
  32. 2022Achieving Long-Term Fairness in Sequential Decision Makingcited by 18
  33. 2020Causal Multi-Level Fairnesscited by 13
  34. 2022Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systemscited by 13
  35. 2021Towards Return Parity in Markov Decision Processescited by 12
  36. 2022Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Makingcited by 12
  37. 2022Fairness and robustness in anti-causal predictioncited by 10
  38. 2019Dynamic Modeling and Equilibria in Fair Decision Makingcited by 8

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 4.

8 papers.

  1. 2024Time Can Invalidate Algorithmic Recoursecited by 8
  2. 2024Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairnesscited by 6
  3. 2024Long-term Fairness For Real-time Decision Making: A Constrained Online Optimization Approachcited by 2
  4. 2026Fairness under uncertainty in sequential decisionscited by 2
  5. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  6. 2026How Predicted Links Influence Network Evolution: Disentangling Choice and Algorithmic Feedback in Dynamic Graphscited by 0
  7. 2026Price of Fairness in Short-Term and Long-Term Algorithmic Selectionscited by 0
  8. 2026Long-term Fairness with Selective Labelscited by 0