mlsanityData to 7 Oct 2026

Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors

arXiv 2301.08987 ↗First posted 21 Jan 2023cs.LG stat.MLcited by 7

Not on the map. Why?

Abstract (arXiv)

The pursuit of long-term fairness involves the interplay between decision-making and the underlying data generating process. In this paper, through causal modeling with a directed acyclic graph (DAG) on the decision-distribution interplay, we investigate the possibility of achieving long-term fairness from a dynamic perspective. We propose Tier Balancing, a technically more challenging but more natural notion to achieve in the context of long-term, dynamic fairness analysis. Different from previous fairness notions that are defined purely on observed variables, our notion goes one step further, capturing behind-the-scenes situation changes on the unobserved latent causal factors that directly carry out the influence from the current decision to the future data distribution. Under the specified dynamics, we prove that in general one cannot achieve the long-term fairness goal only through one-step interventions. Furthermore, in the effort of approaching long-term fairness, we consider the mission of "getting closer to" the long-term fairness goal and present possibility and impossibility results accordingly.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 37 of its 58 references that are in the map. First posted on arXiv 21 Jan 2023.

Builds on

37 of 58 references.

References · 37

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  2. 2017Counterfactual Fairnesscited by 802
  3. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  4. 2018Actionable Recourse in Linear Classificationcited by 327
  5. 2020Performative Predictioncited by 318
  6. 2017Avoiding Discrimination through Causal Reasoningcited by 191
  7. 2018Delayed Impact of Fair Machine Learningcited by 183
  8. 2018Path-Specific Counterfactual Fairnesscited by 179
  9. 2016Fairness in Learning: Classic and Contextual Banditscited by 167
  10. 2017Runaway Feedback Loops in Predictive Policingcited by 97
  11. 2016Fairness in Reinforcement Learningcited by 93
  12. 2019Strategic Classification is Causal Modeling in Disguisecited by 92
25 more
  1. 2021Towards Long-term Fairness in Recommendationcited by 77
  2. 2016A causal framework for discovering and removing direct and indirect discriminationcited by 71
  3. 2020On the Fairness of Causal Algorithmic Recoursecited by 69
  4. 2019PC-Fairness: A Unified Framework for Measuring Causality-based Fairnesscited by 67
  5. 2020Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewardscited by 60
  6. 2019Counterfactual Risk Assessments, Evaluation, and Fairnesscited by 59
  7. 2020How Do Fair Decisions Fare in Long-term Qualification?cited by 59
  8. 2020Robust Fairness under Covariate Shiftcited by 58
  9. 2021Learning latent causal graphs via mixture oraclescited by 55
  10. 2019Algorithms for Fairness in Sequential Decision Makingcited by 53
  11. 2019On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learningcited by 48
  12. 2019Causal Modeling for Fairness in Dynamical Systemscited by 46
  13. 2017A Short-term Intervention for Long-term Fairness in the Labor Marketcited by 44
  14. 2020Fairness in Risk Assessment Instruments: Post-Processing to Achieve Counterfactual Equalized Oddscited by 40
  15. 2020Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learningcited by 40
  16. 2019Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairnesscited by 38
  17. 2022Causal Conceptions of Fairness and their Consequencescited by 38
  18. 2018From Fair Decision Making to Social Equalitycited by 36
  19. 2019Transfer of Machine Learning Fairness across Domainscited by 36
  20. 2018Downstream Effects of Affirmative Actioncited by 34
  21. 2019Equal Opportunity in Online Classification with Partial Feedbackcited by 34
  22. 2018Fair Algorithms for Learning in Allocation Problemscited by 29
  23. 2020Principal Fairness for Human and Algorithmic Decision-Makingcited by 20
  24. 2020Causal Multi-Level Fairnesscited by 13
  25. 2021Model Transferability With Responsive Decision Subjectscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 0; 2026: 1.

7 papers.

  1. 2023Causal Reinforcement Learning: A Surveycited by 22
  2. 2024Prompting Fairness: Integrating Causality to Debias Large Language Modelscited by 20
  3. 2024Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challengescited by 4
  4. 2023Procedural Fairness Through Decoupling Objectionable Data Generating Componentscited by 3
  5. 2024What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learningcited by 3
  6. 2024Lookahead Counterfactual Fairnesscited by 2
  7. 2026Individual Fairness In Strategic Classificationcited by 0