mlsanityData to 7 Oct 2026

Addressing Polarization and Unfairness in Performative Prediction

arXiv 2406.16756 ↗First posted 24 Jun 2024cs.LG cs.AI cs.CYcited by 11

Not on the map. Why?

Abstract (arXiv)

In many real-world applications of machine learning such as recommendations, hiring, and lending, deployed models influence the data they are trained on, leading to feedback loops between predictions and data distribution. The performative prediction (PP) framework captures this phenomenon by modeling the data distribution as a function of the deployed model. While prior work has focused on finding performative stable (PS) solutions for robustness, their societal impacts, particularly regarding fairness, remain underexplored. We show that PS solutions can lead to severe polarization and prediction performance disparities, and that conventional fairness interventions in previous works often fail under model-dependent distribution shifts due to failing the PS criteria. To address these challenges in PP, we introduce novel fairness mechanisms that provably ensure both stability and fairness, validated by theoretical analysis and empirical results.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 33 of its 48 references that are in the map. First posted on arXiv 24 Jun 2024.

Builds on

33 of 48 references.

References · 33

  1. 2014Convex Optimization: Algorithms and Complexitycited by 569
  2. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  3. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  4. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
  5. 2020Performative Predictioncited by 318
  6. 2015Strategic Classificationcited by 256
  7. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 152
  8. 2018The Social Cost of Strategic Classificationcited by 105
  9. 2017Runaway Feedback Loops in Predictive Policingcited by 97
  10. 2021Outside the Echo Chamber: Optimizing the Performative Riskcited by 95
  11. 2020Stochastic Optimization for Performative Predictioncited by 92
  12. 2020Performative Prediction in a Stateful Worldcited by 90
21 more
  1. 2018How Do Classifiers Induce Agents To Invest Effort Strategically?cited by 82
  2. 2018The Disparate Effects of Strategic Manipulationcited by 75
  3. 2021How to Learn when Data Reacts to Your Model: Performative Gradient Descentcited by 70
  4. 2020How Do Fair Decisions Fare in Long-term Qualification?cited by 59
  5. 2020Distributionally Robust Losses for Latent Covariate Mixturescited by 57
  6. 2023Performative Prediction: Past and Futurecited by 52
  7. 2019Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairnesscited by 38
  8. 2023Performative Prediction with Neural Networkscited by 33
  9. 2023Re-weighting Based Group Fairness Regularization via Classwise Robust Optimizationcited by 20
  10. 2021Unintended Selection: Persistent Qualification Rate Disparities and Interventionscited by 18
  11. 2022Achieving Long-Term Fairness in Sequential Decision Makingcited by 18
  12. 2021Unified Group Fairness on Federated Learningcited by 15
  13. 2022Equal Improvability: A New Fairness Notion Considering the Long-term Impactcited by 13
  14. 2021Towards Return Parity in Markov Decision Processescited by 12
  15. 2024Non-linear Welfare-Aware Strategic Learningcited by 12
  16. 2023Loss Balancing for Fair Supervised Learningcited by 11
  17. 2024Learning under Imitative Strategic Behavior with Unforeseeable Outcomescited by 8
  18. 2024Algorithmic Decision-Making under Agents with Persistent Improvementcited by 7
  19. 2022Optimizing the Performative Risk under Weak Convexity Assumptionscited by 4
  20. 2023Performativity and Prospective Fairnesscited by 4
  21. 2022Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimizationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 8.

11 papers.

  1. 2025On the Impact of Performative Risk Minimization for Binary Random Variablescited by 3
  2. 2025A Causal Lens for Learning Long-term Fair Policiescited by 2
  3. 2026Dissecting Performative Prediction: A Comprehensive Surveycited by 2
  4. 2025SPRINT: Stochastic Performative Prediction With Variance Reductioncited by 1
  5. 2026Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMscited by 1
  6. 2026Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamicscited by 1
  7. 2026When Predictions Shape Reality: A Socio-Technical Synthesis of Performative Predictions in Machine Learningcited by 0
  8. 2026Performative Learning Theorycited by 0
  9. 2026Market Games for Generative Models: Equilibria, Welfare, and Strategic Entrycited by 0
  10. 2026Sequential Strategic Classification with Multi-Stage Selective Classifierscited by 0
  11. 2026When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loopcited by 0