mlsanityData to 7 Oct 2026

Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach

arXiv 2303.03300 ↗First posted 6 Mar 2023cs.LG cs.CYcited by 12

Not on the map. Why?

Abstract (arXiv)

Fairness in machine learning has attracted increasing attention in recent years. The fairness methods improving algorithmic fairness for in-distribution data may not perform well under distribution shifts. In this paper, we first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and model weight perturbation. Subsequently, we analyze the sufficient conditions to guarantee fairness (i.e., low demographic parity) for the target dataset, including fairness for the source dataset, and low prediction difference between the source and target datasets for each sensitive attribute group. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR) by considering the worst case within the model weight perturbation ball for each sensitive attribute group. We evaluate the effectiveness of our proposed RFR algorithm on synthetic and real distribution shifts across various datasets. Experimental results demonstrate that RFR achieves better fairness-accuracy trade-off performance compared with several baselines. The source code is available at urlhttps://github.com/zhimengj0326/RFRNeurIPS23.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 37 of its 63 references that are in the map. First posted on arXiv 6 Mar 2023.

Builds on

37 of 63 references.

References · 37

  1. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  4. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  5. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  6. 2017Counterfactual Fairnesscited by 802
  7. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
  8. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  9. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  10. 2015The Variational Fair Autoencodercited by 223
  11. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  12. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
25 more
  1. 2022Towards Understanding Sharpness-Aware Minimizationcited by 145
  2. 2021Efficient Sharpness-aware Minimization for Improved Training of Neural Networkscited by 137
  3. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  4. 2021Fair Mixup: Fairness via Interpolationcited by 109
  5. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  6. 2021Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Supportcited by 61
  7. 2020Robust Fairness under Covariate Shiftcited by 58
  8. 2016Learning to Pivot with Adversarial Networkscited by 55
  9. 2020Two Simple Ways to Learn Individual Fairness Metrics from Datacited by 54
  10. 2022Predicting Out-of-Distribution Error with the Projection Normcited by 50
  11. 2017A Short-term Intervention for Long-term Fairness in the Labor Marketcited by 44
  12. 2020Algorithmic Fairness in Educationcited by 44
  13. 2020SenSeI: Sensitive Set Invariance for Enforcing Individual Fairnesscited by 37
  14. 2022FMP: Toward Fair Graph Message Passing against Topology Biascited by 35
  15. 2020Addressing Fairness in Classification with a Model-Agnostic Multi-Objective Algorithmcited by 23
  16. 2021Fair Classification with Adversarial Perturbationscited by 23
  17. 2022Transferring Fairness under Distribution Shifts via Fair Consistency Regularizationcited by 21
  18. 2022Counterfactual Fairness with Partially Known Causal Graphcited by 20
  19. 2022Domain Adaptation meets Individual Fairness. And they get alongcited by 13
  20. 2023Predicting Out-of-Distribution Error with Confidence Optimal Transportcited by 13
  21. 2022Efficient Resource Allocation with Fairness Constraints in Restless Multi-Armed Banditscited by 11
  22. 2022Consistent Range Approximation for Fair Predictive Modelingcited by 7
  23. 2020Quadratic Metric Elicitation for Fairness and Beyondcited by 3
  24. 2022Individual Fairness in Feature-Based Pricing for Monopoly Marketscited by 3
  25. 2022A Survey on Preserving Fairness Guarantees in Changing Environmentscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 6; 2025: 3; 2026: 1.

12 papers.

  1. 2024Online DPO: Online Direct Preference Optimization with Fast-Slow Chasingcited by 38
  2. 2024SparseDM: Toward Sparse Efficient Diffusion Modelscited by 18
  3. 2024Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibriumcited by 9
  4. 2024Multiply Robust Estimation for Local Distribution Shifts with Multiple Domainscited by 4
  5. 2023Enhancing Group Fairness in Online Settings Using Oblique Decision Forestscited by 3
  6. 2024On the Maximal Local Disparity of Fairness-Aware Classifierscited by 3
  7. 2023Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neurosciencecited by 2
  8. 2024Navigating Towards Fairness with Data Selectioncited by 1
  9. 2025A Flat Minima Perspective on Understanding Augmentations and Model Robustnesscited by 1
  10. 2025Testing for Causal Fairnesscited by 0
  11. 2025DGSAM: Domain Generalization via Individual Sharpness-Aware Minimizationcited by 0
  12. 2026A Comprehensive View of Fairness through Distributional Stabilitycited by 0