mlsanityData to 13 Oct 2026

Supervised Algorithmic Fairness in Distribution Shifts: A Survey

arXiv 2402.01327 ↗First posted 2 Feb 2024cs.LG cs.AI cs.CYcited by 24

Not on the map. Why?

Abstract (arXiv)

Supervised fairness-aware machine learning under distribution shifts is an emerging field that addresses the challenge of maintaining equitable and unbiased predictions when faced with changes in data distributions from source to target domains. In real-world applications, machine learning models are often trained on a specific dataset but deployed in environments where the data distribution may shift over time due to various factors. This shift can lead to unfair predictions, disproportionately affecting certain groups characterized by sensitive attributes, such as race and gender. In this survey, we provide a summary of various types of distribution shifts and comprehensively investigate existing methods based on these shifts, highlighting six commonly used approaches in the literature. Additionally, this survey lists publicly available datasets and evaluation metrics for empirical studies. We further explore the interconnection with related research fields, discuss the significant challenges, and identify potential directions for future studies.

Key facts. Cited by 24 papers in the map (data through 13 Oct 2026). Builds on 34 of its 62 references that are in the map. First posted on arXiv 2 Feb 2024.

Builds on

34 of 62 references.

References · 34

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,005
  2. 2019Invariant Risk Minimizationcited by 1,842
  3. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,371
  4. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,242
  5. 2017Counterfactual Fairnesscited by 804
  6. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 428
  7. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 411
  8. 2020Environment Inference for Invariant Learningcited by 306
  9. 2018Domain Generalization via Conditional Invariant Representationcited by 146
  10. 2019FairFace: Face Attribute Dataset for Balanced Race, Gender, and Agecited by 87
  11. 2020Robust Fairness under Covariate Shiftcited by 58
  12. 2018Residual Unfairness in Fair Machine Learning from Prejudiced Datacited by 49
22 more
  1. 2019Causal Modeling for Fairness in Dynamical Systemscited by 46
  2. 2022Diagnosing failures of fairness transfer across distribution shift in real-world medical settingscited by 45
  3. 2020A Distributionally Robust Approach to Fair Classificationcited by 43
  4. 2019Transfer of Machine Learning Fairness across Domainscited by 36
  5. 2020Ensuring Fairness Beyond the Training Datacited by 35
  6. 2022Learning Fair Representation via Distributional Contrastive Disentanglementcited by 31
  7. 2022Fairness Transferability Subject to Bounded Distribution Shiftcited by 28
  8. 2020FairOD: Fairness-aware Outlier Detectioncited by 24
  9. 2023Fairness and Accuracy under Domain Generalizationcited by 24
  10. 2022Transferring Fairness under Distribution Shifts via Fair Consistency Regularizationcited by 21
  11. 2021Deep Clustering based Fair Outlier Detectioncited by 19
  12. 2021Fairness-Aware Online Meta-learningcited by 19
  13. 2021Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inferencecited by 18
  14. 2022Adaptive Fairness-Aware Online Meta-Learning for Changing Environmentscited by 17
  15. 2020Ensuring Fairness under Prior Probability Shiftscited by 16
  16. 2019Fairness-enhancing interventions in stream classificationcited by 15
  17. 2023Improving Fair Training under Correlation Shiftscited by 14
  18. 2023Towards Fair Disentangled Online Learning for Changing Environmentscited by 11
  19. 2024Graph Fairness Learning under Distribution Shiftscited by 10
  20. 2023Towards Counterfactual Fairness-aware Domain Generalization in Changing Environmentscited by 8
  21. 2023Achieving Counterfactual Fairness for Anomaly Detectioncited by 7
  22. 2023Adaptation Speed Analysis for Fairness-aware Causal Modelscited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 7; 2025: 7; 2026: 10.

24 papers.

Sort:

By area:

  1. 2025Multi-Modal Foundation Models for Computational Pathology: A Surveycited by 9
  2. 2024Learning Fair Invariant Representations under Covariate and Correlation Shifts Simultaneouslycited by 7
  3. 2025The SAGES Critical View of Safety Challenge: A Global Benchmark for AI-Assisted Surgical Quality Assessmentcited by 6
  4. 2024GDDA: Semantic OOD Detection on Graphs under Covariate Shift via Score-Based Diffusion Modelscited by 5
  5. 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Promptscited by 5
  6. 2024FADE: Towards Fairness-aware Generation for Domain Generalization via Classifier-Guided Score-based Diffusion Modelscited by 4
  7. 2024MLDGG: Meta-Learning for Domain Generalization on Graphscited by 4
  8. 2024FEED: Fairness-Enhanced Meta-Learning for Domain Generalizationcited by 3
  9. 2026Object Hallucination-Free Reinforcement Unlearning for Vision-Language Modelscited by 3
  10. 2025Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergiescited by 2
  11. 2025BioPro: Towards Difference-Aware Gender Fairness for Vision-Language Modelscited by 2
  12. 2024Feature-Space Semantic Invariance: Enhanced OOD Detection for Open-Set Domain Generalizationcited by 1
12 more
  1. 2024Hypergraph-Based Dynamic Graph Node Classificationcited by 1
  2. 2025Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domainscited by 1
  3. 2026LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphscited by 1
  4. 2026On the Robustness of Machine Unlearning for Vision-Language Modelscited by 1
  5. 2025Fairness-Aware Low-Rank Representation Fine-Tuningcited by 0
  6. 2025Out-of-Distribution Detection in Heterogeneous Graphs via Energy Propagationcited by 0
  7. 2026Failing on Bias Mitigation: A Case Study on the Challenges of Fairness in Government Datacited by 0
  8. 2026Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFNcited by 0
  9. 2026MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discoverycited by 0
  10. 2026ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Modelscited by 0
  11. 2026Evaluating Model Retraining under Drift: Paired Comparisons of Cumulative Subgroup Disparitycited by 0
  12. 2026FairRSFM: A Biome-Aware Benchmark and Debiasing Framework for Remote Sensing Foundation Modelscited by 0