mlsanityData to 7 Oct 2026

Fair Mixup: Fairness via Interpolation

arXiv 2103.06503 ↗First posted 11 Mar 2021cs.LG cs.CY stat.MLcited by 109

Not on the map. Why?

Abstract (arXiv)

Training classifiers under fairness constraints such as group fairness, regularizes the disparities of predictions between the groups. Nevertheless, even though the constraints are satisfied during training, they might not generalize at evaluation time. To improve the generalizability of fair classifiers, we propose fair mixup, a new data augmentation strategy for imposing the fairness constraint. In particular, we show that fairness can be achieved by regularizing the models on paths of interpolated samples between the groups. We use mixup, a powerful data augmentation strategy to generate these interpolates. We analyze fair mixup and empirically show that it ensures a better generalization for both accuracy and fairness measurement in tabular, vision, and language benchmarks.

Key facts. Cited by 109 papers in the map (data through 7 Oct 2026). Builds on 20 of its 35 references that are in the map. First posted on arXiv 11 Mar 2021.

Builds on

20 of 35 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  7. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  8. 2018A Reductions Approach to Fair Classificationcited by 585
  9. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  10. 2017Fairness in Criminal Justice Risk Assessments: The State of the Artcited by 315
  11. 2015The Variational Fair Autoencodercited by 223
  12. 2017Optimizing the Latent Space of Generative Networkscited by 157
8 more
  1. 2019Robust Learning with Jacobian Regularizationcited by 127
  2. 2018Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizercited by 87
  3. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  4. 2018Data augmentation instead of explicit regularizationcited by 62
  5. 2020Estimating Generalization under Distribution Shifts via Domain-Invariant Representationscited by 56
  6. 2018Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraintscited by 53
  7. 2020A Distributionally Robust Approach to Fair Classificationcited by 43
  8. 2019Jacobian Adversarially Regularized Networks for Robustnesscited by 40

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 26; 2023: 34; 2024: 20; 2025: 14; 2026: 5.

109 papers.

Sort:

By area:

  1. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  2. 2023Debiasing Vision-Language Models via Biased Promptscited by 147
  3. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  4. 2021OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalizationcited by 86
  5. 2021Fairness via Representation Neutralizationcited by 63
  6. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  7. 2022Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifierscited by 53
  8. 2021Learning Fair Classifiers with Partially Annotated Group Labelscited by 40
  9. 2022Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networkscited by 39
  10. 2022FMP: Toward Fair Graph Message Passing against Topology Biascited by 35
  11. 2023FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methodscited by 33
  12. 2022On Learning Fairness and Accuracy on Multiple Subgroupscited by 31
38 more
  1. 2022Understanding Instance-Level Impact of Fairness Constraintscited by 27
  2. 2022Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refittingcited by 26
  3. 2023Survey of Social Bias in Vision-Language Modelscited by 26
  4. 2022Fair Representation Learning through Implicit Path Alignmentcited by 22
  5. 2022Transferring Fairness under Distribution Shifts via Fair Consistency Regularizationcited by 21
  6. 2024Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchorscited by 21
  7. 2022Learning fair representation with a parametric integral probability metriccited by 20
  8. 2023Re-weighting Based Group Fairness Regularization via Classwise Robust Optimizationcited by 20
  9. 2021Towards Understanding the Data Dependency of Mixup-style Trainingcited by 19
  10. 2021Anatomizing Bias in Facial Analysiscited by 18
  11. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  12. 2024CEB: Compositional Evaluation Benchmark for Fairness in Large Language Modelscited by 17
  13. 2023Fairness through Aleatoric Uncertaintycited by 16
  14. 2021k-Mixup Regularization for Deep Learning via Optimal Transportcited by 14
  15. 2021An overview of mixing augmentation methods and augmentation strategiescited by 14
  16. 2022Provably Learning Diverse Features in Multi-View Data with Midpoint Mixupcited by 14
  17. 2023Auditing and Generating Synthetic Data with Controllable Trust Trade-offscited by 13
  18. 2023Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approachcited by 12
  19. 2023FAIRER: Fairness as Decision Rationale Alignmentcited by 12
  20. 2023SYNAuG: Exploiting Synthetic Data for Data Imbalance Problemscited by 12
  21. 2023Chasing Fairness in Graphs: A GNN Architecture Perspectivecited by 12
  22. 2024OxonFair: A Flexible Toolkit for Algorithmic Fairnesscited by 12
  23. 2022Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothingcited by 11
  24. 2022When Neural Networks Fail to Generalize? A Model Sensitivity Perspectivecited by 10
  25. 2023Racial Bias within Face Recognition: A Surveycited by 9
  26. 2024Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibriumcited by 9
  27. 2021Gradual (In)Compatibility of Fairness Criteriacited by 8
  28. 2022Human-in-the-Loop Mixupcited by 8
  29. 2023Data Augmentation via Subgroup Mixup for Improving Fairnesscited by 8
  30. 2023Understanding Fairness Surrogate Functions in Algorithmic Fairnesscited by 8
  31. 2022Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groupscited by 7
  32. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  33. 2023fairret: a Framework for Differentiable Fairness Regularization Termscited by 7
  34. 2025Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metricscited by 7
  35. 2022Fair Classification via Domain Adaptation: A Dual Adversarial Learning Approachcited by 6
  36. 2023Fairness-aware Vision Transformer via Debiased Self-Attentioncited by 6
  37. 2023Data Optimization in Deep Learning: A Surveycited by 6
  38. 2024Promoting Fairness in Link Prediction with Graph Enhancementcited by 6

50 most cited of 109 All 109 (JSON)