mlsanityData to 7 Oct 2026

FR-Train: A Mutual Information-Based Approach to Fair and Robust Training

arXiv 2002.10234 ↗First posted 24 Feb 2020cs.LG stat.MLcited by 52

Not on the map. Why?

Abstract (arXiv)

Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training in the presence of data bias and poisoning. However, the existing model fairness techniques mistakenly view poisoned data as an additional bias to be fixed, resulting in severe performance degradation. To address this problem, we propose FR-Train, which holistically performs fair and robust model training. We provide a mutual information-based interpretation of an existing adversarial training-based fairness-only method, and apply this idea to architect an additional discriminator that can identify poisoned data using a clean validation set and reduce its influence. In our experiments, FR-Train shows almost no decrease in fairness and accuracy in the presence of data poisoning by both mitigating the bias and defending against poisoning. We also demonstrate how to construct clean validation sets using crowdsourcing, and release new benchmark datasets.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 13; 2023: 8; 2024: 9; 2025: 4; 2026: 3.

52 papers.

Sort:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  2. 2021Trustworthy AI: From Principles to Practicescited by 206
  3. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  4. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  5. 2024FairCLIP: Harnessing Fairness in Vision-Language Learningcited by 69
  6. 2021Sample Selection for Fair and Robust Trainingcited by 48
  7. 2022Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Modelscited by 47
  8. 2021On Tilted Losses in Machine Learning: Theory and Applicationscited by 42
  9. 2021Improving Fairness via Federated Learningcited by 39
  10. 2022Fairness Reprogrammingcited by 33
  11. 2023Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalizationcited by 31
  12. 2021A Stochastic Optimization Framework for Fair Risk Minimizationcited by 26
38 more
  1. 2021A Sociotechnical View of Algorithmic Fairnesscited by 24
  2. 2022Optimising Equal Opportunity Fairness in Model Trainingcited by 22
  3. 2021Poisoning Attacks on Fair Machine Learningcited by 19
  4. 2024FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classificationcited by 19
  5. 2021Fairness-Aware PAC Learning from Corrupted Datacited by 18
  6. 2021Information-theoretic regularization for Multi-source Domain Adaptationcited by 15
  7. 2023Improving Fair Training under Correlation Shiftscited by 14
  8. 2022Equal Improvability: A New Fairness Notion Considering the Long-term Impactcited by 13
  9. 2023FairVision: Equitable Deep Learning for Eye Disease Screening via Fair Identity Scalingcited by 13
  10. 2024Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosiscited by 9
  11. 2024On the Inductive Biases of Demographic Parity-based Fair Learning Algorithmscited by 5
  12. 2021Fair Training of Decision Tree Classifierscited by 4
  13. 2022Breaking Fair Binary Classification with Optimal Flipping Attackscited by 4
  14. 2022Prototype Based Classification from Hierarchy to Fairnesscited by 4
  15. 2022Fairness-aware Regression Robust to Adversarial Attackscited by 4
  16. 2023FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scalingcited by 4
  17. 2024LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Viewscited by 4
  18. 2024Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness and Efficiencycited by 3
  19. 2021Responsible AI Challenges in End-to-end Machine Learningcited by 2
  20. 2021Fair Machine Learning under Limited Demographically Labeled Datacited by 2
  21. 2022A Survey on Preserving Fairness Guarantees in Changing Environmentscited by 2
  22. 2023Mitigating Label Bias in Machine Learning: Fairness through Confident Learningcited by 2
  23. 2024MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakagecited by 2
  24. 2025Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detectioncited by 2
  25. 2022Improving Evaluation of Debiasing in Image Classificationcited by 1
  26. 2022Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and R'enyi Measurescited by 1
  27. 2022Towards Fair Classification against Poisoning Attackscited by 1
  28. 2023Boosting Fair Classifier Generalization through Adaptive Priority Reweighingcited by 1
  29. 2023Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk Minimization Frameworkcited by 1
  30. 2023Responsible AI (RAI) Games and Ensemblescited by 1
  31. 2026Nearest-Neighbor Density Estimation for Dependency Suppressioncited by 1
  32. 2021FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Datacited by 0
  33. 2022Abstract Interpretation-Based Feature Importance for SVMscited by 0
  34. 2024Utilizing Adversarial Examples for Bias Mitigation and Accuracy Enhancementcited by 0
  35. 2024Fair Class-Incremental Learning using Sample Weightingcited by 0
  36. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  37. 2025Simple and Effective Specialized Representations for Fair Classifierscited by 0
  38. 2025Toward Unifying Group Fairness Evaluation from a Sparsity Perspectivecited by 0

50 most cited of 52 All 52 (JSON)