mlsanityData to 7 Oct 2026

Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization

arXiv 2108.05449 ↗First posted 11 Aug 2021cs.LG cs.AI cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Deep learning algorithms mine knowledge from the training data and thus would likely inherit the dataset's bias information. As a result, the obtained model would generalize poorly and even mislead the decision process in real-life applications. We propose to remove the bias information misused by the target task with a cross-sample adversarial debiasing (CSAD) method. CSAD explicitly extracts target and bias features disentangled from the latent representation generated by a feature extractor and then learns to discover and remove the correlation between the target and bias features. The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator. Moreover, we propose joint content and local structural representation learning to boost mutual information estimation for better performance. We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 45 of its 59 references that are in the map. First posted on arXiv 11 Aug 2021.

Builds on

45 of 59 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  6. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  7. 2019Contrastive Multiview Codingcited by 1,297
  8. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  9. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  10. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  11. 2018MINE: Mutual Information Neural Estimationcited by 680
  12. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
33 more
  1. 2019On Variational Bounds of Mutual Informationcited by 550
  2. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  3. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  4. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
  5. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  6. 2019On Mutual Information Maximization for Representation Learningcited by 315
  7. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 279
  8. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  9. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  10. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 214
  11. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  12. 2019Learning De-biased Representations with Biased Representationscited by 199
  13. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  14. 2019Federated Adversarial Domain Adaptationcited by 140
  15. 2020Learning from Failure: Training Debiased Classifier from Biased Classifiercited by 133
  16. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  17. 2019Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognitioncited by 117
  18. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  19. 2018Invariant Representations without Adversarial Trainingcited by 111
  20. 2019Domain Agnostic Learning with Disentangled Representationscited by 107
  21. 2020Face Recognition: Too Bias, or Not Too Bias?cited by 82
  22. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  23. 2018iFair: Learning Individually Fair Data Representations for Algorithmic Decision Makingcited by 64
  24. 2019Operationalizing Individual Fairness with Pairwise Fair Representationscited by 64
  25. 2018Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentationcited by 49
  26. 2018Contemplating Visual Emotions: Understanding and Overcoming Dataset Biascited by 41
  27. 2020Accuracy and Fairness Trade-offs in Machine Learning: A Stochastic Multi-Objective Approachcited by 39
  28. 2020SenSeI: Sensitive Set Invariance for Enforcing Individual Fairnesscited by 37
  29. 2019Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generationcited by 36
  30. 2020Learning Unbiased Representations via Mutual Information Backpropagationcited by 25
  31. 2020Towards Gender-Neutral Face Descriptors for Mitigating Bias in Face Recognitioncited by 11
  32. 2018PhoneMD: Learning to Diagnose Parkinson's Disease from Smartphone Datacited by 4
  33. 2020Predicting Parkinson's Disease with Multimodal Irregularly Collected Longitudinal Smartphone Datacited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 7; 2023: 9; 2024: 6; 2025: 7; 2026: 1.

32 papers.

Sort:

By area:

  1. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  2. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  3. 2022Learning Debiased Classifier with Biased Committeecited by 51
  4. 2023Overcoming Simplicity Bias in Deep Networks using a Feature Sievecited by 29
  5. 2023Generalizing Graph ODE for Learning Complex System Dynamics across Environmentscited by 23
  6. 2022Localized Adversarial Domain Generalizationcited by 19
  7. 2023On Fairness of Medical Image Classification with Multiple Sensitive Attributes via Learning Orthogonal Representationscited by 17
  8. 2022Pseudo Bias-Balanced Learning for Debiased Chest X-ray Classificationcited by 14
  9. 2021Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignmentcited by 8
  10. 2021General Greedy De-bias Learningcited by 7
  11. 2022CAT: Controllable Attribute Translation for Fair Facial Attribute Classificationcited by 6
  12. 2024Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimizationcited by 6
20 more
  1. 2023When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attackscited by 5
  2. 2023Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networkscited by 3
  3. 2023Pushing the Accuracy-Group Robustness Frontier with Introspective Self-playcited by 2
  4. 2024Medical Image Debiasing by Learning Adaptive Agreement from a Biased Councilcited by 2
  5. 2024Mitigating Spurious Correlations via Disagreement Probabilitycited by 2
  6. 2024Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimizationcited by 2
  7. 2025Do Fairness Interventions Come at the Cost of Privacy: Evaluations for Binary Classifierscited by 2
  8. 2025Controllable Feature Whitening for Hyperparameter-Free Bias Mitigationcited by 2
  9. 2026Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Informationcited by 2
  10. 2022Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite Imagerycited by 1
  11. 2023Learning Fair Representations with High-Confidence Guaranteescited by 1
  12. 2023SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filteringcited by 1
  13. 2025Debiased Prompt Tuning in Vision-Language Model without Annotationscited by 1
  14. 2025Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domainscited by 1
  15. 2023Delving into Identify-Emphasize Paradigm for Combating Unknown Biascited by 0
  16. 2024Revisiting the Dataset Bias Problem from a Statistical Perspectivecited by 0
  17. 2024From Discrete to Continuous: Deep Fair Clustering With Transferable Representationscited by 0
  18. 2025Information Subtraction: Learning Representations for Conditional Entropycited by 0
  19. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  20. 2025Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inferencecited by 0