mlsanityData to 14 Oct 2026

Controllable Invariance through Adversarial Feature Learning

arXiv 1705.11122 ↗First posted 31 May 2017cs.LG cs.AI cs.CLcited by 127

Not on the map. Why?

Abstract (arXiv)

Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning. In this paper, we tackle the problem of learning representations invariant to a specific factor or trait of data. The representation learning process is formulated as an adversarial minimax game. We analyze the optimal equilibrium of such a game and find that it amounts to maximizing the uncertainty of inferring the detrimental factor given the representation while maximizing the certainty of making task-specific predictions. On three benchmark tasks, namely fair and bias-free classification, language-independent generation, and lighting-independent image classification, we show that the proposed framework induces an invariant representation, and leads to better generalization evidenced by the improved performance.

Key facts. Cited by 127 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 35; 2022: 38; 2023: 16; 2024: 19; 2025: 16; 2026: 3.

127 papers.

Sort:

By area:

  1. 2021GAN Inversion: A Surveycited by 367
  2. 2023LEACE: Perfect linear concept erasure in closed formcited by 267
  3. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  4. 2021Debiasing Pre-trained Contextualised Embeddingscited by 107
  5. 2021EnD: Entangling and Disentangling deep representations for bias correctioncited by 105
  6. 2022Linear Adversarial Concept Erasurecited by 101
  7. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 77
  8. 2022MEDFAIR: Benchmarking Fairness for Medical Imagingcited by 68
  9. 2021Controllable Guarantees for Fair Outcomes via Contrastive Information Estimationcited by 45
  10. 2021Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlationscited by 41
  11. 2022Probing Classifiers are Unreliable for Concept Removal and Detectioncited by 41
  12. 2022Unbiased Supervised Contrastive Learningcited by 40
38 more
  1. 2025Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuningcited by 39
  2. 2021Personalized Counterfactual Fairness in Recommendationcited by 38
  3. 2021Fair Normalizing Flowscited by 38
  4. 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
  5. 2021Quantifying and Mitigating Privacy Risks of Contrastive Learningcited by 36
  6. 2021Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankerscited by 35
  7. 2023Prompt Optimization via Adversarial In-Context Learningcited by 33
  8. 2022Learning Fair Representation via Distributional Contrastive Disentanglementcited by 31
  9. 2022Invariant Causal Mechanisms through Distribution Matchingcited by 31
  10. 2021Fair Representation Learning for Heterogeneous Information Networkscited by 28
  11. 2021Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updatescited by 27
  12. 2022Fairness in Recommendation: Foundations, Methods and Applicationscited by 27
  13. 2021An Information-theoretic Approach to Distribution Shiftscited by 25
  14. 2023Parameter-efficient Modularised Bias Mitigation via AdapterFusioncited by 25
  15. 2023Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projectioncited by 25
  16. 2021Dictionary-based Debiasing of Pre-trained Word Embeddingscited by 24
  17. 2021CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learningcited by 23
  18. 2023Efficient fair PCA for fair representation learningcited by 23
  19. 2021MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learningcited by 21
  20. 2021NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learningcited by 21
  21. 2022FARE: Provably Fair Representation Learning with Practical Certificatescited by 21
  22. 2022Unlearning Protected User Attributes in Recommendations with Adversarial Trainingcited by 20
  23. 2022Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworkscited by 18
  24. 2023FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associationscited by 18
  25. 2021Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Taskscited by 16
  26. 2022Learning Fair Representations via Rate-Distortion Maximizationcited by 15
  27. 2024Utility-Fairness Trade-Offs and How to Find Themcited by 15
  28. 2021Metadata Normalizationcited by 14
  29. 2022Learning Disentangled Textual Representations via Statistical Measures of Similaritycited by 14
  30. 2022Visual Comparison of Language Model Adaptationcited by 14
  31. 2022MMD-B-Fair: Learning Fair Representations with Statistical Testingcited by 13
  32. 2024Fairness and Bias Mitigation in Computer Vision: A Surveycited by 13
  33. 2021On Characterizing the Trade-off in Invariant Representation Learningcited by 12
  34. 2023SOAR: Scene-debiasing Open-set Action Recognitioncited by 12
  35. 2022Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learningcited by 11
  36. 2024Model Inversion Attacks: A Survey of Approaches and Countermeasurescited by 11
  37. 2022Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networkscited by 10
  38. 2022Semi-Leak: Membership Inference Attacks Against Semi-supervised Learningcited by 10

50 most cited of 127 All 127 (JSON)