mlsanityData to 14 Oct 2026

Latent Space Smoothing for Individually Fair Representations

arXiv 2111.13650 ↗First posted 26 Nov 2021cs.LG cs.AI cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Fair representation learning transforms user data into a representation that ensures fairness and utility regardless of the downstream application. However, learning individually fair representations, i.e., guaranteeing that similar individuals are treated similarly, remains challenging in high-dimensional settings such as computer vision. In this work, we introduce LASSI, the first representation learning method for certifying individual fairness of high-dimensional data. Our key insight is to leverage recent advances in generative modeling to capture the set of similar individuals in the generative latent space. This enables us to learn individually fair representations that map similar individuals close together by using adversarial training to minimize the distance between their representations. Finally, we employ randomized smoothing to provably map similar individuals close together, in turn ensuring that local robustness verification of the downstream application results in end-to-end fairness certification. Our experimental evaluation on challenging real-world image data demonstrates that our method increases certified individual fairness by up to 90% without significantly affecting task utility.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 63 of its 96 references that are in the map. First posted on arXiv 26 Nov 2021.

Builds on

63 of 96 references.

References · 63

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  8. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  9. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  11. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  12. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
38 more
  1. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  2. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 384
  3. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  4. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  5. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
  6. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 242
  7. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  8. 2019Pareto Multi-Task Learningcited by 224
  9. 2015The Variational Fair Autoencodercited by 223
  10. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  11. 2015Censoring Representations with an Adversarycited by 192
  12. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 153
  13. 2018Reducing Gender Bias in Abusive Language Detectioncited by 152
  14. 2019On the Fairness of Disentangled Representationscited by 144
  15. 2020Fair Attribute Classification through Latent Space De-biasingcited by 125
  16. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  17. 2018Learning Controllable Fair Representationscited by 83
  18. 2019Conditional Learning of Fair Representationscited by 78
  19. 2019Predictive Inequity in Object Detectioncited by 77
  20. 2020Fairness by Learning Orthogonal Disentangled Representationscited by 76
  21. 2019Image Counterfactual Sensitivity Analysis for Detecting Unintended Biascited by 74
  22. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  23. 2020Learning Certified Individually Fair Representationscited by 69
  24. 2018iFair: Learning Individually Fair Data Representations for Algorithmic Decision Makingcited by 64
  25. 2019Operationalizing Individual Fairness with Pairwise Fair Representationscited by 64
  26. 2020Towards causal benchmarking of bias in face analysis algorithmscited by 64
  27. 2020Two Simple Ways to Learn Individual Fairness Metrics from Datacited by 54
  28. 2019Metric Learning for Individual Fairnesscited by 52
  29. 2020Verifying Individual Fairness in Machine Learning Modelscited by 49
  30. 2020Learning perturbation sets for robust machine learningcited by 48
  31. 2021Discover the Unknown Biased Attribute of an Image Classifiercited by 46
  32. 2018Probabilistic Verification of Fairness Properties via Concentrationcited by 45
  33. 2020Counterfactual Fairness with Disentangled Causal Effect Variational Autoencodercited by 45
  34. 2019Perfectly Parallel Fairness Certification of Neural Networkscited by 42
  35. 2021Fair Normalizing Flowscited by 38
  36. 2020Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulationcited by 37
  37. 2020SenSeI: Sensitive Set Invariance for Enforcing Individual Fairnesscited by 37
  38. 2019Learning Fair Representations via an Adversarial Frameworkcited by 29

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 2; 2024: 3; 2025: 5; 2026: 3.

18 papers.

Sort:

By area:

  1. 2022FARE: Provably Fair Representation Learning with Practical Certificatescited by 21
  2. 2022Certifying Some Distributional Fairness with Subpopulation Decompositioncited by 11
  3. 2024Distributionally Generative Augmentation for Fair Facial Attribute Classificationcited by 8
  4. 2022Private and Reliable Neural Network Inferencecited by 7
  5. 2022Human-Guided Fair Classification for Natural Language Processingcited by 5
  6. 2024Path-GPTOmic: A Balanced Multi-modal Learning Framework for Survival Outcome Predictioncited by 5
  7. 2025AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Datacited by 5
  8. 2024KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Modelscited by 3
  9. 2022Robustness of Unsupervised Representation Learning without Labelscited by 2
  10. 2023Certification of Distributional Individual Fairnesscited by 2
  11. 2023Learning Fair Representations with High-Confidence Guaranteescited by 1
  12. 2025pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learningcited by 1
6 more
  1. 2025Correct-By-Construction: Certified Individual Fairness through Neural Network Trainingcited by 1
  2. 2026SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognitioncited by 1
  3. 2026Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Studycited by 1
  4. 2025Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inferencecited by 0
  5. 2025FairExpand: Individual Fairness on Graphs with Partial Similarity Informationcited by 0
  6. 2026FairNVT: Fair Classification via Noise Injection in Vision Transformerscited by 0