mlsanityData to 7 Oct 2026

Fair Normalizing Flows

arXiv 2106.05937 ↗First posted 10 Jun 2021cs.LG cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

Fair representation learning is an attractive approach that promises fairness of downstream predictors by encoding sensitive data. Unfortunately, recent work has shown that strong adversarial predictors can still exhibit unfairness by recovering sensitive attributes from these representations. In this work, we present Fair Normalizing Flows (FNF), a new approach offering more rigorous fairness guarantees for learned representations. Specifically, we consider a practical setting where we can estimate the probability density for sensitive groups. The key idea is to model the encoder as a normalizing flow trained to minimize the statistical distance between the latent representations of different groups. The main advantage of FNF is that its exact likelihood computation allows us to obtain guarantees on the maximum unfairness of any potentially adversarial downstream predictor. We experimentally demonstrate the effectiveness of FNF in enforcing various group fairness notions, as well as other attractive properties such as interpretability and transfer learning, on a variety of challenging real-world datasets.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 52 of its 93 references that are in the map. First posted on arXiv 10 Jun 2021.

Builds on

52 of 93 references.

References · 52

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Variational Inference with Normalizing Flowscited by 2,161
  4. 2016Density estimation using Real NVPcited by 2,029
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  8. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  9. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  10. 2016Pixel Recurrent Neural Networkscited by 814
  11. 2019Neural Spline Flowscited by 590
  12. 2018Learning Adversarially Fair and Transferable Representationscited by 353
38 more
  1. 2018Actionable Recourse in Linear Classificationcited by 327
  2. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  3. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  4. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 232
  5. 2019Pareto Multi-Task Learningcited by 224
  6. 2015The Variational Fair Autoencodercited by 223
  7. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  8. 2015Censoring Representations with an Adversarycited by 191
  9. 2018Adversarial Removal of Demographic Attributes from Text Datacited by 166
  10. 2020A Theory of Usable Information Under Computational Constraintscited by 153
  11. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 152
  12. 2019On the Fairness of Disentangled Representationscited by 144
  13. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  14. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  15. 2018Invariant Representations without Adversarial Trainingcited by 111
  16. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  17. 2018Learning Controllable Fair Representationscited by 83
  18. 2019Integer Discrete Flows and Lossless Compressioncited by 82
  19. 2018Differentially Private Fair Learningcited by 76
  20. 2019Overlearning Reveals Sensitive Attributescited by 74
  21. 2020Anomaly Detection with Density Estimationcited by 71
  22. 2020Learning Certified Individually Fair Representationscited by 69
  23. 2019Discrete Flows: Invertible Generative Models of Discrete Datacited by 68
  24. 2020Verifying Individual Fairness in Machine Learning Modelscited by 49
  25. 2019Mitigating Information Leakage in Image Representations: A Maximum Entropy Approachcited by 48
  26. 2020Learning perturbation sets for robust machine learningcited by 48
  27. 2018Probabilistic Verification of Fairness Properties via Concentrationcited by 45
  28. 2021Controllable Guarantees for Fair Outcomes via Contrastive Information Estimationcited by 45
  29. 2019Perfectly Parallel Fairness Certification of Neural Networkscited by 42
  30. 2019AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flowscited by 33
  31. 2014Tight bounds for learning a mixture of two gaussianscited by 29
  32. 2019Learning Fair Representations via an Adversarial Frameworkcited by 29
  33. 2020The Fairness-Accuracy Pareto Frontcited by 26
  34. 2019A Closer Look at the Optimization Landscapes of Generative Adversarial Networkscited by 25
  35. 2019Invariant Representations through Adversarial Forgettingcited by 20
  36. 2018Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Correctionscited by 19
  37. 2020Null-sampling for Interpretable and Fair Representationscited by 16
  38. 2020Fairness in the Eyes of the Data: Certifying Machine-Learning Modelscited by 16

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 12; 2024: 7; 2025: 12; 2026: 1.

38 papers.

Sort:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2023Efficient fair PCA for fair representation learningcited by 23
  3. 2022FARE: Provably Fair Representation Learning with Practical Certificatescited by 21
  4. 2021Latent Space Smoothing for Individually Fair Representationscited by 18
  5. 2023Unraveling Privacy Risks of Individual Fairness in Graph Neural Networkscited by 16
  6. 2022Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Makingcited by 12
  7. 2023CuTS: Customizable Tabular Synthetic Data Generationcited by 12
  8. 2022Certifying Some Distributional Fairness with Subpopulation Decompositioncited by 11
  9. 2024Normalizing Flow-based Differentiable Particle Filterscited by 10
  10. 2023Scalable Infomin Learningcited by 8
  11. 2023Monitoring Algorithmic Fairnesscited by 8
  12. 2025Towards Fair In-Context Learning with Tabular Foundation Modelscited by 8
26 more
  1. 2023Monitoring Algorithmic Fairness under Partial Observationscited by 7
  2. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  3. 202410 Years of Fair Representations: Challenges and Opportunitiescited by 6
  4. 2022FairNorm: Fair and Fast Graph Neural Network Trainingcited by 4
  5. 2024Benchmarking the Fairness of Image Upsampling Methodscited by 3
  6. 2023Counterfactual Reasoning for Bias Evaluation and Detection in a Fairness under Unawareness settingcited by 2
  7. 2023From Principle to Practice: Vertical Data Minimization for Machine Learningcited by 2
  8. 2024Weighted Risk Invariance: Domain Generalization under Invariant Feature Shiftcited by 2
  9. 2024Efficient Fairness-Performance Pareto Front Computationcited by 2
  10. 2025Do Fairness Interventions Come at the Cost of Privacy: Evaluations for Binary Classifierscited by 2
  11. 2025Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyondcited by 2
  12. 2025On Optimal Steering to Achieve Exact Fairnesscited by 2
  13. 2023Learning Fair Representations with High-Confidence Guaranteescited by 1
  14. 2024AdapFair: Ensuring Adaptive Fairness for Machine Learning Operationscited by 1
  15. 2025SoK: Data Minimization in Machine Learningcited by 1
  16. 2025Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domainscited by 1
  17. 2023Counterfactual Fair Opportunity: Measuring Decision Model Fairness with Counterfactual Reasoningcited by 0
  18. 2023A Fair Classifier Embracing Triplet Collapsecited by 0
  19. 2024Back to the Drawing Board for Fair Representation Learningcited by 0
  20. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  21. 2025Simple and Effective Specialized Representations for Fair Classifierscited by 0
  22. 2025Monitoring of Static Fairnesscited by 0
  23. 2025Incorporating Fairness Constraints into Archetypal Analysiscited by 0
  24. 2025Algorithmic Fairness: A Runtime Perspectivecited by 0
  25. 2025Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inferencecited by 0
  26. 2026Is invariance all you need for algorithmic fairness? Removing demographic information can create new biascited by 0