mlsanityData to 7 Oct 2026

MMD-B-Fair: Learning Fair Representations with Statistical Testing

arXiv 2211.07907 ↗First posted 15 Nov 2022stat.ML cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

We introduce a method, MMD-B-Fair, to learn fair representations of data via kernel two-sample testing. We find neural features of our data where a maximum mean discrepancy (MMD) test cannot distinguish between representations of different sensitive groups, while preserving information about the target attributes. Minimizing the power of an MMD test is more difficult than maximizing it (as done in previous work), because the test threshold's complex behavior cannot be simply ignored. Our method exploits the simple asymptotics of block testing schemes to efficiently find fair representations without requiring complex adversarial optimization or generative modelling schemes widely used by existing work on fair representation learning. We evaluate our approach on various datasets, showing its ability to ``hide'' information about sensitive attributes, and its effectiveness in downstream transfer tasks.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 30 of its 52 references that are in the map. First posted on arXiv 15 Nov 2022.

Builds on

30 of 52 references.

References · 30

  1. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  2. 2018Demystifying MMD GANscited by 1,268
  3. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  4. 2015Deep Kernel Learningcited by 440
  5. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  6. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  7. 2016Revisiting Classifier Two-Sample Testscited by 258
  8. 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 251
  9. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  10. 2015The Variational Fair Autoencodercited by 223
  11. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  12. 2015Censoring Representations with an Adversarycited by 191
18 more
  1. 2020Learning Deep Kernels for Non-Parametric Two-Sample Testscited by 129
  2. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  3. 2019Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learningcited by 116
  4. 2016Generative Models and Model Criticism via Optimized Maximum Mean Discrepancycited by 99
  5. 2018A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indicescited by 97
  6. 2019Conditional Learning of Fair Representationscited by 78
  7. 2019Predictive Inequity in Object Detectioncited by 77
  8. 2021Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Testscited by 77
  9. 2021Self-Supervised Learning with Kernel Dependence Maximizationcited by 77
  10. 2021Controllable Guarantees for Fair Outcomes via Contrastive Information Estimationcited by 45
  11. 2016Classification accuracy as a proxy for two sample testingcited by 39
  12. 2018Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variancecited by 33
  13. 2015A Test of Relative Similarity For Model Selection in Generative Modelscited by 25
  14. 2022Learning fair representation with a parametric integral probability metriccited by 20
  15. 2021Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifoldcited by 18
  16. 2015Adaptivity and Computation-Statistics Tradeoffs for Kernel and Distance based High Dimensional Two Sample Testingcited by 14
  17. 2019Unbiased estimators for the variance of MMD estimatorscited by 10
  18. 2013B-tests: Low Variance Kernel Two-Sample Testscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 7; 2026: 2.

13 papers.

Sort:

  1. 2023MMD-FUSE: Learning and Combining Kernels for Two-Sample Testing Without Data Splittingcited by 33
  2. 2025Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metricscited by 7
  3. 2025On the Hardness of Conditional Independence Testing In Practicecited by 6
  4. 2024A Unified Data Representation Learning for Non-parametric Two-sample Testingcited by 5
  5. 2025On the geometry and topology of representations: the manifolds of modular additioncited by 3
  6. 2024Learning Representations for Independence Testingcited by 2
  7. 2023Learning Fair Representations with High-Confidence Guaranteescited by 1
  8. 2025ReLU integral probability metric and its applicationscited by 1
  9. 2025Maximum Mean Discrepancy with Unequal Sample Sizes via Generalized U-Statisticscited by 1
  10. 2025Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learningcited by 0
  11. 2025Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inferencecited by 0
  12. 2026Finite-Sample Unbiased Variance of MMD under Unbalanced Sampling: Exact Estimation and Quasi-Linear Computationcited by 0
1 more
  1. 2026A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributescited by 0