mlsanityData to 14 Oct 2026

Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics

arXiv 2505.06435 ↗First posted 9 May 2025stat.ML cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

AI fairness, also known as algorithmic fairness, aims to ensure that algorithms operate without bias or discrimination towards any individual or group. Among various AI algorithms, the Fair Representation Learning (FRL) approach has gained significant interest in recent years. However, existing FRL algorithms have a limitation: they are primarily designed for categorical sensitive attributes and thus cannot be applied to continuous sensitive attributes, such as age or income. In this paper, we propose an FRL algorithm for continuous sensitive attributes. First, we introduce a measure called the Expectation of Integral Probability Metrics (EIPM) to assess the fairness level of representation space for continuous sensitive attributes. We demonstrate that if the distribution of the representation has a low EIPM value, then any prediction head constructed on the top of the representation become fair, regardless of the selection of the prediction head. Furthermore, EIPM possesses a distinguished advantage in that it can be accurately estimated using our proposed estimator with finite samples. Based on these properties, we propose a new FRL algorithm called Fair Representation using EIPM with MMD (FREM). Experimental evidences show that FREM outperforms other baseline methods.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 38 of its 72 references that are in the map. First posted on arXiv 9 May 2025.

Builds on

38 of 72 references.

References · 38

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  3. 2019Simplifying Graph Convolutional Networkscited by 1,477
  4. 2014Certifying and removing disparate impactcited by 715
  5. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  6. 2017Self-Normalizing Neural Networkscited by 598
  7. 2018A Reductions Approach to Fair Classificationcited by 587
  8. 2017Algorithmic decision making and the cost of fairnesscited by 403
  9. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  10. 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 254
  11. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  12. 2015The Variational Fair Autoencodercited by 223
26 more
  1. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  2. 2015Censoring Representations with an Adversarycited by 192
  3. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  4. 2019Wasserstein Fair Classificationcited by 131
  5. 2021Fair Mixup: Fairness via Interpolationcited by 109
  6. 2018Learning Controllable Fair Representationscited by 83
  7. 2020Fairness by Learning Orthogonal Disentangled Representationscited by 76
  8. 2020Learning Certified Individually Fair Representationscited by 69
  9. 2016Satisfying Real-world Goals with Dataset Constraintscited by 68
  10. 2021Controllable Guarantees for Fair Outcomes via Contrastive Information Estimationcited by 45
  11. 2022Learning Fair Representation via Distributional Contrastive Disentanglementcited by 31
  12. 2019Learning Fair Representations via an Adversarial Frameworkcited by 29
  13. 2021Fair Representation Learning for Heterogeneous Information Networkscited by 28
  14. 2022Fair Representation Learning through Implicit Path Alignmentcited by 22
  15. 2022FARE: Provably Fair Representation Learning with Practical Certificatescited by 21
  16. 2022Learning fair representation with a parametric integral probability metriccited by 20
  17. 2021Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifoldcited by 18
  18. 2020Distributional Robustness with IPMs and links to Regularization and GANscited by 17
  19. 2021Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Taskscited by 16
  20. 2022Learn what matters: cross-domain imitation learning with task-relevant embeddingscited by 14
  21. 2022MMD-B-Fair: Learning Fair Representations with Statistical Testingcited by 13
  22. 2020Learning Smooth and Fair Representationscited by 12
  23. 2020FairNN- Conjoint Learning of Fair Representations for Fair Decisionscited by 11
  24. 2023Covariate balancing using the integral probability metric for causal inferencecited by 9
  25. 2023Generalized Disparate Impact for Configurable Fairness Solutions in MLcited by 7
  26. 2020Seeing Red: PPG Biometrics Using Smartphone Camerascited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025On the geometry and topology of representations: the manifolds of modular additioncited by 3
  2. 2025Doubly-Regressing Approach for Subgroup Fairnesscited by 1
  3. 2026AIFS-SUBS: Extending Data-Driven Forecasting to Sub-Seasonal Timescalescited by 1
  4. 2025Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learningcited by 0
  5. 2025Extending Fair Null-Space Projections for Continuous Attributes to Kernel Methodscited by 0
  6. 2026A nonparametric two-sample test using a parametric integral probability metriccited by 0
  7. 2026A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributescited by 0