mlsanityData to 14 Oct 2026

10 Years of Fair Representations: Challenges and Opportunities

arXiv 2407.03834 ↗First posted 4 Jul 2024cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Fair Representation Learning (FRL) is a broad set of techniques, mostly based on neural networks, that seeks to learn new representations of data in which sensitive or undesired information has been removed. Methodologically, FRL was pioneered by Richard Zemel et al. about ten years ago. The basic concepts, objectives and evaluation strategies for FRL methodologies remain unchanged to this day. In this paper, we look back at the first ten years of FRL by i) revisiting its theoretical standing in light of recent work in deep learning theory that shows the hardness of removing information in neural network representations and ii) presenting the results of a massive experimentation (225.000 model fits and 110.000 AutoML fits) we conducted with the objective of improving on the common evaluation scenario for FRL. More specifically, we use automated machine learning (AutoML) to adversarially "mine" sensitive information from supposedly fair representations. Our theoretical and experimental analysis suggests that deterministic, unquantized FRL methodologies have serious issues in removing sensitive information, which is especially troubling as they might seem "fair" at first glance.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 30 of its 54 references that are in the map. First posted on arXiv 4 Jul 2024.

Builds on

30 of 54 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  3. 2016Density estimation using Real NVPcited by 2,042
  4. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  5. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  6. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  7. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 503
  8. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 449
  9. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  10. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  11. 2015The Variational Fair Autoencodercited by 223
  12. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 215
18 more
  1. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  2. 2018Invariant Representations without Adversarial Trainingcited by 112
  3. 2016Measuring Fairness in Ranked Outputscited by 81
  4. 2018Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principlecited by 70
  5. 2020The Information Bottleneck Problem and Its Applications in Machine Learningcited by 66
  6. 2019Pairwise Fairness for Ranking and Regressioncited by 58
  7. 2016Learning to Pivot with Adversarial Networkscited by 55
  8. 2018The age of secrecy and unfairness in recidivism predictioncited by 53
  9. 2021Fair Normalizing Flowscited by 38
  10. 2023Beyond Normal: On the Evaluation of Mutual Information Estimatorscited by 37
  11. 2018Reducing Disparate Exposure in Ranking: A Learning To Rank Approachcited by 33
  12. 2019AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flowscited by 33
  13. 2017Provably Fair Representationscited by 22
  14. 2022FARE: Provably Fair Representation Learning with Practical Certificatescited by 21
  15. 2020FaiR-N: Fair and Robust Neural Networks for Structured Datacited by 16
  16. 2022Fair Group-Shared Representations with Normalizing Flowscited by 5
  17. 2022Invariant Representations with Stochastically Quantized Neural Networkscited by 4
  18. 2022Fair Interpretable Representation Learning with Correction Vectorscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 1.

6 papers.

  1. 2024Rethinking Fair Representation Learning for Performance-Sensitive Taskscited by 8
  2. 2025On Optimal Steering to Achieve Exact Fairnesscited by 2
  3. 2025Fairness-aware Anomaly Detection via Fair Projectioncited by 1
  4. 2025Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learningcited by 0
  5. 2025Happiness as a Measure of Fairnesscited by 0
  6. 2026Is invariance all you need for algorithmic fairness? Removing demographic information can create new biascited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Towards Poisoning Fair Representations
  2. 2025Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion Model
  3. 2026Debias Anything: Fairness with Diversity without Supervision in Diffusion Models
  4. 2026Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
  5. 2024INFELM: In-depth Fairness Evaluation of Large Text-To-Image Models
  6. 2023FroSSL: Frobenius Norm Minimization for Efficient Multiview Self-Supervised Learning
  7. 2024Generating Synthetic Fair Syntax-agnostic Data by Learning and Distilling Fair Representation
  8. 2025AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data