mlsanityData to 7 Oct 2026

Efficient fair PCA for fair representation learning

arXiv 2302.13319 ↗First posted 26 Feb 2023stat.ML cs.CY cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

We revisit the problem of fair principal component analysis (PCA), where the goal is to learn the best low-rank linear approximation of the data that obfuscates demographic information. We propose a conceptually simple approach that allows for an analytic solution similar to standard PCA and can be kernelized. Our methods have the same complexity as standard PCA, or kernel PCA, and run much faster than existing methods for fair PCA based on semidefinite programming or manifold optimization, while achieving similar results.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 28 of its 49 references that are in the map. First posted on arXiv 26 Feb 2023.

Builds on

28 of 49 references.

References · 28

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2018A Reductions Approach to Fair Classificationcited by 585
  4. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  5. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  6. 2015The Variational Fair Autoencodercited by 223
  7. 2015Censoring Representations with an Adversarycited by 191
  8. 2018Fair Clustering Through Fairletscited by 176
  9. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
  10. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  11. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  12. 2018Invariant Representations without Adversarial Trainingcited by 111
16 more
  1. 2022Linear Adversarial Concept Erasurecited by 98
  2. 2018Learning Controllable Fair Representationscited by 83
  3. 2020Fairness by Learning Orthogonal Disentangled Representationscited by 76
  4. 2018The Price of Fair PCA: One Extra Dimensioncited by 67
  5. 2019Conscientious Classification: A Data Scientist's Guide to Discrimination-Aware Classificationcited by 55
  6. 2019Eigenvalue and Generalized Eigenvalue Problems: Tutorialcited by 45
  7. 2021Fair Normalizing Flowscited by 38
  8. 2022Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Informationcited by 33
  9. 2022Learning Fair Representation via Distributional Contrastive Disentanglementcited by 31
  10. 2019Learning Fair Representations via an Adversarial Frameworkcited by 29
  11. 2018Convex Formulations for Fair Principal Component Analysiscited by 20
  12. 2018Gradient Reversal Against Discriminationcited by 20
  13. 2019Efficient Fair Principal Component Analysiscited by 20
  14. 2021Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifoldcited by 18
  15. 2018Right for the Right Reason: Training Agnostic Networkscited by 7
  16. 2021Obstructing Classification via Projectioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 5; 2025: 10; 2026: 2.

23 papers.

Sort:

By area:

  1. 2023LEACE: Perfect linear concept erasure in closed formcited by 254
  2. 2024Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categoriescited by 74
  3. 2025SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Modelscited by 28
  4. 2023Evaluating the Fairness of Discriminative Foundation Models in Computer Visioncited by 12
  5. 2024Fair CoVariance Neural Networkscited by 6
  6. 2025FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Modelscited by 6
  7. 2023A Joint Matrix Factorization Analysis of Multilingual Representationscited by 5
  8. 2023Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpointcited by 5
  9. 2023Fair Canonical Correlation Analysiscited by 3
  10. 2025Preserving Task-Relevant Information Under Linear Concept Removalcited by 3
  11. 2024Surgical Feature-Space Decomposition of LLMs: Why, When and How?cited by 2
  12. 2024On Socially Fair Low-Rank Approximation and Column Subset Selectioncited by 2
11 more
  1. 2023Learning Fair Representations with High-Confidence Guaranteescited by 1
  2. 2024AdapFair: Ensuring Adaptive Fairness for Machine Learning Operationscited by 1
  3. 2025FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Modelcited by 1
  4. 2025Hidden Convexity of Fair PCA and Fast Solver via Eigenvalue Optimizationcited by 1
  5. 2025Fair CCA for Fair Representation Learning: An ADNI Studycited by 1
  6. 2026Enhancing SAE-based Steering via Neighbor Integrated Feature Selectioncited by 1
  7. 2025PLS-based approach for fair representation learningcited by 0
  8. 2025Fair PCA, One Component at a Timecited by 0
  9. 2025Incorporating Fairness Constraints into Archetypal Analysiscited by 0
  10. 2025Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inferencecited by 0
  11. 2026Generalizing Fair Top-k Selection: An Integrative Approachcited by 0