mlsanityData to 14 Oct 2026

Proxy Fairness

arXiv 1806.11212 ↗First posted 28 Jun 2018cs.LG stat.MLcited by 29

Not on the map. Why?

Abstract (arXiv)

We consider the problem of improving fairness when one lacks access to a dataset labeled with protected groups, making it difficult to take advantage of strategies that can improve fairness but require protected group labels, either at training or runtime. To address this, we investigate improving fairness metrics for proxy groups, and test whether doing so results in improved fairness for the true sensitive groups. Results on benchmark and real-world datasets demonstrate that such a proxy fairness strategy can work well in practice. However, we caution that the effectiveness likely depends on the choice of fairness metric, as well as how aligned the proxy groups are with the true protected groups in terms of the constrained model parameters.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 5; 2023: 6; 2024: 6; 2025: 4; 2026: 2.

29 papers.

Sort:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2021Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communitiescited by 40
  3. 2021Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Informationcited by 33
  4. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  5. 2021Fair Classification with Adversarial Perturbationscited by 23
  6. 2021Fairness without the sensitive attribute via Causal Variational Autoencodercited by 21
  7. 2021Modeling Techniques for Machine Learning Fairness: A Surveycited by 17
  8. 2023Causal Fairness under Unobserved Confounding: A Neural Sensitivity Frameworkcited by 10
  9. 2022Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivitycited by 8
  10. 2021Measuring Model Fairness under Noisy Covariates: A Theoretical Perspectivecited by 7
  11. 2022Fair Classification via Domain Adaptation: A Dual Adversarial Learning Approachcited by 6
  12. 2024FairJob: A Real-World Dataset for Fairness in Online Systemscited by 6
17 more
  1. 2024Fairness without Sensitive Attributes via Knowledge Sharingcited by 6
  2. 2025Preserving AUC Fairness in Learning with Noisy Protected Groupscited by 6
  3. 2022Estimating and Controlling for Equalized Odds via Sensitive Attribute Predictorscited by 5
  4. 2022Manifestations of Xenophobia in AI Systemscited by 4
  5. 2023Fairness Under Demographic Scarce Regimecited by 4
  6. 2024Accurate and Data-Efficient Toxicity Prediction when Annotators Disagreecited by 3
  7. 2025Fair Text Classification via Transferable Representationscited by 3
  8. 2023Group Fairness with Uncertainty in Sensitive Attributescited by 2
  9. 2024Fair Recommendations with Limited Sensitive Attributes: A Distributionally Robust Optimization Approachcited by 2
  10. 2025Multiaccuracy and Multicalibration via Proxy Groupscited by 2
  11. 2026Multi-Distribution Robust Conformal Predictioncited by 2
  12. 2023The Effects of Mixed Sample Data Augmentation are Class Dependentcited by 1
  13. 2025On Explaining Proxy Discrimination and Unfairness in Individual Decisions Made by AI Systemscited by 1
  14. 2023TIDE: Textual Identity Detection for Evaluating and Augmenting Classification and Language Modelscited by 0
  15. 2024Fairness Risks for Group-conditionally Missing Demographicscited by 0
  16. 2024De-Biasing Models of Biased Decisions: A Comparison of Methods Using Mortgage Application Datacited by 0
  17. 2026Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profilescited by 0