# Proxy Fairness

arXiv: https://arxiv.org/abs/1806.11212 · HTML: https://mlsanity.com/paper/1806.11212/

## Key facts

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

## Built on by (most cited first, 29 of 29)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities](https://mlsanity.com/paper/2102.04257/) (2021)
- [Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information](https://mlsanity.com/paper/2102.08410/) (2021)
- [Privacy and Fairness in Federated Learning: on the Perspective of Trade-off](https://mlsanity.com/paper/2306.14123/) (2023)
- [Fair Classification with Adversarial Perturbations](https://mlsanity.com/paper/2106.05964/) (2021)
- [Fairness without the sensitive attribute via Causal Variational Autoencoder](https://mlsanity.com/paper/2109.04999/) (2021)
- [Modeling Techniques for Machine Learning Fairness: A Survey](https://mlsanity.com/paper/2111.03015/) (2021)
- [Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework](https://mlsanity.com/paper/2311.18460/) (2023)
- [Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity](https://mlsanity.com/paper/2211.02139/) (2022)
- [Measuring Model Fairness under Noisy Covariates: A Theoretical Perspective](https://mlsanity.com/paper/2105.09985/) (2021)
- [Fair Classification via Domain Adaptation: A Dual Adversarial Learning Approach](https://mlsanity.com/paper/2206.03656/) (2022)
- [FairJob: A Real-World Dataset for Fairness in Online Systems](https://mlsanity.com/paper/2407.03059/) (2024)
- [Fairness without Sensitive Attributes via Knowledge Sharing](https://mlsanity.com/paper/2409.18470/) (2024)
- [Preserving AUC Fairness in Learning with Noisy Protected Groups](https://mlsanity.com/paper/2505.18532/) (2025)
- [Estimating and Controlling for Equalized Odds via Sensitive Attribute Predictors](https://mlsanity.com/paper/2207.12497/) (2022)
- [Manifestations of Xenophobia in AI Systems](https://mlsanity.com/paper/2212.07877/) (2022)
- [Fairness Under Demographic Scarce Regime](https://mlsanity.com/paper/2307.13081/) (2023)
- [Accurate and Data-Efficient Toxicity Prediction when Annotators Disagree](https://mlsanity.com/paper/2410.12217/) (2024)
- [Fair Text Classification via Transferable Representations](https://mlsanity.com/paper/2503.07691/) (2025)
- [Group Fairness with Uncertainty in Sensitive Attributes](https://mlsanity.com/paper/2302.08077/) (2023)
- [Fair Recommendations with Limited Sensitive Attributes: A Distributionally Robust Optimization Approach](https://mlsanity.com/paper/2405.01063/) (2024)
- [Multiaccuracy and Multicalibration via Proxy Groups](https://mlsanity.com/paper/2503.02870/) (2025)
- [Multi-Distribution Robust Conformal Prediction](https://mlsanity.com/paper/2601.02998/) (2026)
- [The Effects of Mixed Sample Data Augmentation are Class Dependent](https://mlsanity.com/paper/2307.09136/) (2023)
- [On Explaining Proxy Discrimination and Unfairness in Individual Decisions Made by AI Systems](https://mlsanity.com/paper/2509.25662/) (2025)
- [TIDE: Textual Identity Detection for Evaluating and Augmenting Classification and Language Models](https://mlsanity.com/paper/2309.04027/) (2023)
- [Fairness Risks for Group-conditionally Missing Demographics](https://mlsanity.com/paper/2402.13393/) (2024)
- [De-Biasing Models of Biased Decisions: A Comparison of Methods Using Mortgage Application Data](https://mlsanity.com/paper/2405.00910/) (2024)
- [Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles](https://mlsanity.com/paper/2606.12088/) (2026)

## 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.