# Robust Optimization for Fairness with Noisy Protected Groups

arXiv: https://arxiv.org/abs/2002.09343 · HTML: https://mlsanity.com/paper/2002.09343/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Feb 2020.

## Built on by (most cited first, 30 of 78)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective](https://mlsanity.com/paper/2112.06409/) (2021)
- [Examining and Combating Spurious Features under Distribution Shift](https://mlsanity.com/paper/2106.07171/) (2021)
- [Sample Selection for Fair and Robust Training](https://mlsanity.com/paper/2110.14222/) (2021)
- [Learning Fair Classifiers with Partially Annotated Group Labels](https://mlsanity.com/paper/2111.14581/) (2021)
- [Fairness for Image Generation with Uncertain Sensitive Attributes](https://mlsanity.com/paper/2106.12182/) (2021)
- [Privacy and Fairness in Federated Learning: on the Perspective of Trade-off](https://mlsanity.com/paper/2306.14123/) (2023)
- [BARACK: Partially Supervised Group Robustness With Guarantees](https://mlsanity.com/paper/2201.00072/) (2021)
- [A Sociotechnical View of Algorithmic Fairness](https://mlsanity.com/paper/2110.09253/) (2021)
- [Fair Classification with Adversarial Perturbations](https://mlsanity.com/paper/2106.05964/) (2021)
- [Differentially Private SGDA for Minimax Problems](https://mlsanity.com/paper/2201.09046/) (2022)
- [Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization](https://mlsanity.com/paper/2303.00442/) (2023)
- [Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions](https://mlsanity.com/paper/2301.11781/) (2023)
- [Fairness-Aware PAC Learning from Corrupted Data](https://mlsanity.com/paper/2102.06004/) (2021)
- [What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective](https://mlsanity.com/paper/2206.04101/) (2022)
- [Multiaccurate Proxies for Downstream Fairness](https://mlsanity.com/paper/2107.04423/) (2021)
- [Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes](https://mlsanity.com/paper/2210.03175/) (2022)
- [Fair Ranking with Noisy Protected Attributes](https://mlsanity.com/paper/2211.17067/) (2022)
- [Fair Sequential Selection Using Supervised Learning Models](https://mlsanity.com/paper/2110.13986/) (2021)
- [Distributionally Robust Optimization via Ball Oracle Acceleration](https://mlsanity.com/paper/2203.13225/) (2022)
- [Improving Fair Training under Correlation Shifts](https://mlsanity.com/paper/2302.02323/) (2023)
- [Algorithmic Bias and Data Bias: Understanding the Relation between Distributionally Robust Optimization and Data Curation](https://mlsanity.com/paper/2106.09467/) (2021)
- [Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial](https://mlsanity.com/paper/2107.05913/) (2021)
- [A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms](https://mlsanity.com/paper/2204.10233/) (2022)
- [Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing](https://mlsanity.com/paper/2206.11423/) (2022)
- [Wasserstein Robust Classification with Fairness Constraints](https://mlsanity.com/paper/2103.06828/) (2021)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [AIM: Attributing, Interpreting, Mitigating Data Unfairness](https://mlsanity.com/paper/2406.08819/) (2024)
- [The Role of Learning Algorithms in Collective Action](https://mlsanity.com/paper/2405.06582/) (2024)
- [Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions](https://mlsanity.com/paper/2107.09546/) (2021)

## Abstract (arXiv)

Many existing fairness criteria for machine learning involve equalizing some metric across protected groups such as race or gender. However, practitioners trying to audit or enforce such group-based criteria can easily face the problem of noisy or biased protected group information. First, we study the consequences of naively relying on noisy protected group labels: we provide an upper bound on the fairness violations on the true groups G when the fairness criteria are satisfied on noisy groups hatG. Second, we introduce two new approaches using robust optimization that, unlike the naive approach of only relying on hatG, are guaranteed to satisfy fairness criteria on the true protected groups G while minimizing a training objective. We provide theoretical guarantees that one such approach converges to an optimal feasible solution. Using two case studies, we show empirically that the robust approaches achieve better true group fairness guarantees than the naive approach.