# A Distributionally Robust Approach to Fair Classification

arXiv: https://arxiv.org/abs/2007.09530 · HTML: https://mlsanity.com/paper/2007.09530/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2020.

## Built on by (most cited first, 30 of 43)

- [Fair Mixup: Fairness via Interpolation](https://mlsanity.com/paper/2103.06503/) (2021)
- [Diagnosing failures of fairness transfer across distribution shift in real-world medical settings](https://mlsanity.com/paper/2202.01034/) (2022)
- [Sinkhorn Distributionally Robust Optimization](https://mlsanity.com/paper/2109.11926/) (2021)
- [Understanding Instance-Level Impact of Fairness Constraints](https://mlsanity.com/paper/2206.15437/) (2022)
- [A Stochastic Optimization Framework for Fair Risk Minimization](https://mlsanity.com/paper/2102.12586/) (2021)
- [Supervised Algorithmic Fairness in Distribution Shifts: A Survey](https://mlsanity.com/paper/2402.01327/) (2024)
- [Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization](https://mlsanity.com/paper/2303.00442/) (2023)
- [Poisoning Attacks on Fair Machine Learning](https://mlsanity.com/paper/2110.08932/) (2021)
- [Fairness-Aware PAC Learning from Corrupted Data](https://mlsanity.com/paper/2102.06004/) (2021)
- [Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution](https://mlsanity.com/paper/2103.06263/) (2021)
- [Algorithmic Bias and Data Bias: Understanding the Relation between Distributionally Robust Optimization and Data Curation](https://mlsanity.com/paper/2106.09467/) (2021)
- [Flow-based Distributionally Robust Optimization](https://mlsanity.com/paper/2310.19253/) (2023)
- [Wasserstein Robust Classification with Fairness Constraints](https://mlsanity.com/paper/2103.06828/) (2021)
- [Robust Fairness-aware Learning Under Sample Selection Bias](https://mlsanity.com/paper/2105.11570/) (2021)
- [Distributionally Robust Fair Principal Components via Geodesic Descents](https://mlsanity.com/paper/2202.03071/) (2022)
- [The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning](https://mlsanity.com/paper/2410.09600/) (2024)
- [Consistent Range Approximation for Fair Predictive Modeling](https://mlsanity.com/paper/2212.10839/) (2022)
- [Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously](https://mlsanity.com/paper/2311.13816/) (2023)
- [Metrizing Fairness](https://mlsanity.com/paper/2205.15049/) (2022)
- [Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces](https://mlsanity.com/paper/2308.08938/) (2023)
- [f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization](https://mlsanity.com/paper/2312.03259/) (2023)
- [Fair Regression under Sample Selection Bias](https://mlsanity.com/paper/2110.04372/) (2021)
- [Distributionally Robust Data Join](https://mlsanity.com/paper/2202.05797/) (2022)
- [On the Fairness ROAD: Robust Optimization for Adversarial Debiasing](https://mlsanity.com/paper/2310.18413/) (2023)
- [Inducing Group Fairness in Prompt-Based Language Model Decisions](https://mlsanity.com/paper/2406.16738/) (2024)
- [Is it Still Fair? A Comparative Evaluation of Fairness Algorithms through the Lens of Covariate Drift](https://mlsanity.com/paper/2409.12428/) (2024)
- [A Survey on Preserving Fairness Guarantees in Changing Environments](https://mlsanity.com/paper/2211.07530/) (2022)
- [Certification of Distributional Individual Fairness](https://mlsanity.com/paper/2311.11911/) (2023)
- [Wasserstein Distributionally Robust Regret Optimization](https://mlsanity.com/paper/2504.10796/) (2025)
- [Towards A Scalable Solution for Improving Multi-Group Fairness in Compositional Classification](https://mlsanity.com/paper/2307.05728/) (2023)

## Abstract (arXiv)

We propose a distributionally robust logistic regression model with an unfairness penalty that prevents discrimination with respect to sensitive attributes such as gender or ethnicity. This model is equivalent to a tractable convex optimization problem if a Wasserstein ball centered at the empirical distribution on the training data is used to model distributional uncertainty and if a new convex unfairness measure is used to incentivize equalized opportunities. We demonstrate that the resulting classifier improves fairness at a marginal loss of predictive accuracy on both synthetic and real datasets. We also derive linear programming-based confidence bounds on the level of unfairness of any pre-trained classifier by leveraging techniques from optimal uncertainty quantification over Wasserstein balls.