# Ensuring Fairness Beyond the Training Data

arXiv: https://arxiv.org/abs/2007.06029 · HTML: https://mlsanity.com/paper/2007.06029/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2020.

## Built on by (most cited first, 30 of 35)

- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Sample Selection for Fair and Robust Training](https://mlsanity.com/paper/2110.14222/) (2021)
- [Fairness Transferability Subject to Bounded Distribution Shift](https://mlsanity.com/paper/2206.00129/) (2022)
- [A Sociotechnical View of Algorithmic Fairness](https://mlsanity.com/paper/2110.09253/) (2021)
- [Supervised Algorithmic Fairness in Distribution Shifts: A Survey](https://mlsanity.com/paper/2402.01327/) (2024)
- [Characterizing the risk of fairwashing](https://mlsanity.com/paper/2106.07504/) (2021)
- [Certifying Robustness to Programmable Data Bias in Decision Trees](https://mlsanity.com/paper/2110.04363/) (2021)
- [Transferring Fairness under Distribution Shifts via Fair Consistency Regularization](https://mlsanity.com/paper/2206.12796/) (2022)
- [Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization](https://mlsanity.com/paper/2303.00442/) (2023)
- [Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing](https://mlsanity.com/paper/2206.11423/) (2022)
- [How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts](https://mlsanity.com/paper/2207.01168/) (2022)
- [Fairness with Continuous Optimal Transport](https://mlsanity.com/paper/2101.02084/) (2021)
- [Graph Fairness Learning under Distribution Shifts](https://mlsanity.com/paper/2401.16784/) (2024)
- [Segmenting across places: The need for fair transfer learning with satellite imagery](https://mlsanity.com/paper/2204.04358/) (2022)
- [Exploring Bias and Prediction Metrics to Characterise the Fairness of Machine Learning for Equity-Centered Public Health Decision-Making: A Narrative Review](https://mlsanity.com/paper/2408.13295/) (2024)
- [GDDA: Semantic OOD Detection on Graphs under Covariate Shift via Score-Based Diffusion Models](https://mlsanity.com/paper/2410.17526/) (2024)
- [FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networks](https://mlsanity.com/paper/2206.00553/) (2022)
- [Manifestations of Xenophobia in AI Systems](https://mlsanity.com/paper/2212.07877/) (2022)
- [Group-blind optimal transport to group parity and its constrained variants](https://mlsanity.com/paper/2310.11407/) (2023)
- [DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models](https://mlsanity.com/paper/2309.09944/) (2023)
- [On the Fairness ROAD: Robust Optimization for Adversarial Debiasing](https://mlsanity.com/paper/2310.18413/) (2023)
- [Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives](https://mlsanity.com/paper/2502.16841/) (2025)
- [How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies](https://mlsanity.com/paper/2207.04581/) (2022)
- [A Survey on Preserving Fairness Guarantees in Changing Environments](https://mlsanity.com/paper/2211.07530/) (2022)
- [Fairness under Covariate Shift: Improving Fairness-Accuracy tradeoff with few Unlabeled Test Samples](https://mlsanity.com/paper/2310.07535/) (2023)
- [Bias Begins with Data: The FairGround Corpus for Robust and Reproducible Research on Algorithmic Fairness](https://mlsanity.com/paper/2510.22363/) (2025)
- [Trustworthy Representation Learning Across Domains](https://mlsanity.com/paper/2308.12315/) (2023)
- [Towards Fair and Calibrated Models](https://mlsanity.com/paper/2310.10399/) (2023)
- [Responsible AI (RAI) Games and Ensembles](https://mlsanity.com/paper/2310.18832/) (2023)

## Abstract (arXiv)

We initiate the study of fair classifiers that are robust to perturbations in the training distribution. Despite recent progress, the literature on fairness has largely ignored the design of fair and robust classifiers. In this work, we develop classifiers that are fair not only with respect to the training distribution, but also for a class of distributions that are weighted perturbations of the training samples. We formulate a min-max objective function whose goal is to minimize a distributionally robust training loss, and at the same time, find a classifier that is fair with respect to a class of distributions. We first reduce this problem to finding a fair classifier that is robust with respect to the class of distributions. Based on online learning algorithm, we develop an iterative algorithm that provably converges to such a fair and robust solution. Experiments on standard machine learning fairness datasets suggest that, compared to the state-of-the-art fair classifiers, our classifier retains fairness guarantees and test accuracy for a large class of perturbations on the test set. Furthermore, our experiments show that there is an inherent trade-off between fairness robustness and accuracy of such classifiers.