# Optimal Transport for Fairness: Archival Data Repair using Small Research Data Sets

arXiv: https://arxiv.org/abs/2403.13864 · HTML: https://mlsanity.com/paper/2403.13864/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 42 references that are in the map.
- First posted on arXiv 20 Mar 2024.

## Builds on (most cited first, 15 of 15)

- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [A comparative study of fairness-enhancing interventions in machine learning](https://mlsanity.com/paper/1802.04422/) (2018)
- [Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm](https://mlsanity.com/paper/1802.04367/) (2018)
- [Fair Regression with Wasserstein Barycenters](https://mlsanity.com/paper/2006.07286/) (2020)
- [On Robust Optimal Transport: Computational Complexity and Barycenter Computation](https://mlsanity.com/paper/2102.06857/) (2021)
- [On the complexity of the optimal transport problem with graph-structured cost](https://mlsanity.com/paper/2110.00627/) (2021)
- [Confidence Intervals for Testing Disparate Impact in Fair Learning](https://mlsanity.com/paper/1807.06362/) (2018)
- [Feature Robust Optimal Transport for High-dimensional Data](https://mlsanity.com/paper/2005.12123/) (2020)
- [Group-blind optimal transport to group parity and its constrained variants](https://mlsanity.com/paper/2310.11407/) (2023)

## Built on by (most cited first, 3 of 3)

- [Overcoming Representation Bias in Fairness-Aware data Repair using Optimal Transport](https://mlsanity.com/paper/2410.02840/) (2024)
- [Auditing and Enforcing Conditional Fairness via Optimal Transport](https://mlsanity.com/paper/2410.14029/) (2024)
- [humancompatible.interconnect: Testing Properties of Repeated Uses of Interconnections of AI Systems](https://mlsanity.com/paper/2507.09626/) (2025)

## Abstract (arXiv)

With the advent of the AI Act and other regulations, there is now an urgent need for algorithms that repair unfairness in training data. In this paper, we define fairness in terms of conditional independence between protected attributes (S) and features (X), given unprotected attributes (U). We address the important setting in which torrents of archival data need to be repaired, using only a small proportion of these data, which are S|U-labelled (the research data). We use the latter to design optimal transport (OT)-based repair plans on interpolated supports. This allows em off-sample, labelled, archival data to be repaired, subject to stationarity assumptions. It also significantly reduces the size of the supports of the OT plans, with correspondingly large savings in the cost of their design and of their em sequential/ application to the off-sample data. We provide detailed experimental results with simulated and benchmark real data (the Adult data set). Our performance figures demonstrate effective repair -- in the sense of quenching conditional dependence -- of large quantities of off-sample, labelled (archival) data.