# Wasserstein-based fairness interpretability framework for machine learning models

arXiv: https://arxiv.org/abs/2011.03156 · HTML: https://mlsanity.com/paper/2011.03156/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2020.

## Built on by (most cited first, 14 of 14)

- [FairCanary: Rapid Continuous Explainable Fairness](https://mlsanity.com/paper/2106.07057/) (2021)
- [Unified Shapley Framework to Explain Prediction Drift](https://mlsanity.com/paper/2102.07862/) (2021)
- [Model-agnostic bias mitigation methods with regressor distribution control for Wasserstein-based fairness metrics](https://mlsanity.com/paper/2111.11259/) (2021)
- [Retiring DeltaDP: New Distribution-Level Metrics for Demographic Parity](https://mlsanity.com/paper/2301.13443/) (2023)
- [Standardized Interpretable Fairness Measures for Continuous Risk Scores](https://mlsanity.com/paper/2308.11375/) (2023)
- [OT-Net: A Reusable Neural Optimal Transport Solver](https://mlsanity.com/paper/2306.08233/) (2023)
- [Enforcing Fair Predicted Scores on Intervals of Percentiles by Difference-of-Convex Constraints](https://mlsanity.com/paper/2505.12530/) (2025)
- [FiSH: Fair Spatial Hotspots](https://mlsanity.com/paper/2106.06049/) (2021)
- [AI Fairness: from Principles to Practice](https://mlsanity.com/paper/2207.09833/) (2022)
- [Reducing Biases in Record Matching Through Scores Calibration](https://mlsanity.com/paper/2411.01685/) (2024)
- [Explainable post-training bias mitigation with distribution-based fairness metrics](https://mlsanity.com/paper/2504.01223/) (2025)
- [From Fragile to Certified: Wasserstein Audits of Group Fairness Under Distribution Shift](https://mlsanity.com/paper/2509.26241/) (2025)
- [Optimal Transport for Efficient, Unsupervised Anomaly Detection on Industrial Data](https://mlsanity.com/paper/2609.13940/) (2026)
- [Multi-Sensitive Distributional Fairness: Joint Wasserstein Audits and Shapley Allocation](https://mlsanity.com/paper/2610.19252/) (2026)

## Abstract (arXiv)

The objective of this article is to introduce a fairness interpretability framework for measuring and explaining the bias in classification and regression models at the level of a distribution. In our work, we measure the model bias across sub-population distributions in the model output using the Wasserstein metric. To properly quantify the contributions of predictors, we take into account the favorability of both the model and predictors with respect to the non-protected class. The quantification is accomplished by the use of transport theory, which gives rise to the decomposition of the model bias and bias explanations to positive and negative contributions. To gain more insight into the role of favorability and allow for additivity of bias explanations, we adapt techniques from cooperative game theory.