# Explainability for fair machine learning

arXiv: https://arxiv.org/abs/2010.07389 · HTML: https://mlsanity.com/paper/2010.07389/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

## Built on by (most cited first, 30 of 34)

- [Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities](https://mlsanity.com/paper/2102.04257/) (2021)
- [Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations](https://mlsanity.com/paper/2205.07277/) (2022)
- [Fairness and Explainability: Bridging the Gap Towards Fair Model Explanations](https://mlsanity.com/paper/2212.03840/) (2022)
- [Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models](https://mlsanity.com/paper/2206.03945/) (2022)
- [Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decomposition](https://mlsanity.com/paper/2108.05335/) (2021)
- [A Critical Survey on Fairness Benefits of Explainable AI](https://mlsanity.com/paper/2310.13007/) (2023)
- [ALMANACS: A Simulatability Benchmark for Language Model Explainability](https://mlsanity.com/paper/2312.12747/) (2023)
- [How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis](https://mlsanity.com/paper/2206.00667/) (2022)
- [Fool SHAP with Stealthily Biased Sampling](https://mlsanity.com/paper/2205.15419/) (2022)
- [Understanding Disparities in Post Hoc Machine Learning Explanation](https://mlsanity.com/paper/2401.14539/) (2024)
- [A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures](https://mlsanity.com/paper/2404.00673/) (2024)
- [Unified Shapley Framework to Explain Prediction Drift](https://mlsanity.com/paper/2102.07862/) (2021)
- [Explainable Global Fairness Verification of Tree-Based Classifiers](https://mlsanity.com/paper/2209.13179/) (2022)
- [Manifestations of Xenophobia in AI Systems](https://mlsanity.com/paper/2212.07877/) (2022)
- [SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning](https://mlsanity.com/paper/2312.16191/) (2023)
- [Procedural Fairness in Machine Learning](https://mlsanity.com/paper/2404.01877/) (2024)
- [On Explaining Unfairness: An Overview](https://mlsanity.com/paper/2402.10762/) (2024)
- [Interpretable Ensembles of Hyper-Rectangles as Base Models](https://mlsanity.com/paper/2303.08625/) (2023)
- [Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data](https://mlsanity.com/paper/2501.13818/) (2025)
- [Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration](https://mlsanity.com/paper/2505.00802/) (2025)
- [Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions](https://mlsanity.com/paper/2302.09190/) (2023)
- [Feature Importance Disparities for Data Bias Investigations](https://mlsanity.com/paper/2303.01704/) (2023)
- [Fair Feature Importance Scores for Interpreting Tree-Based Methods and Surrogates](https://mlsanity.com/paper/2310.04352/) (2023)
- [Towards Fair and Calibrated Models](https://mlsanity.com/paper/2310.10399/) (2023)
- [REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Values](https://mlsanity.com/paper/2403.08880/) (2024)
- [Constructing Fair Latent Space for Intersection of Fairness and Explainability](https://mlsanity.com/paper/2412.17523/) (2024)
- [MESD: A Risk-Sensitive Metric for Explanation Fairness Across Intersectional Subgroups](https://mlsanity.com/paper/2603.13452/) (2026)
- [Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI](https://mlsanity.com/paper/2605.09852/) (2026)
- [Shapley value-based approaches to explain the robustness of classifiers in machine learning](https://mlsanity.com/paper/2209.04254/) (2022)
- [Tensions Between the Proxies of Human Values in AI](https://mlsanity.com/paper/2212.07508/) (2022)

## Abstract (arXiv)

As the decisions made or influenced by machine learning models increasingly impact our lives, it is crucial to detect, understand, and mitigate unfairness. But even simply determining what "unfairness" should mean in a given context is non-trivial: there are many competing definitions, and choosing between them often requires a deep understanding of the underlying task. It is thus tempting to use model explainability to gain insights into model fairness, however existing explainability tools do not reliably indicate whether a model is indeed fair. In this work we present a new approach to explaining fairness in machine learning, based on the Shapley value paradigm. Our fairness explanations attribute a model's overall unfairness to individual input features, even in cases where the model does not operate on sensitive attributes directly. Moreover, motivated by the linearity of Shapley explainability, we propose a meta algorithm for applying existing training-time fairness interventions, wherein one trains a perturbation to the original model, rather than a new model entirely. By explaining the original model, the perturbation, and the fair-corrected model, we gain insight into the accuracy-fairness trade-off that is being made by the intervention. We further show that this meta algorithm enjoys both flexibility and stability benefits with no loss in performance.