# Fairness by Explicability and Adversarial SHAP Learning

arXiv: https://arxiv.org/abs/2003.05330 · HTML: https://mlsanity.com/paper/2003.05330/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 9 of 9)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Why do explanations fail? A typology and discussion on failures in XAI](https://mlsanity.com/paper/2405.13474/) (2024)
- [Algorithmic decision making methods for fair credit scoring](https://mlsanity.com/paper/2209.07912/) (2022)
- [Multi-fairness under class-imbalance](https://mlsanity.com/paper/2104.13312/) (2021)
- [MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networks](https://mlsanity.com/paper/2502.07422/) (2025)
- [Understanding User Preferences in Explainable Artificial Intelligence: A Survey and a Mapping Function Proposal](https://mlsanity.com/paper/2302.03180/) (2023)
- [Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps](https://mlsanity.com/paper/2305.09399/) (2023)
- [Peer-induced Fairness: A Causal Approach for Algorithmic Fairness Auditing](https://mlsanity.com/paper/2408.02558/) (2024)
- [Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?](https://mlsanity.com/paper/2509.22291/) (2025)

## Abstract (arXiv)

The ability to understand and trust the fairness of model predictions, particularly when considering the outcomes of unprivileged groups, is critical to the deployment and adoption of machine learning systems. SHAP values provide a unified framework for interpreting model predictions and feature attribution but do not address the problem of fairness directly. In this work, we propose a new definition of fairness that emphasises the role of an external auditor and model explicability. To satisfy this definition, we develop a framework for mitigating model bias using regularizations constructed from the SHAP values of an adversarial surrogate model. We focus on the binary classification task with a single unprivileged group and link our fairness explicability constraints to classical statistical fairness metrics. We demonstrate our approaches using gradient and adaptive boosting on: a synthetic dataset, the UCI Adult (Census) dataset and a real-world credit scoring dataset. The models produced were fairer and performant.