# How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis

arXiv: https://arxiv.org/abs/2206.00667 · HTML: https://mlsanity.com/paper/2206.00667/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 65 references that are in the map.
- First posted on arXiv 1 Jun 2022.

## Builds on (most cited first, 21 of 21)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [FAHT: An Adaptive Fairness-aware Decision Tree Classifier](https://mlsanity.com/paper/1907.07237/) (2019)
- [Poisoning Attacks on Algorithmic Fairness](https://mlsanity.com/paper/2004.07401/) (2020)
- [Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation](https://mlsanity.com/paper/2205.04610/) (2022)
- [On the relation between accuracy and fairness in binary classification](https://mlsanity.com/paper/1505.05723/) (2015)
- [Exacerbating Algorithmic Bias through Fairness Attacks](https://mlsanity.com/paper/2012.08723/) (2020)
- [Fairness Metrics: A Comparative Analysis](https://mlsanity.com/paper/2001.07864/) (2020)
- [Achieving Fairness at No Utility Cost via Data Reweighing with Influence](https://mlsanity.com/paper/2202.00787/) (2022)
- [A survey of bias in Machine Learning through the prism of Statistical Parity for the Adult Data Set](https://mlsanity.com/paper/2003.14263/) (2020)
- [Explainability for fair machine learning](https://mlsanity.com/paper/2010.07389/) (2020)
- [Justicia: A Stochastic SAT Approach to Formally Verify Fairness](https://mlsanity.com/paper/2009.06516/) (2020)
- [Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decomposition](https://mlsanity.com/paper/2108.05335/) (2021)
- [Algorithmic Fairness Verification with Graphical Models](https://mlsanity.com/paper/2109.09447/) (2021)
- [Fairness seen as Global Sensitivity Analysis](https://mlsanity.com/paper/2103.04613/) (2021)
- [Human Imperceptible Attacks and Applications to Improve Fairness](https://mlsanity.com/paper/2111.15603/) (2021)

## Built on by (most cited first, 7 of 7)

- [A Critical Survey on Fairness Benefits of Explainable AI](https://mlsanity.com/paper/2310.13007/) (2023)
- [How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features](https://mlsanity.com/paper/2305.12100/) (2023)
- [FairSense: Long-Term Fairness Analysis of ML-Enabled Systems](https://mlsanity.com/paper/2501.01665/) (2025)
- [Influence-based Attributions can be Manipulated](https://mlsanity.com/paper/2409.05208/) (2024)
- [Laplace Sample Information: Data Informativeness Through a Bayesian Lens](https://mlsanity.com/paper/2505.15303/) (2025)
- [Detecting labeling bias using influence functions](https://mlsanity.com/paper/2602.19130/) (2026)
- [The Fair Game: Auditing & Debiasing AI Algorithms Over Time](https://mlsanity.com/paper/2508.06443/) (2025)

## Abstract (arXiv)

Fairness in machine learning has attained significant focus due to the widespread application in high-stake decision-making tasks. Unregulated machine learning classifiers can exhibit bias towards certain demographic groups in data, thus the quantification and mitigation of classifier bias is a central concern in fairness in machine learning. In this paper, we aim to quantify the influence of different features in a dataset on the bias of a classifier. To do this, we introduce the Fairness Influence Function (FIF). This function breaks down bias into its components among individual features and the intersection of multiple features. The key idea is to represent existing group fairness metrics as the difference of the scaled conditional variances in the classifier's prediction and apply a decomposition of variance according to global sensitivity analysis. To estimate FIFs, we instantiate an algorithm FairXplainer that applies variance decomposition of classifier's prediction following local regression. Experiments demonstrate that FairXplainer captures FIFs of individual feature and intersectional features, provides a better approximation of bias based on FIFs, demonstrates higher correlation of FIFs with fairness interventions, and detects changes in bias due to fairness affirmative/punitive actions in the classifier. The code is available at https://github.com/ReAILe/bias-explainer.