# FALE: Fairness-Aware ALE Plots for Auditing Bias in Subgroups

arXiv: https://arxiv.org/abs/2404.18685 · HTML: https://mlsanity.com/paper/2404.18685/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Algorithmic recourse under imperfect causal knowledge: a probabilistic approach](https://mlsanity.com/paper/2006.06831/) (2020)
- [An Empirical Study of Rich Subgroup Fairness for Machine Learning](https://mlsanity.com/paper/1808.08166/) (2018)
- [Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AI](https://mlsanity.com/paper/2005.05906/) (2020)
- [A Simple and Effective Model-Based Variable Importance Measure](https://mlsanity.com/paper/1805.04755/) (2018)
- [FlipTest: Fairness Testing via Optimal Transport](https://mlsanity.com/paper/1906.09218/) (2019)
- [Global Counterfactual Explanations: Investigations, Implementations and Improvements](https://mlsanity.com/paper/2204.06917/) (2022)
- [FairTest: Discovering Unwarranted Associations in Data-Driven Applications](https://mlsanity.com/paper/1510.02377/) (2015)
- [Legal perspective on possible fairness measures - A legal discussion using the example of hiring decisions (preprint)](https://mlsanity.com/paper/2108.06918/) (2021)

## Abstract (arXiv)

Fairness is steadily becoming a crucial requirement of Machine Learning (ML) systems. A particularly important notion is subgroup fairness, i.e., fairness in subgroups of individuals that are defined by more than one attributes. Identifying bias in subgroups can become both computationally challenging, as well as problematic with respect to comprehensibility and intuitiveness of the finding to end users. In this work we focus on the latter aspects; we propose an explainability method tailored to identifying potential bias in subgroups and visualizing the findings in a user friendly manner to end users. In particular, we extend the ALE plots explainability method, proposing FALE (Fairness aware Accumulated Local Effects) plots, a method for measuring the change in fairness for an affected population corresponding to different values of a feature (attribute). We envision FALE to function as an efficient, user friendly, comprehensible and reliable first-stage tool for identifying subgroups with potential bias issues.