# Explaining Knock-on Effects of Bias Mitigation

arXiv: https://arxiv.org/abs/2312.00765 · HTML: https://mlsanity.com/paper/2312.00765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 1 Dec 2023.

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

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [A comparative study of fairness-enhancing interventions in machine learning](https://mlsanity.com/paper/1802.04422/) (2018)
- [An Empirical Study of Rich Subgroup Fairness for Machine Learning](https://mlsanity.com/paper/1808.08166/) (2018)
- [Identifying Significant Predictive Bias in Classifiers](https://mlsanity.com/paper/1611.08292/) (2016)

## Abstract (arXiv)

In machine learning systems, bias mitigation approaches aim to make outcomes fairer across privileged and unprivileged groups. Bias mitigation methods work in different ways and have known "waterfall" effects, e.g., mitigating bias at one place may manifest bias elsewhere. In this paper, we aim to characterise impacted cohorts when mitigation interventions are applied. To do so, we treat intervention effects as a classification task and learn an explainable meta-classifier to identify cohorts that have altered outcomes. We examine a range of bias mitigation strategies that work at various stages of the model life cycle. We empirically demonstrate that our meta-classifier is able to uncover impacted cohorts. Further, we show that all tested mitigation strategies negatively impact a non-trivial fraction of cases, i.e., people who receive unfavourable outcomes solely on account of mitigation efforts. This is despite improvement in fairness metrics. We use these results as a basis to argue for more careful audits of static mitigation interventions that go beyond aggregate metrics.