# Disaggregated Interventions to Reduce Inequality

arXiv: https://arxiv.org/abs/2107.00593 · HTML: https://mlsanity.com/paper/2107.00593/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 23 of 23)

- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer](https://mlsanity.com/paper/1711.06664/) (2017)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Delayed Impact of Fair Machine Learning](https://mlsanity.com/paper/1803.04383/) (2018)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Algorithmic recourse under imperfect causal knowledge: a probabilistic approach](https://mlsanity.com/paper/2006.06831/) (2020)
- [An Intersectional Definition of Fairness](https://mlsanity.com/paper/1807.08362/) (2018)
- [Towards a Critical Race Methodology in Algorithmic Fairness](https://mlsanity.com/paper/1912.03593/) (2019)
- [Machine Learning Methods Economists Should Know About](https://mlsanity.com/paper/1903.10075/) (2019)
- [A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity](https://mlsanity.com/paper/1809.03400/) (2018)
- [The Use and Misuse of Counterfactuals in Ethical Machine Learning](https://mlsanity.com/paper/2102.05085/) (2021)
- [Learning Optimal Fair Policies](https://mlsanity.com/paper/1809.02244/) (2018)
- [Racial categories in machine learning](https://mlsanity.com/paper/1811.11668/) (2018)
- [Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making](https://mlsanity.com/paper/1806.04959/) (2018)
- [Fair Classification and Social Welfare](https://mlsanity.com/paper/1905.00147/) (2019)
- [What's Sex Got To Do With Fair Machine Learning?](https://mlsanity.com/paper/2006.01770/) (2020)
- [Downstream Effects of Affirmative Action](https://mlsanity.com/paper/1808.09004/) (2018)
- [Balanced Ranking with Diversity Constraints](https://mlsanity.com/paper/1906.01747/) (2019)
- [Causal Diagrams for Interference](https://mlsanity.com/paper/1403.1239/) (2014)
- [Bipartite Causal Inference with Interference](https://mlsanity.com/paper/1807.08660/) (2018)
- [Causal Multi-Level Fairness](https://mlsanity.com/paper/2010.07343/) (2020)
- [Estimating Average Causal Effects Under General Interference, with Application to a Social Network Experiment](https://mlsanity.com/paper/1305.6156/) (2013)

## Built on by (most cited first, 5 of 5)

- [When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction](https://mlsanity.com/paper/2206.02058/) (2022)
- [Counterfactuals for the Future](https://mlsanity.com/paper/2212.03974/) (2022)
- [FATE in AI: Towards Algorithmic Inclusivity and Accessibility](https://mlsanity.com/paper/2301.01590/) (2023)
- [Causal Dependence Plots](https://mlsanity.com/paper/2303.04209/) (2023)
- [A New Paradigm for Counterfactual Reasoning in Fairness and Recourse](https://mlsanity.com/paper/2401.13935/) (2024)

## Abstract (arXiv)

A significant body of research in the data sciences considers unfair discrimination against social categories such as race or gender that could occur or be amplified as a result of algorithmic decisions. Simultaneously, real-world disparities continue to exist, even before algorithmic decisions are made. In this work, we draw on insights from the social sciences brought into the realm of causal modeling and constrained optimization, and develop a novel algorithmic framework for tackling pre-existing real-world disparities. The purpose of our framework, which we call the "impact remediation framework," is to measure real-world disparities and discover the optimal intervention policies that could help improve equity or access to opportunity for those who are underserved with respect to an outcome of interest. We develop a disaggregated approach to tackling pre-existing disparities that relaxes the typical set of assumptions required for the use of social categories in structural causal models. Our approach flexibly incorporates counterfactuals and is compatible with various ontological assumptions about the nature of social categories. We demonstrate impact remediation with a hypothetical case study and compare our disaggregated approach to an existing state-of-the-art approach, comparing its structure and resulting policy recommendations. In contrast to most work on optimal policy learning, we explore disparity reduction itself as an objective, explicitly focusing the power of algorithms on reducing inequality.