# Causal Multi-Level Fairness

arXiv: https://arxiv.org/abs/2010.07343 · HTML: https://mlsanity.com/paper/2010.07343/

## Key facts

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

## Built on by (most cited first, 14 of 14)

- [Causal Conceptions of Fairness and their Consequences](https://mlsanity.com/paper/2207.05302/) (2022)
- [Counterfactual Fairness Is Basically Demographic Parity](https://mlsanity.com/paper/2208.03843/) (2022)
- [Designing Long-term Group Fair Policies in Dynamical Systems](https://mlsanity.com/paper/2311.12447/) (2023)
- [Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors](https://mlsanity.com/paper/2301.08987/) (2023)
- [Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools](https://mlsanity.com/paper/2309.17337/) (2023)
- [Understanding Disparities in Post Hoc Machine Learning Explanation](https://mlsanity.com/paper/2401.14539/) (2024)
- [Disaggregated Interventions to Reduce Inequality](https://mlsanity.com/paper/2107.00593/) (2021)
- [Minimum Levels of Interpretability for Artificial Moral Agents](https://mlsanity.com/paper/2307.00660/) (2023)
- [Fairness-Aware Naive Bayes Classifier for Data with Multiple Sensitive Features](https://mlsanity.com/paper/2202.11499/) (2022)
- [A Review of Fairness and A Practical Guide to Selecting Context-Appropriate Fairness Metrics in Machine Learning](https://mlsanity.com/paper/2411.06624/) (2024)
- [Designing Equitable Algorithms](https://mlsanity.com/paper/2302.09157/) (2023)
- [A Tutorial On Intersectionality in Fair Rankings](https://mlsanity.com/paper/2502.05333/) (2025)
- [The Design and Composition of Structural Causal Decision Processes](https://mlsanity.com/paper/2605.02681/) (2026)
- [Algorithmic Fairness Over Time: Advances & Prospects](https://mlsanity.com/paper/2610.15015/) (2026)

## Abstract (arXiv)

Algorithmic systems are known to impact marginalized groups severely, and more so, if all sources of bias are not considered. While work in algorithmic fairness to-date has primarily focused on addressing discrimination due to individually linked attributes, social science research elucidates how some properties we link to individuals can be conceptualized as having causes at macro (e.g. structural) levels, and it may be important to be fair to attributes at multiple levels. For example, instead of simply considering race as a causal, protected attribute of an individual, the cause may be distilled as perceived racial discrimination an individual experiences, which in turn can be affected by neighborhood-level factors. This multi-level conceptualization is relevant to questions of fairness, as it may not only be important to take into account if the individual belonged to another demographic group, but also if the individual received advantaged treatment at the macro-level. In this paper, we formalize the problem of multi-level fairness using tools from causal inference in a manner that allows one to assess and account for effects of sensitive attributes at multiple levels. We show importance of the problem by illustrating residual unfairness if macro-level sensitive attributes are not accounted for, or included without accounting for their multi-level nature. Further, in the context of a real-world task of predicting income based on macro and individual-level attributes, we demonstrate an approach for mitigating unfairness, a result of multi-level sensitive attributes.