Causal Multi-Level Fairness

TL;DR

This paper introduces a causal framework for multi-level fairness, addressing biases at both individual and macro levels, and demonstrates its importance and effectiveness in reducing unfairness in real-world predictions.

Contribution

It formalizes multi-level fairness using causal inference tools and shows how neglecting macro-level biases leads to residual unfairness, proposing mitigation strategies.

Findings

Residual unfairness occurs if macro-level sensitive attributes are ignored.

Incorporating multi-level attributes reduces unfairness in income prediction.

The approach effectively mitigates bias in real-world tasks.

Abstract

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.