On the Robustness of Fairness Practices: A Causal Framework for Systematic Evaluation

TL;DR

This paper introduces a causal framework to systematically evaluate the robustness of fairness practices in machine learning, addressing their reliability under real-world data challenges like bias, missing data, and distribution shifts.

Contribution

It proposes a novel causal evaluation framework to assess the effectiveness and robustness of fairness interventions in ML systems under various data issues.

Findings

Fairness practices vary in robustness under data imperfections

Causal analysis reveals limitations of current fairness interventions

Guidelines for more reliable fairness assessments are proposed

Abstract

Machine learning (ML) algorithms are increasingly deployed to make critical decisions in socioeconomic applications such as finance, criminal justice, and autonomous driving. However, due to their data-driven and pattern-seeking nature, ML algorithms may develop decision logic that disproportionately distributes opportunities, benefits, resources, or information among different population groups, potentially harming marginalized communities. In response to such fairness concerns, the software engineering and ML communities have made significant efforts to establish the best practices for creating fair ML software. These include fairness interventions for training ML models, such as including sensitive features, selecting non-sensitive attributes, and applying bias mitigators. But how reliably can software professionals tasked with developing data-driven systems depend on these recommendations? And how well do these practices generalize in the presence of faulty labels, missing data, or distribution shifts? These questions form the core theme of this paper.