Survey on Causal-based Machine Learning Fairness Notions

TL;DR

This survey reviews causal-based fairness notions in machine learning, discussing their theoretical foundations, practical estimation methods, and providing guidelines for selecting appropriate fairness measures in real-world applications.

Contribution

It offers a comprehensive overview of causal fairness notions, including their applicability, estimation techniques, and a ranking based on deployment difficulty.

Findings

Most causal fairness notions are defined with non-observable quantities.

Different approaches exist for estimating causal quantities from observational data.

Guidelines and rankings assist in selecting suitable fairness notions for specific scenarios.

Abstract

Addressing the problem of fairness is crucial to safely use machine learning algorithms to support decisions with a critical impact on people's lives such as job hiring, child maltreatment, disease diagnosis, loan granting, etc. Several notions of fairness have been defined and examined in the past decade, such as statistical parity and equalized odds. The most recent fairness notions, however, are causal-based and reflect the now widely accepted idea that using causality is necessary to appropriately address the problem of fairness. This paper examines an exhaustive list of causal-based fairness notions and study their applicability in real-world scenarios. As the majority of causal-based fairness notions are defined in terms of non-observable quantities (e.g., interventions and counterfactuals), their deployment in practice requires to compute or estimate those quantities using observational data. This paper offers a comprehensive report of the different approaches to infer causal quantities from observational data including identifiability (Pearl's SCM framework) and estimation (potential outcome framework). The main contributions of this survey paper are (1) a guideline to help selecting a suitable fairness notion given a specific real-world scenario, and (2) a ranking of the fairness notions according to Pearl's causation ladder indicating how difficult it is to deploy each notion in practice.