Targeted Learning for Data Fairness

TL;DR

This paper introduces a targeted learning framework for statistical inference of data fairness, enabling evaluation of fairness properties directly in the data generation process, with robust estimators validated through simulations and real data applications.

Contribution

It extends fairness inference to data fairness, providing new estimators for demographic parity, equal opportunity, and mutual information within a nonparametric, double-robust framework.

Findings

Estimators for demographic parity, equal opportunity, and mutual information were successfully derived.

The proposed estimators demonstrate double robustness in probabilistic fairness metrics.

Validation through simulations and real data confirms the effectiveness of the approach.

Abstract

Data and algorithms have the potential to produce and perpetuate discrimination and disparate treatment. As such, significant effort has been invested in developing approaches to defining, detecting, and eliminating unfair outcomes in algorithms. In this paper, we focus on performing statistical inference for fairness. Prior work in fairness inference has largely focused on inferring the fairness properties of a given predictive algorithm. Here, we expand fairness inference by evaluating fairness in the data generating process itself, referred to here as data fairness. We perform inference on data fairness using targeted learning, a flexible framework for nonparametric inference. We derive estimators demographic parity, equal opportunity, and conditional mutual information. Additionally, we find that our estimators for probabilistic metrics exploit double robustness. To validate our approach, we perform several simulations and apply our estimators to real data.