Bursting the Burden Bubble? An Assessment of Sharma et al.'s Counterfactual-based Fairness Metric

TL;DR

This paper evaluates the Burden fairness metric, based on counterfactuals, comparing it to statistical parity across synthetic and real datasets, highlighting their differences and complementary use in fairness assessment.

Contribution

It introduces a comparative analysis of Burden and statistical parity, demonstrating Burden's unique ability to detect certain unfairness aspects missed by statistical parity.

Findings

Burden can identify unfairness where statistical parity cannot.

The two metrics may disagree on which group is treated unfairly.

Using both metrics provides a more comprehensive fairness assessment.

Abstract

Machine learning has seen an increase in negative publicity in recent years, due to biased, unfair, and uninterpretable models. There is a rising interest in making machine learning models more fair for unprivileged communities, such as women or people of color. Metrics are needed to evaluate the fairness of a model. A novel metric for evaluating fairness between groups is Burden, which uses counterfactuals to approximate the average distance of negatively classified individuals in a group to the decision boundary of the model. The goal of this study is to compare Burden to statistical parity, a well-known fairness metric, and discover Burden's advantages and disadvantages. We do this by calculating the Burden and statistical parity of a sensitive attribute in three datasets: two synthetic datasets are created to display differences between the two metrics, and one real-world dataset is used. We show that Burden can show unfairness where statistical parity can not, and that the two metrics can even disagree on which group is treated unfairly. We conclude that Burden is a valuable metric, but does not replace statistical parity: it rather is valuable to use both.