Differential Adjusted Parity for Learning Fair Representations

TL;DR

The paper introduces Differential Adjusted Parity (DAP), a novel loss function that enhances fairness and accuracy in machine learning models by addressing bias and inconsistency across sensitive features.

Contribution

It proposes a differentiable adjusted parity loss that improves fairness metrics without degeneracy, outperforming adversarial methods in bias mitigation and accuracy.

Findings

DAP improves demographic parity by up to 22.5%.

It enhances equalized odds by up to 44.1%.

The method outperforms adversarial models in fairness and accuracy.

Abstract

The development of fair and unbiased machine learning models remains an ongoing objective for researchers in the field of artificial intelligence. We introduce the Differential Adjusted Parity (DAP) loss to produce unbiased informative representations. It utilises a differentiable variant of the adjusted parity metric to create a unified objective function. By combining downstream task classification accuracy and its inconsistency across sensitive feature domains, it provides a single tool to increase performance and mitigate bias. A key element in this approach is the use of soft balanced accuracies. In contrast to previous non-adversarial approaches, DAP does not suffer a degeneracy where the metric is satisfied by performing equally poorly across all sensitive domains. It outperforms several adversarial models on downstream task accuracy and fairness in our analysis. Specifically, it improves the demographic parity, equalized odds and sensitive feature accuracy by as much as 22.5\%, 44.1\% and 40.1\%, respectively, when compared to the best performing adversarial approaches on these metrics. Overall, the DAP loss and its associated metric can play a significant role in creating more fair machine learning models.