Learning Fair Representations with Kolmogorov-Arnold Networks

TL;DR

This paper introduces a novel fair learning framework using Kolmogorov-Arnold Networks within an adversarial setting, improving fairness and interpretability in high-stakes decision-making tasks.

Contribution

It proposes integrating KANs into fair adversarial learning, providing theoretical stability analysis and an adaptive fairness penalty mechanism.

Findings

Achieves improved fairness across sensitive attributes

Maintains high predictive accuracy

Demonstrates effectiveness on real-world datasets

Abstract

Despite recent advances in fairness-aware machine learning, predictive models often exhibit discriminatory behavior towards marginalized groups. Such unfairness might arise from biased training data, model design, or representational disparities across groups, posing significant challenges in high-stakes decision-making domains such as college admissions. While existing fair learning models aim to mitigate bias, achieving an optimal trade-off between fairness and accuracy remains a challenge. Moreover, the reliance on black-box models hinders interpretability, limiting their applicability in socially sensitive domains. To circumvent these issues, we propose integrating Kolmogorov-Arnold Networks (KANs) within a fair adversarial learning framework. Leveraging the adversarial robustness and interpretability of KANs, our approach facilitates stable adversarial learning. We derive theoretical insights into the spline-based KAN architecture that ensure stability during adversarial optimization. Additionally, an adaptive fairness penalty update mechanism is proposed to strike a balance between fairness and accuracy. We back these findings with empirical evidence on two real-world admissions datasets, demonstrating the proposed framework's efficiency in achieving fairness across sensitive attributes while preserving predictive performance.