Fair Representation Learning for Heterogeneous Information Networks

TL;DR

This paper introduces multiple de-biasing techniques for fair representation learning in Heterogeneous Information Networks, addressing societal concerns by reducing gender bias in career recommendation systems.

Contribution

It proposes a comprehensive set of de-biasing methods for HINs and systematically evaluates their effectiveness in balancing fairness and accuracy.

Findings

Certain methods effectively reduce gender bias in career recommendations.

Trade-offs exist between fairness improvements and prediction accuracy.

Different techniques perform best under varying conditions.

Abstract

Recently, much attention has been paid to the societal impact of AI, especially concerns regarding its fairness. A growing body of research has identified unfair AI systems and proposed methods to debias them, yet many challenges remain. Representation learning for Heterogeneous Information Networks (HINs), a fundamental building block used in complex network mining, has socially consequential applications such as automated career counseling, but there have been few attempts to ensure that it will not encode or amplify harmful biases, e.g. sexism in the job market. To address this gap, in this paper we propose a comprehensive set of de-biasing methods for fair HINs representation learning, including sampling-based, projection-based, and graph neural networks (GNNs)-based techniques. We systematically study the behavior of these algorithms, especially their capability in balancing the trade-off between fairness and prediction accuracy. We evaluate the performance of the proposed methods in an automated career counseling application where we mitigate gender bias in career recommendation. Based on the evaluation results on two datasets, we identify the most effective fair HINs representation learning techniques under different conditions.