A Benchmark for Fairness-Aware Graph Learning

TL;DR

This paper introduces a comprehensive benchmark for fairness-aware graph learning methods, evaluating their performance on multiple fairness criteria and efficiency across real-world datasets to guide future research and applications.

Contribution

It provides the first extensive benchmark with a systematic evaluation protocol for fairness-aware graph learning methods on diverse datasets.

Findings

Identifies strengths and limitations of current methods

Offers practical guidance for applying fairness-aware graph learning

Highlights the need for balanced fairness and efficiency

Abstract

Fairness-aware graph learning has gained increasing attention in recent years. Nevertheless, there lacks a comprehensive benchmark to evaluate and compare different fairness-aware graph learning methods, which blocks practitioners from choosing appropriate ones for broader real-world applications. In this paper, we present an extensive benchmark on ten representative fairness-aware graph learning methods. Specifically, we design a systematic evaluation protocol and conduct experiments on seven real-world datasets to evaluate these methods from multiple perspectives, including group fairness, individual fairness, the balance between different fairness criteria, and computational efficiency. Our in-depth analysis reveals key insights into the strengths and limitations of existing methods. Additionally, we provide practical guidance for applying fairness-aware graph learning methods in applications. To the best of our knowledge, this work serves as an initial step towards comprehensively understanding representative fairness-aware graph learning methods to facilitate future advancements in this area.