SaGIF: Improving Individual Fairness in Graph Neural Networks via Similarity Encoding

TL;DR

This paper introduces SaGIF, a novel approach that enhances individual fairness in graph neural networks by integrating similarity encoding through topology and feature fusion, validated on real-world datasets.

Contribution

The paper proposes new similarity metrics and a GNN model, SaGIF, that improves individual fairness by learning similarity representations, addressing gaps in understanding and identifying similar individuals.

Findings

SaGIF outperforms existing fairness methods on multiple datasets.

The proposed metrics effectively evaluate similarity consistency.

SaGIF maintains utility performance while improving fairness.

Abstract

Individual fairness (IF) in graph neural networks (GNNs), which emphasizes the need for similar individuals should receive similar outcomes from GNNs, has been a critical issue. Despite its importance, research in this area has been largely unexplored in terms of (1) a clear understanding of what induces individual unfairness in GNNs and (2) a comprehensive consideration of identifying similar individuals. To bridge these gaps, we conduct a preliminary analysis to explore the underlying reason for individual unfairness and observe correlations between IF and similarity consistency, a concept introduced to evaluate the discrepancy in identifying similar individuals based on graph structure versus node features. Inspired by our observations, we introduce two metrics to assess individual similarity from two distinct perspectives: topology fusion and feature fusion. Building upon these metrics, we propose Similarity-aware GNNs for Individual Fairness, named SaGIF. The key insight behind SaGIF is the integration of individual similarities by independently learning similarity representations, leading to an improvement of IF in GNNs. Our experiments on several real-world datasets validate the effectiveness of our proposed metrics and SaGIF. Specifically, SaGIF consistently outperforms state-of-the-art IF methods while maintaining utility performance. Code is available at: https://github.com/ZzoomD/SaGIF.