FairGE: Fairness-Aware Graph Encoding in Incomplete Social Networks

TL;DR

FairGE introduces a spectral graph theory-based fairness-aware encoding method for graph transformers in incomplete social networks, improving fairness metrics without reconstructing sensitive attributes.

Contribution

It proposes a novel fairness-aware graph encoding framework that directly encodes fairness through spectral methods, avoiding sensitive attribute reconstruction.

Findings

Achieves at least 16% improvement in statistical parity

Enhances equality of opportunity in social network analysis

Validated on seven real-world datasets

Abstract

Graph Transformers (GTs) are increasingly applied to social network analysis, yet their deployment is often constrained by fairness concerns. This issue is particularly critical in incomplete social networks, where sensitive attributes are frequently missing due to privacy and ethical restrictions. Existing solutions commonly generate these incomplete attributes, which may introduce additional biases and further compromise user privacy. To address this challenge, FairGE (Fair Graph Encoding) is introduced as a fairness-aware framework for GTs in incomplete social networks. Instead of generating sensitive attributes, FairGE encodes fairness directly through spectral graph theory. By leveraging the principal eigenvector to represent structural information and padding incomplete sensitive attributes with zeros to maintain independence, FairGE ensures fairness without data reconstruction. Theoretical analysis demonstrates that the method suppresses the influence of non-principal spectral components, thereby enhancing fairness. Extensive experiments on seven real-world social network datasets confirm that FairGE achieves at least a 16% improvement in both statistical parity and equality of opportunity compared with state-of-the-art baselines. The source code is shown in https://github.com/LuoRenqiang/FairGE.