FairGU: Fairness-aware Graph Unlearning in Social Network

TL;DR

FairGU addresses the gap where graph unlearning methods degrade fairness when sensitive attributes are removed. It fuses a pre-trained sensitive-attribute estimator, a fairness-aware GNN with adversarial debiasing and a covariance constraint, and an FIM-based unlearning mechanism to selectively dampen parameters tied to forgotten data. Experiments on Income, Pokec-z, and Pokec-n show FairGU outperforms state-of-the-art unlearning and fairness baselines in both accuracy and fairness metrics, while offering strong privacy protection against membership inference attacks. The work demonstrates a practical approach to rebuilding socially responsible web systems that support data deletion without amplifying bias, and it lays groundwork for extending to dynamic graphs and multi-attribute fairness scenarios.

Abstract

Graph unlearning has emerged as a critical mechanism for supporting sustainable and privacy-preserving social networks, enabling models to remove the influence of deleted nodes and thereby better safeguard user information. However, we observe that existing graph unlearning techniques insufficiently protect sensitive attributes, often leading to degraded algorithmic fairness compared with traditional graph learning methods. To address this gap, we introduce FairGU, a fairness-aware graph unlearning framework designed to preserve both utility and fairness during the unlearning process. FairGU integrates a dedicated fairness-aware module with effective data protection strategies, ensuring that sensitive attributes are neither inadvertently amplified nor structurally exposed when nodes are removed. Through extensive experiments on multiple real-world datasets, we demonstrate that FairGU consistently outperforms state-of-the-art graph unlearning methods and fairness-enhanced graph learning baselines in terms of both accuracy and fairness metrics. Our findings highlight a previously overlooked risk in current unlearning practices and establish FairGU as a robust and equitable solution for the next generation of socially sustainable networked systems. The codes are available at https://github.com/LuoRenqiang/FairGU.

Figures (2)

• Figure 1: The $\Delta_{\text{SP}}$ and $\Delta_{\text{EO}}$ of graph unlearning methods and fairness-aware graph learning method. Lower values of $\Delta_{\text{SP}}$ and $\Delta_{\text{EO}}$ indicate better fairness performance.
• Figure 2: The illustration of FairGU.