Certified Defense on the Fairness of Graph Neural Networks

TL;DR

This paper introduces ELEGANT, a certifiable framework that guarantees the fairness of GNNs against input perturbations without retraining, enhancing trustworthiness in graph-based learning tasks.

Contribution

We propose ELEGANT, a universal, re-training-free certification framework for GNN fairness, applicable to any GNN architecture with theoretical guarantees.

Findings

ELEGANT successfully certifies fairness under specified perturbation budgets.

The framework is effective across various GNN backbones and datasets.

ELEGANT does not require assumptions on GNN structure or parameters.

Abstract

Graph Neural Networks (GNNs) have emerged as a prominent graph learning model in various graph-based tasks over the years. Nevertheless, due to the vulnerabilities of GNNs, it has been empirically shown that malicious attackers could easily corrupt the fairness level of their predictions by adding perturbations to the input graph data. In this paper, we take crucial steps to study a novel problem of certifiable defense on the fairness level of GNNs. Specifically, we propose a principled framework named ELEGANT and present a detailed theoretical certification analysis for the fairness of GNNs. ELEGANT takes {\em any} GNN as its backbone, and the fairness level of such a backbone is theoretically impossible to be corrupted under certain perturbation budgets for attackers. Notably, ELEGANT does not make any assumptions over the GNN structure or parameters, and does not require re-training the GNNs to realize certification. Hence it can serve as a plug-and-play framework for any optimized GNNs ready to be deployed. We verify the satisfactory effectiveness of ELEGANT in practice through extensive experiments on real-world datasets across different backbones of GNNs and parameter settings.