Mitigating the Performance Sacrifice in DP-Satisfied Federated Settings through Graph Contrastive Learning

TL;DR

This paper explores how graph contrastive learning can mitigate the performance degradation caused by differential privacy mechanisms in federated graph learning, demonstrating improved results across multiple models and datasets.

Contribution

It introduces a novel approach leveraging graph contrastive learning to counteract the performance loss due to differential privacy in federated graph learning.

Findings

Contrastive learning alleviates DP-induced performance drops

Experimental results show improved accuracy with the proposed method

Effective across multiple graph models and datasets

Abstract

Currently, graph learning models are indispensable tools to help researchers explore graph-structured data. In academia, using sufficient training data to optimize a graph model on a single device is a typical approach for training a capable graph learning model. Due to privacy concerns, however, it is infeasible to do so in real-world scenarios. Federated learning provides a practical means of addressing this limitation by introducing various privacy-preserving mechanisms, such as differential privacy (DP) on the graph edges. However, although DP in federated graph learning can ensure the security of sensitive information represented in graphs, it usually causes the performance of graph learning models to degrade. In this paper, we investigate how DP can be implemented on graph edges and observe a performance decrease in our experiments. In addition, we note that DP on graph edges introduces noise that perturbs graph proximity, which is one of the graph augmentations in graph contrastive learning. Inspired by this, we propose leveraging graph contrastive learning to alleviate the performance drop resulting from DP. Extensive experiments conducted with four representative graph models on five widely used benchmark datasets show that contrastive learning indeed alleviates the models' DP-induced performance drops.