Mitigating the performance sacrifice in DP-satisfied federated settings through graph contrastive learning

Haoran YANG, Xiangyu ZHAO, Muyang LI, Hongxu CHEN, Guandong XU

Research output: Contribution to journalArticlespeer-review

1 Citation (Scopus)

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. Copyright © 2023 Elsevier Inc. All rights reserved.

Original languageEnglish
Article number119552
JournalInformation Sciences
Volume648
Early online dateAug 2023
DOIs
Publication statusPublished - Nov 2023

Citation

Yang, H., Zhao, X., Li, M., Chen, H., & Xu, G. (2023). Mitigating the performance sacrifice in DP-satisfied federated settings through graph contrastive learning. Information Sciences, 648, Article 119552. https://doi.org/10.1016/j.ins.2023.119552

Fingerprint

Dive into the research topics of 'Mitigating the performance sacrifice in DP-satisfied federated settings through graph contrastive learning'. Together they form a unique fingerprint.