Subgraph Federated Learning with Information Bottleneck Constrained Generative Learning
Open Access
- 21 July 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (6) , 1-23
Abstract
Federated Learning (FL) is a groundbreaking approach that enables multiple clients to jointly train deep learning models by pooling their data, while addressing privacy and bandwidth issues that prevent direct data sharing. This approach is particularly suitable for building strong and widely applicable graph models, given the increasing amounts of graph data stored across different locations. However, FL for subgraph models faces significant challenges, such as the diversity of data and the risk of attacks, which can affect the strength and reliability of these models. In response to these challenges, our research delves into the complexities of FL for subgraphs from an information theory perspective. We identify a major issue that affects the performance of graph models: the bias in the optimization goal of the commonly used FedAVG training method. To address this, we propose InfoFedGNN, an innovative FL framework for subgraphs that is based on the Information Bottleneck principle. InfoFedGNN is designed to overcome the problem of Non-Independent and Identically Distributed (non-i.i.d.) data in FL and to significantly improve its defense against security threats. Our thorough evaluation of InfoFedGNN on five public datasets, with both uniform and diverse data distributions, highlights its improved defense capabilities and better training outcomes. These results confirm the effectiveness of InfoFedGNN in enhancing the security and efficiency of FL, demonstrating its potential to push forward the development of federated graph models.Keywords
This publication has 20 references indexed in Scilit:
- A decentralized federated learning-based spatial–temporal model for freight traffic speed forecastingExpert Systems with Applications, 2023
- FedEL: Federated ensemble learning for non-iid dataExpert Systems with Applications, 2023
- FedMMD: A Federated weighting algorithm considering Non-IID and Local Model DeviationExpert Systems with Applications, 2023
- An Information Theoretic Perspective for Heterogeneous Subgraph Federated Learning2023
- Federated learning based driver recommendation for next generation transportation systemExpert Systems with Applications, 2023
- Learning Robust Representation Through Graph Adversarial Contrastive Learning2022
- Cluster-driven Graph Federated Learning over Multiple Domains2021
- ASFGNN: Automated separated-federated graph neural networkPeer-to-Peer Networking and Applications, 2021
- Deep learning and the information bottleneck principle2015
- Fast unfolding of communities in large networksJournal of Statistical Mechanics: Theory and Experiment, 2008