Graph Federated Learning Based on the Decentralized Framework

TL;DR

This paper introduces a decentralized framework for graph federated learning that enhances scalability and robustness by replacing the traditional client-server model, using confidence-based gradient aggregation, and demonstrating superior performance over existing methods.

Contribution

It proposes a novel decentralized framework for graph federated learning, addressing scalability and failure issues of the client-server model, with confidence-based gradient aggregation.

Findings

Outperforms FedAvg, Fedprox, GCFL, and GCFL+ in experiments

Improves scalability and robustness of graph federated learning

Demonstrates effectiveness of confidence-based gradient aggregation

Abstract

Graph learning has a wide range of applications in many scenarios, which require more need for data privacy. Federated learning is an emerging distributed machine learning approach that leverages data from individual devices or data centers to improve the accuracy and generalization of the model, while also protecting the privacy of user data. Graph-federated learning is mainly based on the classical federated learning framework i.e., the Client-Server framework. However, the Client-Server framework faces problems such as a single point of failure of the central server and poor scalability of network topology. First, we introduce the decentralized framework to graph-federated learning. Second, determine the confidence among nodes based on the similarity of data among nodes, subsequently, the gradient information is then aggregated by linear weighting based on confidence. Finally, the proposed method is compared with FedAvg, Fedprox, GCFL, and GCFL+ to verify the effectiveness of the proposed method. Experiments demonstrate that the proposed method outperforms other methods.