Federated Graph Learning with Graphless Clients

TL;DR

This paper introduces FedGLS, a federated graph learning framework that enables clients without graph structure data to collaboratively learn graph models by transferring structure knowledge through a local graph learner and knowledge distillation.

Contribution

The paper proposes FedGLS, a novel federated graph learning method that allows graphless clients to learn and transfer graph structure knowledge, addressing a key limitation of existing methods.

Findings

FedGLS outperforms five baseline methods in experiments.

Graphless clients can effectively learn local graph structures.

Knowledge transfer improves overall model performance.

Abstract

Federated Graph Learning (FGL) is tasked with training machine learning models, such as Graph Neural Networks (GNNs), for multiple clients, each with its own graph data. Existing methods usually assume that each client has both node features and graph structure of its graph data. In real-world scenarios, however, there exist federated systems where only a part of the clients have such data while other clients (i.e. graphless clients) may only have node features. This naturally leads to a novel problem in FGL: how to jointly train a model over distributed graph data with graphless clients? In this paper, we propose a novel framework FedGLS to tackle the problem in FGL with graphless clients. In FedGLS, we devise a local graph learner on each graphless client which learns the local graph structure with the structure knowledge transferred from other clients. To enable structure knowledge transfer, we design a GNN model and a feature encoder on each client. During local training, the feature encoder retains the local graph structure knowledge together with the GNN model via knowledge distillation, and the structure knowledge is transferred among clients in global update. Our extensive experiments demonstrate the superiority of the proposed FedGLS over five baselines.