Abstract: Federated graph learning 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 learning systems where only a part of the clients have such data while other clients graphless clients may only have features. This naturally leads to a novel problem in federated graph learning: how to jointly train a model over distributed graph data with graphless clients? To tackle this problem, we propose a novel Federated Graph Structure Learning (FedGSL) framework in this paper. In FedGSL, 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 on five real-world graph datasets demonstrate the superiority of FedGSL over other five federated learning approaches.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: 1. Added contents about horizontal and vertical FL in Introduction;
2. Added a new example in Introduction;
3. Added more contents in Conclusion;
4. Added parentheses for citations;
5. Moved Related work to Section 2.
Assigned Action Editor: ~Olgica_Milenkovic1
Submission Number: 2595
Loading