Personalized Subgraph Federated Learning with Sheaf Collaboration
This work addresses the problem of handling diverse data distributions in graph-structured applications for clients in federated learning, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles performance variation in personalized subgraph federated learning due to heterogeneous local subgraphs by proposing FedSheafHN, which uses a sheaf collaboration mechanism and hypernetwork to generate customized models, resulting in outperforming existing methods on various graph datasets with fast convergence and generalization to new clients.
Graph-structured data is prevalent in many applications. In subgraph federated learning (FL), this data is distributed across clients, each with a local subgraph. Personalized subgraph FL aims to develop a customized model for each client to handle diverse data distributions. However, performance variation across clients remains a key issue due to the heterogeneity of local subgraphs. To overcome the challenge, we propose FedSheafHN, a novel framework built on a sheaf collaboration mechanism to unify enhanced client descriptors with efficient personalized model generation. Specifically, FedSheafHN embeds each client's local subgraph into a server-constructed collaboration graph by leveraging graph-level embeddings and employing sheaf diffusion within the collaboration graph to enrich client representations. Subsequently, FedSheafHN generates customized client models via a server-optimized hypernetwork. Empirical evaluations demonstrate that FedSheafHN outperforms existing personalized subgraph FL methods on various graph datasets. Additionally, it exhibits fast model convergence and effectively generalizes to new clients.