Decoupled Subgraph Federated Learning
This addresses privacy-preserving graph learning for distributed clients, but it is incremental as it builds on existing federated learning methods with a novel structural approach.
The paper tackled federated learning on graph-structured data with interconnected subgraphs by proposing FedStruct, a framework that uses global graph structure to capture dependencies without sharing sensitive data, achieving performance close to centralized approaches on six datasets for node classification.
We address the challenge of federated learning on graph-structured data distributed across multiple clients. Specifically, we focus on the prevalent scenario of interconnected subgraphs, where interconnections between different clients play a critical role. We present a novel framework for this scenario, named FedStruct, that harnesses deep structural dependencies. To uphold privacy, unlike existing methods, FedStruct eliminates the necessity of sharing or generating sensitive node features or embeddings among clients. Instead, it leverages explicit global graph structure information to capture inter-node dependencies. We validate the effectiveness of FedStruct through experimental results conducted on six datasets for semi-supervised node classification, showcasing performance close to the centralized approach across various scenarios, including different data partitioning methods, varying levels of label availability, and number of clients.