DFed-SST: Building Semantic- and Structure-aware Topologies for Decentralized Federated Graph Learning
This addresses the challenge of adapting decentralized federated learning to graph data for applications like social networks or recommendation systems, representing an incremental advance by combining existing concepts.
The paper tackles the problem of decentralized federated learning for graph data by proposing DFed-SST, which uses a dual-topology adaptive communication mechanism to handle local subgraph heterogeneity, resulting in a 3.26% average accuracy improvement over baselines.
Decentralized Federated Learning (DFL) has emerged as a robust distributed paradigm that circumvents the single-point-of-failure and communication bottleneck risks of centralized architectures. However, a significant challenge arises as existing DFL optimization strategies, primarily designed for tasks such as computer vision, fail to address the unique topological information inherent in the local subgraph. Notably, while Federated Graph Learning (FGL) is tailored for graph data, it is predominantly implemented in a centralized server-client model, failing to leverage the benefits of decentralization.To bridge this gap, we propose DFed-SST, a decentralized federated graph learning framework with adaptive communication. The core of our method is a dual-topology adaptive communication mechanism that leverages the unique topological features of each client's local subgraph to dynamically construct and optimize the inter-client communication topology. This allows our framework to guide model aggregation efficiently in the face of heterogeneity. Extensive experiments on eight real-world datasets consistently demonstrate the superiority of DFed-SST, achieving 3.26% improvement in average accuracy over baseline methods.