Structural Entropy-Driven Graph Diffusion Generation for One-Shot Federated Graph Learning
One-shot federated graph learning (FGL) requires the server to estimate client contributions from highly compressed information, yet conventional volume-based weighting captures the amount of client data while overlooking how its connectivity is organized. In this paper, we propose SPIRE, a Structural Entropy-Driven Gr...
Shu-Tong Zheng, Le-Le Fu, Sheng Huang et al.
· 0 citations