mlsanityData to 14 Oct 2026

Structural Entropy-Driven Graph Diffusion Generation for One-Shot Federated Graph Learning

arXiv 2609.06499 ↗First posted 6 Sep 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 Graph Diffusion Generation method that introduces topology-aware client differentiation into one-shot FGL. Specifically, we employ first-order degree-distribution structural entropy as a compact descriptor of degree-mass dispersion and use it to derive structural client weights, providing an inductive bias that accounts for differences in graph topology beyond data volume. On the generation side, a graph diffusion model on the server synthesizes pseudographs conditioned on the weighted client prototypes, capturing both semantic and structural information without requiring additional client-side training. The generated pseudographs are then assembled via disjoint union fusion to train a global graph neural network. Extensive experiments on seven real-world graph datasets demonstrate that SPIRE consistently outperforms conventional and one-shot FGL methods, with particularly strong gains under highly heterogeneous (non-IID) and graph-perturbed settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 48 references that are in the map. First posted on arXiv 6 Sep 2026.

Builds on

18 of 48 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2020Adaptive Federated Optimizationcited by 1,046
  4. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  5. 2021Model-Contrastive Federated Learningcited by 766
  6. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  7. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 260
  8. 2019One-Shot Federated Learningcited by 125
  9. 2021Federated Graph Classification over Non-IID Graphscited by 114
  10. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  11. 2020Practical One-Shot Federated Learning for Cross-Silo Settingcited by 77
  12. 2024FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learningcited by 47
6 more
  1. 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
  2. 2019One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Themcited by 23
  3. 2024FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Modelscited by 17
  4. 2024Revisiting Ensembling in One-Shot Federated Learningcited by 13
  5. 2024One-shot Federated Learning via Synthetic Distiller-Distillate Communicationcited by 12
  6. 2023Towards Fair Graph Federated Learning via Incentive Mechanismscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Communication-efficient Federated Graph Classification via Generative Diffusion Modeling
  2. 2026Discrete Diffusion for Large Graph Generation via Structural Candidate Restriction
  3. 2025Knowledge-Driven Federated Graph Learning on Model Heterogeneity
  4. 2024FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning
  5. 2024Federated Graph Condensation with Information Bottleneck Principles
  6. 2024Federated Graph Learning with Graphless Clients
  7. 2024Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models
  8. 2025Do Graph Diffusion Models Accurately Capture and Generate Substructure Distributions?