mlsanityData to 7 Oct 2026

Communication-efficient Federated Graph Classification via Generative Diffusion Modeling

arXiv 2601.15722 ↗First posted 22 Jan 2026cs.LGcited by 0

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

Graph Neural Networks (GNNs) unlock new ways of learning from graph-structured data, proving highly effective in capturing complex relationships and patterns. Federated GNNs (FGNNs) have emerged as a prominent distributed learning paradigm for training GNNs over decentralized data. However, FGNNs face two significant challenges: high communication overhead from multiple rounds of parameter exchanges and non-IID data characteristics across clients. To address these issues, we introduce CeFGC, a novel FGNN paradigm that facilitates efficient GNN training over non-IID data by limiting communication between the server and clients to three rounds only. The core idea of CeFGC is to leverage generative diffusion models to minimize direct client-server communication. Each client trains a generative diffusion model that captures its local graph distribution and shares this model with the server, which then redistributes it back to all clients. Using these generative models, clients generate synthetic graphs combined with their local graphs to train local GNN models. Finally, clients upload their model weights to the server for aggregation into a global GNN model. We theoretically analyze the I/O complexity of communication volume to show that CeFGC reduces to a constant of three communication rounds only. Extensive experiments on several real graph datasets demonstrate the effectiveness and efficiency of CeFGC against state-of-the-art competitors, reflecting our superior performance on non-IID graphs by aligning local and global model objectives and enriching the training set with diverse graphs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 51 of its 92 references that are in the map. First posted on arXiv 22 Jan 2026.

Builds on

51 of 92 references.

References · 51

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2019Advances and Open Problems in Federated Learningcited by 3,021
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  9. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  10. 2016Improved Techniques for Training GANscited by 2,938
  11. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  12. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
38 more
  1. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  3. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  4. 2021Model-Contrastive Federated Learningcited by 762
  5. 2019Graph Neural Networks for Social Recommendationcited by 711
  6. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  7. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  8. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  9. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 413
  10. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  11. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  12. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  13. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 298
  14. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  15. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  16. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  17. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
  18. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  19. 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 178
  20. 2020Threats to Federated Learning: A Surveycited by 171
  21. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 154
  22. 2021A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directionscited by 144
  23. 2019One-Shot Federated Learningcited by 124
  24. 2021Federated Graph Classification over Non-IID Graphscited by 113
  25. 2020Distilled One-Shot Federated Learningcited by 108
  26. 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 102
  27. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  28. 2023Generative Diffusion Models on Graphs: Methods and Applicationscited by 79
  29. 2022NVIDIA FLARE: Federated Learning from Simulation to Real-Worldcited by 78
  30. 2022Diffusion Models for Graphs Benefit From Discrete State Spacescited by 69
  31. 2020Fast-Convergent Federated Learning with Adaptive Weightingcited by 67
  32. 2021Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryptioncited by 46
  33. 2022GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generationcited by 43
  34. 2021Graph Embedding for Recommendation against Attribute Inference Attackscited by 40
  35. 2021Communication Efficiency in Federated Learning: Achievements and Challengescited by 40
  36. 2021Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryptioncited by 18
  37. 2022NVDiff: Graph Generation through the Diffusion of Node Vectorscited by 18
  38. 2022Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applicationscited by 14

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Structural Entropy-Driven Graph Diffusion Generation for One-Shot Federated Graph Learning
  2. 2025Federated Learning for Diffusion Models
  3. 2024Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data
  4. 2025Do Graph Diffusion Models Accurately Capture and Generate Substructure Distributions?
  5. 2025FedPhD: Federated Pruning with Hierarchical Learning of Diffusion Models
  6. 2024Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning
  7. 2026Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach
  8. 2024Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification