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

• URL: http://arxiv.org/abs/2609.06499v1
• Date: Sun, 06 Sep 2026 09:31:12 GMT
• Title: Structural Entropy-Driven Graph Diffusion Generation for One-Shot Federated Graph Learning
• Abstract summary: One-shot federated graph learning (FGL) requires the server to estimate client contributions from highly compressed information.<n>We propose SPIRE, a Structural Entropy-Driven Graph Diffusion Generation method that introduces topology-aware client differentiation into one-shot FGL.
• Score: 16.26727371966201
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors [32.18961351570798]
  Graph neural networks (GNNs) face a fundamental limitation: they require separate training for each new graph.<n>We introduce NodePFN, which generalizes to arbitrary graphs without graph-specific training.<n>A single pre-trained NodePFN achieves 71.27 average accuracy on 23 benchmarks.
  arXiv  Detail & Related papers  (2026-04-21T03:23:34Z)
• Personalized Subgraph Federated Learning with Sheaf Collaboration [22.825083541211168]
  FedSheafHN is a novel framework built on a sheaf collaboration mechanism to unify enhanced client descriptors with efficient personalized model generation.<n>Specifically, FedSheafHN embeds each client's local subgraph into a server-constructed collaboration graph.<n>It generates customized client models via a server-optimized hypernetwork.
  arXiv  Detail & Related papers  (2025-08-19T08:52:50Z)
• Generating Large Semi-Synthetic Graphs of Any Size [0.4419843514606336]
  Graph generation is an important area in network science.<n>Recent advancements in deep learning have enabled data-driven methods to learn and generate graphs.<n>We propose Latent Graph Sampling Generation (LGSG) to generate graphs of varying sizes without retraining.
  arXiv  Detail & Related papers  (2025-07-02T21:46:28Z)
• FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs [55.51300642911766]
  Federated Graph Learning (FGL) empowers clients to collaboratively train Graph neural networks (GNNs) in a distributed manner.<n>FGL methods usually require that the graph data owned by all clients is homophilic to ensure similar neighbor distribution patterns of nodes.<n>We propose FedHERO, an FGL framework designed to harness and share insights from heterophilic graphs effectively.
  arXiv  Detail & Related papers  (2025-04-29T22:23:35Z)
• Personalized One-shot Federated Graph Learning for Heterogeneous Clients [11.438281045702976]
  Federated Graph Learning (FGL) aims to enhance model utility by training personalized models tailored to client needs.<n>Existing pFGL methods require numerous communication rounds under heterogeneous graphs.<n>One-shot Federated Learning (OFL) enables collaboration in a single round, but is ineffective for graph data.<n>We introduce a two-stage personalized training approach that adaptively balances local personal information and global insights.
  arXiv  Detail & Related papers  (2024-11-18T05:59:29Z)
• Federated Graph Learning with Graphless Clients [52.5629887481768]
  Federated Graph Learning (FGL) is tasked with training machine learning models, such as Graph Neural Networks (GNNs) We propose a novel framework FedGLS to tackle the problem in FGL with graphless clients.
  arXiv  Detail & Related papers  (2024-11-13T06:54:05Z)
• Federated Hypergraph Learning with Local Differential Privacy: Toward Privacy-Aware Hypergraph Structure Completion [9.163655213173067]
  FedHGL is a first-of-its-kind framework for federated hypergraph learning on disjoint and privacy-constrained hypergraph partitions.<n>We develop FedHGL, a first-of-its-kind framework for federated hypergraph learning on disjoint and privacy-constrained hypergraph partitions.
  arXiv  Detail & Related papers  (2024-08-09T16:31:41Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• FedSheafHN: Personalized Federated Learning on Graph-structured Data [22.825083541211168]
  We propose a model called FedSheafHN, which embeds each client's local subgraph into a server-constructed collaboration graph. Our model improves the integration and interpretation of complex client characteristics. It also has fast model convergence and effective new clients generalization.
  arXiv  Detail & Related papers  (2024-05-25T04:51:41Z)
• GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks [72.01829954658889]
  This paper introduces the mathematical definition of this novel problem setting. We devise a general framework that coordinates a single graph-shared structure learner and multiple graph-specific GNNs. The well-trained structure learner can directly produce adaptive structures for unseen target graphs without any fine-tuning.
  arXiv  Detail & Related papers  (2023-06-20T03:33:22Z)
• Graph Generation with Diffusion Mixture [57.78958552860948]
  Generation of graphs is a major challenge for real-world tasks that require understanding the complex nature of their non-Euclidean structures. We propose a generative framework that models the topology of graphs by explicitly learning the final graph structures of the diffusion process.
  arXiv  Detail & Related papers  (2023-02-07T17:07:46Z)
• EGRC-Net: Embedding-induced Graph Refinement Clustering Network [66.44293190793294]
  We propose a novel graph clustering network called Embedding-Induced Graph Refinement Clustering Network (EGRC-Net) EGRC-Net effectively utilizes the learned embedding to adaptively refine the initial graph and enhance the clustering performance. Our proposed methods consistently outperform several state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-19T09:08:43Z)
• Graph Information Bottleneck [77.21967740646784]
  Graph Neural Networks (GNNs) provide an expressive way to fuse information from network structure and node features. Inheriting from the general Information Bottleneck (IB), GIB aims to learn the minimal sufficient representation for a given task. We show that our proposed models are more robust than state-of-the-art graph defense models.
  arXiv  Detail & Related papers  (2020-10-24T07:13:00Z)
• Tensor Graph Convolutional Networks for Multi-relational and Robust Learning [74.05478502080658]
  This paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. The proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.
  arXiv  Detail & Related papers  (2020-03-15T02:33:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.