SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion

• URL: http://arxiv.org/abs/2508.14352v1
• Date: Wed, 20 Aug 2025 01:47:46 GMT
• Title: SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion
• Authors: Junwei Su, Shan Wu,
• Abstract summary: Graph diffusion generative models (GDGMs) have emerged as powerful tools for generating high-quality graphs.<n>GDGMs struggle to scale to large graphs due to their high memory requirements.<n>We propose the block graph diffusion model, which refines graph representations into a block graph space.
• Score: 2.3043270848984
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph diffusion generative models (GDGMs) have emerged as powerful tools for generating high-quality graphs. However, their broader adoption faces challenges in \emph{scalability and size generalization}. GDGMs struggle to scale to large graphs due to their high memory requirements, as they typically operate in the full graph space, requiring the entire graph to be stored in memory during training and inference. This constraint limits their feasibility for large-scale real-world graphs. GDGMs also exhibit poor size generalization, with limited ability to generate graphs of sizes different from those in the training data, restricting their adaptability across diverse applications. To address these challenges, we propose the stochastic block graph diffusion (SBGD) model, which refines graph representations into a block graph space. This space incorporates structural priors based on real-world graph patterns, significantly reducing memory complexity and enabling scalability to large graphs. The block representation also improves size generalization by capturing fundamental graph structures. Empirical results show that SBGD achieves significant memory improvements (up to 6$\times$) while maintaining comparable or even superior graph generation performance relative to state-of-the-art methods. Furthermore, experiments demonstrate that SBGD better generalizes to unseen graph sizes. The significance of SBGD extends beyond being a scalable and effective GDGM; it also exemplifies the principle of modularization in generative modeling, offering a new avenue for exploring generative models by decomposing complex tasks into more manageable components.

Related papers

• VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention [61.96837866507746]
  VecFormer is an efficient and highly generalizable model for node classification.<n>VecFormer outperforms the existing Graph Transformer in both performance and speed.
  arXiv  Detail & Related papers  (2026-02-23T09:10:39Z)
• G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge [88.82814893945077]
  Large language models (LLMs) excel at complex reasoning but remain limited by static and incomplete parametric knowledge.<n>Recent graph-enhanced RAG (GraphRAG) attempts to bridge this gap by constructing tailored graphs and enabling LLMs to reason on them.<n>G-reasoner is a unified framework that integrates graph and language foundation models for reasoning over diverse graph-structured knowledge.
  arXiv  Detail & Related papers  (2025-09-29T04:38:12Z)
• 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)
• Scalable Graph Generative Modeling via Substructure Sequences [37.64864614356634]
  We introduce Generative Graph Pattern Machine (G$2$PM), a generative Transformer pre-training framework for graphs.<n>G$2$PM represents graph instances as sequences of substructures, and employs generative pre-training over the sequences to learn generalizable, transferable representations.<n>On the ogbn-arxiv benchmark, G$2$PM continues to improve with model sizes up to 60M parameters, outperforming prior generative approaches that plateau at significantly smaller scales.
  arXiv  Detail & Related papers  (2025-05-22T02:16:34Z)
• RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs [58.10503898336799]
  We introduce the RAG-on-Graphs Library (RGL), a modular framework that seamlessly integrates the complete RAG pipeline.<n>RGL addresses key challenges by supporting a variety of graph formats and integrating optimized implementations for essential components.<n>Our evaluations demonstrate that RGL not only accelerates the prototyping process but also enhances the performance and applicability of graph-based RAG systems.
  arXiv  Detail & Related papers  (2025-03-25T03:21:48Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs)<n>This framework provides a standardized setting to evaluate GNNs across diverse datasets.<n>We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• DHIL-GT: Scalable Graph Transformer with Decoupled Hierarchy Labeling [10.556366638048384]
  Graph Transformer (GT) has recently emerged as a promising neural network architecture for learning graph-structured data.<n>We propose DHIL-GT, a scalable Graph Transformer that simplifies network learning by fully decoupling the graph computation to a separate stage in advance.<n> DHIL-GT is efficient in terms of computational boost and mini-batch capability over existing scalable Graph Transformer designs on large-scale benchmarks.
  arXiv  Detail & Related papers  (2024-12-06T02:59:01Z)
• AnyGraph: Graph Foundation Model in the Wild [16.313146933922752]
  Graph foundation models offer the potential to learn robust, generalizable representations from graph data. In this work, we investigate a unified graph model, AnyGraph, designed to handle key challenges. Our experiments on diverse 38 graph datasets have demonstrated the strong zero-shot learning performance of AnyGraph.
  arXiv  Detail & Related papers  (2024-08-20T09:57:13Z)
• Advancing Graph Generation through Beta Diffusion [49.49740940068255]
  Graph Beta Diffusion (GBD) is a generative model specifically designed to handle the diverse nature of graph data. We propose a modulation technique that enhances the realism of generated graphs by stabilizing critical graph topology.
  arXiv  Detail & Related papers  (2024-06-13T17:42:57Z)
• Improving Graph Generation by Restricting Graph Bandwidth [0.7874708385247353]
  Deep graph generative modeling has proven capable of learning the distribution of complex, multi-scale structures characterizing real-world graphs. One of the main limitations of existing methods is their large output space. We propose a novel approach that significantly reduces the output space of existing graph generative models.
  arXiv  Detail & Related papers  (2023-01-25T22:27:46Z)
• Graph Generative Model for Benchmarking Graph Neural Networks [73.11514658000547]
  We introduce a novel graph generative model that learns and reproduces the distribution of real-world graphs in a privacy-controlled way. Our model can successfully generate privacy-controlled, synthetic substitutes of large-scale real-world graphs that can be effectively used to benchmark GNN models.
  arXiv  Detail & Related papers  (2022-07-10T06:42:02Z)
• Scaling R-GCN Training with Graph Summarization [71.06855946732296]
  Training of Relation Graph Convolutional Networks (R-GCN) does not scale well with the size of the graph. In this work, we experiment with the use of graph summarization techniques to compress the graph. We obtain reasonable results on the AIFB, MUTAG and AM datasets.
  arXiv  Detail & Related papers  (2022-03-05T00:28:43Z)
• Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming [48.99614465020678]
  We introduce a novel self-supervised graph representation learning algorithm via Graph Contrastive Adjusted Zooming. This mechanism enables G-Zoom to explore and extract self-supervision signals from a graph from multiple scales. We have conducted extensive experiments on real-world datasets, and the results demonstrate that our proposed model outperforms state-of-the-art methods consistently.
  arXiv  Detail & Related papers  (2021-11-20T22:45:53Z)

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.