Leveraging Graph Diffusion Models for Network Refinement Tasks
On the map: Diffusion models → Flow matching, time series and science
Abstract (arXiv)
Most real-world networks are noisy and incomplete samples from an unknown target distribution. Refining them by correcting corruptions or inferring unobserved regions typically improves downstream performance. Inspired by the impressive generative capabilities that have been used to correct corruptions in images, and the similarities between "in-painting" and filling in missing nodes and edges conditioned on the observed graph, we propose a novel graph generative framework, SGDM, which is based on subgraph diffusion. Our framework not only improves the scalability and fidelity of graph diffusion models, but also leverages the reverse process to perform novel, conditional generation tasks. In particular, through extensive empirical analysis and a set of novel metrics, we demonstrate that our proposed model effectively supports the following refinement tasks for partially observable networks: T1: denoising extraneous subgraphs, T2: expanding existing subgraphs and T3: performing "style" transfer by regenerating a particular subgraph to match the characteristics of a different node or subgraph.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 47 of its 58 references that are in the map. First posted on arXiv 29 Nov 2023.
Builds on
47 of 58 references.
Closest ancestors · 5
Same direction, newest first
- 2023SaGess: Sampling Graph Denoising Diffusion Model for Scalable Graph Generation29 Jun
- 2023Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling6 May
- 2022DiGress: Discrete Denoising diffusion for graph generation29 Sep
- 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations5 Feb
- 2020Permutation Invariant Graph Generation via Score-Based Generative Modeling2 Mar
Other references · 42
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
- 2021Zero-Shot Text-to-Image Generationcited by 4,276
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
- 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
- 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
- 2016Variational Graph Auto-Encoderscited by 1,373
- 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
30 more
- 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
- 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
- 2018Link Prediction Based on Graph Neural Networkscited by 829
- 2020Benchmarking Graph Neural Networkscited by 672
- 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
- 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 526
- 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
- 2022Diffusion Models for Adversarial Purificationcited by 469
- 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 413
- 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
- 2018MolGAN: An implicit generative model for small molecular graphscited by 392
- 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
- 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
- 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
- 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 231
- 2019Position-aware Graph Neural Networkscited by 203
- 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 131
- 2017GraphGAN: Graph Representation Learning with Generative Adversarial Netscited by 121
- 2023DiffCollage: Parallel Generation of Large Content with Diffusion Modelscited by 100
- 2022SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generatorscited by 96
- 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
- 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
- 2022SinDDM: A Single Image Denoising Diffusion Modelcited by 60
- 2022SinFusion: Training Diffusion Models on a Single Image or Videocited by 58
- 2022JPEG Artifact Correction using Denoising Diffusion Restoration Modelscited by 45
- 2022Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidancecited by 33
- 2020The impossibility of low rank representations for triangle-rich complex networkscited by 32
- 2022Improving Diffusion Model Efficiency Through Patchingcited by 15
- 2021On the Power of Edge Independent Graph Modelscited by 13
- 2022Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoderscited by 8
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026Generative Diffusion Models of Stochastic Graph Signals
- 2023Autoregressive Diffusion Model for Graph Generation
- 2025Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation
- 2025Diffusion-Free Graph Generation with Next-Scale Prediction
- 2025Do Graph Diffusion Models Accurately Capture and Generate Substructure Distributions?
- 2024IFH: a Diffusion Framework for Flexible Design of Graph Generative Models
- 2025DiffGraph: Heterogeneous Graph Diffusion Model
- 2025Graph Representation Learning with Diffusion Generative Models