Graph Diffusion

Ask about this topic

Overview

Graph diffusion describes processes that spread signals, labels, or probability across connected nodes, and it underpins both graph learning and generation of graph-structured data. Methods include spectral heat kernels and random walks, neural diffusion operators such as personalized PageRank and sheaf-based propagation, and continuous or discrete denoising models such as score-based diffusion and DiGress-style methods. These approaches are used for node classification and clustering, molecular and network generation, forecasting on sensor graphs, and prediction on irregular physical meshes. A central tension is that stronger or longer-range propagation can capture useful global structure but also cause oversmoothing, while generative models must balance fidelity, sampling cost, structural constraints, and risks such as memorization.

Latest papers

CardsList

75 papers14 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

  1. From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion

    Oct 29, 2026Jiaqi Wang, Yisen Gao, Huayang Shi +7KG CompletionLink Prediction

    Tongji University · The Chinese University of Hong Kong · The Hong Kong University of Science and Technology +1

  2. ActionRAG: Evidence-Refining Graph Diffusion for Long-Term Memory in LLM Agents

    Oct 23, 2026Navyansh Mahla, Sashank VandrangiLLM Agent MemoryGraph-Based Agent Memory

    Actioneer, Mountain View, California, USA

  3. GraphCAD: Geometry-Aware Diffusion on Edge-Adjacency Graphs for CAD Generation

    Oct 22, 2026Wenhao Zheng, Xianggen Liu, Li Yue +23D Shape GenerationGraph Diffusion

    College of Computer Science, Sichuan University · Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education · Dongfang Electric (Chengdu) Innovation Research Co., Ltd. +1

  4. Logic-Guided Graph Denoising Diffusion Models

    Oct 16, 2026Samuel Cognolato, Luciano Serafini, Alessandro Sperduti +1Graph GenerationConstrained Generative Modeling

    Department of Mathematics “Tullio Levi-Civita”, University of Padova, Padova, Italy · Fondazione Bruno Kessler (FBK), Trento, Italy · Human Inspired Technology Research Centre (HIT), University of Padova, Padova, Italy +1

  5. Colored Graph Signal Diffusion Models

    Oct 12, 2026Yiğit Berkay Uslu, Samar Hadou, Shirin Saeedi Bidokhti +1Diffusion ModelsGraph Diffusion

    Dept. of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA

  6. MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation

    Oct 12, 2026Protyay Dey, Ayush Roy, Hyuna Cho +2Functional ConnectivityNeuroimaging

    University at Buffalo, SUNY, USA · National Institutes of Health, USA · POSTECH, South Korea

  7. Your Discrete Graph Diffusion Model is Secretly Memorizing

    Oct 9, 2026Adarsh Jamadandi, Nicolas KerivenMemorization in Generative ModelsGraph Diffusion

    CNRS, IRISA, Rennes, France

  8. When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors

    Oct 9, 2026Adarsh Jamadandi, Nicolas Keriven, Aline RoumyGraph GenerationGraph Diffusion

    CNRS, IRISA, Rennes, France1 · INRIA, Rennes, France2

  9. Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective

    Oct 3, 2026André Ribeiro, Germano Barcelos, Amauri H. Souza +2Over-Squashing in GNNsGraph Neural Networks

    Getulio Vargas Foundation · Federal University of Viçosa · Federal Institute of Ceará, 2δ AI +2

  10. Discrete Diffusion for Large Graph Generation via Structural Candidate Restriction

    Oct 2, 2026Yassin Mohamadi, Zeno Geradts, Marcel WorringGraph GenerationDiffusion Models

  11. Explainable Molecular Structure Inference from GC--MS with Diffusion Models and LLM Reranking

    Oct 2, 2026Changlin Liu, Tianyu Yi, Chengchun Liu +2Molecular Graph GenerationMass Spectrometry

  12. Graph Representation via Elements of Discrete Morse and Cobordism Theories

    Oct 1, 2026Jennifer Rozenblit, Chenguang Yang, Yuxin Liu +2Diffusion Model GuidanceTopological Representation Learning

    Department of Mathematics; University of Texas, Austin · Department of Statistics; University of California, Riverside · Department of Statistics; Virginia Tech

  13. Network World Models as Environments for Algorithm Design on Complex Systems

    Oct 1, 2026Rishab Alagharu, Hongji Pu, Zeeshan Memon +3Automated Algorithm DiscoveryWorld Model-Based Planning

    Emory University · University of Illinois Urbana-Champaign

  14. Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals

    Sep 30, 2026Jinwei Li, Daniel TenbrinckGraph Signal ProcessingDiffusion Model Inference Acceleration

    Department of Data Science Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen, Germany

  15. Propagate, Then Sharpen: Post-Hoc Refinement of Frozen Node Classifiers

    Sep 28, 2026Preben Johnsen Bentdal, Nello Blaser, Xue-Cheng TaiGraph-Based Semi-Supervised LearningClassification

    Department of Informatics, University of Bergen · Norwegian Research Centre (NORCE)

  16. From Graphs to Feeders: Constraint-Guided Diffusion for Rule-Compliant Feeder Generation

    Sep 24, 2026Yu Qin, Andrew Glaws, Aadil Latif +1Constrained Generative ModelingDiffusion Models

    National Laboratory of the Rockies, Golden, Colorado, USA

  17. ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation

    Sep 14, 2026Salvatore Romano, Marco Grassia, Pietro Liò +1Graph GenerationDiffusion Guidance

    Department of Electrical, Electronic and Computer Engineering, University of Catania, Italy · Department of Computer Science and Technology, University of Cambridge, UK · University Campus Bio-Medico of Rome, Italy

  18. Generation of High-Level Concepts in 3D Scene Graphs via Autoregressive Diffusion

    Aug 28, 2026Jose Andres Millan-Romera, Samuel Cognolato, Holger Voos +23D SGGAutoregressive Generation

    Automation and Robotics Research Group, SnT University of Luxembourg, Luxembourg · University of Padova, Padova, Italy · Fondazione Bruno Kessler, Trento, Italy +1

  19. MDTE: Minority-Aware Diffusion over Temporal Edge Events for Imbalanced Node Classification

    Aug 25, 2026Zhou Zelong, Zhang Tianming, Yang Zhengyi +4Node ClassificationClass-Imbalanced Learning

    Zhejiang University of Technology Hangzhou, China · The University of Sydney Sydney, Australia · Vecton AI Australia

  20. Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation

    Aug 21, 2026Yanglei Gan, Peng He, Run Lin +3Temporal KGsTemporal Link Prediction

    Southwest Minzu University, Chengdu, China · University of Electronic Science and Technology of China, Chengdu, China · Weixin Group, Tencent, Gunagzhou, China +1

  21. Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversion

    Aug 12, 2026David Bechtoldt, Sidney BenderCounterfactual EvaluationCounterfactual Explanations

    Machine Learning Group, TU Berlin, 10587 Berlin, Germany · BIFOLD–Berlin Institute for the Foundations of Learning and Data, Berlin, Germany

  22. ProBAG: Prototype-Guided Boundary-Aware Graph Diffusion for Weakly Supervised Histopathology Segmentation

    Aug 12, 2026Duy-Dong Nguyen, Le-Van Thai, Hoai Nhan Pham +3Histopathology Image SegmentationWeakly Supervised Semantic Segmentation

    AI VIETNAM Lab, Vietnam · Department of Mechanical System Engineering, Jeonbuk National University, Republic of Korea · Washington University School of Medicine, Saint Louis, MO, USA +1

  23. HeAD-CP: Heterophily-Aware Diffused Conformal Prediction Sets for Graph Neural Networks

    Jul 28, 2026Phan Binh Nguyen Lam, Nguyen Thai AnhGraph Neural NetworksConformal Prediction

    Faculty of Information Technology, University of Science, Vietnam National University, Ho Chi Minh City, Vietnam · Faculty of Information Technology, Van Lang School of Technology, Van Lang University, Ho Chi Minh City, Vietnam

  24. MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion

    Jul 20, 2026Tasfia Nuzhat Ornee, Elias Hossain, Ivan Garibay +1Masked Diffusion ModelsMolecular Graph Generation

    University of Central Florida

  25. From Diffusion to Reaction-Diffusion: A Dynamical-Systems View of Oversmoothing in Hypergraph Neural Networks

    Jul 17, 2026Zhiheng Zhou, Mengyao Zhou, Yancheng Chen +3Hypergraph Neural NetworksHypergraph Learning

    School of Mathematics and Statistics, Shandong University, Weihai, Shandong 264209, China · Academy of Mathematics and Systems Science, Chinese Academy of Sciences and also with the University of Chinese Academy of Sciences, Beijing 100190, China

  26. MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion

    Jul 17, 2026Xu Hou, Meiyu Liang, Wei Huang +6Multimodal KGsKG Completion

    Beijing University of Posts and Telecommunications · School of Computer Science, Beijing University of Posts and Telecommunications · Zhejiang University +3

  27. DAPGNet: Dynamic Adaptive Physics-Guided Graph Diffusion Network for Hyperspectral Image Classification

    Jul 16, 2026Pengkun Wang, Weijia Cao, Ning Wang +1Graph Structure LearningHyperspectral Imaging

    National Engineering Laboratory for Satellite Remote Sensing Applications, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China · Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China · Guangzhou University, Guangzhou 510006, China

  28. Measuring Spatial Clustering via Metropolis-Hastings Diffusion Distance

    Jul 16, 2026Thomas Weighill, Chidinma WilliamsClusteringGraph Diffusion

    Department of Mathematics and Statistics, University of North Carolina at Greensboro, Greensboro, NC 27402

  29. DiPhon: Diffusion on Graphons for Scalable Graph Generation

    Jul 8, 2026Sergio Rozada, Yiming Qin, Manuel Madeira +2Graphon TheoryGraph Generation

    King Juan Carlos University · EPFL, Lausanne, Switzerland · University of Pennsylvania

  30. Generative Diffusion Models of Stochastic Graph Signals

    Jul 7, 2026Yiğit Berkay Uslu, Samar Hadou, Sergio Rozada +2Graph Neural NetworksFinancial Forecasting

    Dept. of Electrical and Systems Eng., University of Pennsylvania, Philadelphia, PA 19104 USA · Department of Signal Processing and Communications, King Juan Carlos University, Madrid, Spain