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. Learning Discrete Diffusion of Graphs via Free-Energy Gradient Flows

    Apr 13, 2026Dario Rancati, Jan Maas, Francesco LocatelloDiffusion ModelsGraph Diffusion

    Institute of Science and Technology Austria

  2. Bias mitigation in graph diffusion models

    Apr 2, 2026Meng Yu, Kun ZhanDiffusion ModelsGraph Diffusion

    School of Information Science & Engineering, Lanzhou University

  3. PiGRAND: Physics-informed Graph Neural Diffusion for Intelligent Additive Manufacturing

    Mar 16, 2026Benjamin Uhrich, Tim Häntschel, Erhard RahmPhysics-Informed GNNsGraph Diffusion

    Center for Scalable Data Analytics and Artificial Intelligence Dresden/Leipzig, Germany. · Leipzig University, Leipzig, Germany.

  4. Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach

    Mar 16, 2026Mengyao Zhou, Zhiheng Zhou, Xiao Han +3Over-Smoothing in GNNsHypergraph Neural Networks

    the Academy of Mathematics and Systems Science, Chinese Academy of Sciences and also with the University of Chinese Academy of Sciences, Beijing 100190, China · the School of Mathematics and Statistics, Shandong University, Weihai, Shandong 264209, China · School of Artificial Intelligence, Beihang University, Beijing 100191, China +1

  5. MorphSNN: Adaptive Graph Diffusion and Structural Plasticity for Spiking Neural Networks

    Mar 15, 2026Yongsheng Huang, Peibo Duan, Yujie Wu +7Spiking Neural NetworksDynamic Neural Networks

    School of Software, Northeastern University, China · Guangdong Institute of Intelligence Science and Technolog, China · The Hong Kong Polytechnic University, China +1

  6. Semantic Level of Detail for Knowledge Graphs: Discovering Abstraction Boundaries via Spectral Heat Diffusion

    Mar 9, 2026Edward IzgorodinKnowledge GraphsGraph Clustering

    Mnemoverse.AI, Funchal, Madeira, Portugal

  7. Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

    Mar 2, 2026Wendi Wang, Jiaxi Yang, Yongkang Du +1Graph GenerationGraph Diffusion

    Purdue University · Pennsylvania State University

  8. DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation

    Feb 22, 2026Aleksei Liuliakov, Luca Hermes, Barbara HammerGraph GenerationGraph Diffusion

    Machine Learning Group, Bielefeld University, Germany

  9. Geometry-Induced Diffusion on Graphs: A Learnable Weighted Laplacian for Spectral GNNs

    Feb 20, 2026Mia Zosso, Ali Hariri, Victor Kawasaki-Borruat +2Long-Range Graph LearningGraph Representation Learning

    École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland · École Normale Supérieure – PSL, Paris, France

  10. MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

    Feb 19, 2026Hojung Jung, Rodrigo Hormazabal, Jaehyeong Jo +5Molecular Graph GenerationDiffusion Models

    KAIST AI · LG AI Research · Seoul National University

  11. Out-of-Distribution Detection in Molecular Complexes via Diffusion Models for Irregular Graphs

    Dec 20, 2025David Graber, Victor Armegioiu, Rebecca Buller +1Diffusion-Based OOD DetectionOOD Detection

    Seminar for Applied Mathematics, Department of Mathematics and ETH AI Center, ETH Zurich, 8092 Zurich, Switzerland · Institute for Computational Life Sciences, Zurich University of Applied Sciences, 8820 Waedenswil, Switzerland · Department of Chemistry, Biochemistry and Pharmaceutical Sciences, University of Bern, 3012 Bern, Switzerland

  12. Fractional Heat Kernel for Semi-Supervised Graph Learning with Small Training Sample Size

    Oct 6, 2025Farid Bozorgnia, Vyacheslav Kungurtsev, Shirali Kadyrov +1Over-Smoothing in GNNsGraph-Based Semi-Supervised Learning

  13. Double-Diffusion: Balancing Speed, Accuracy, and Uncertainty in Probabilistic Forecasting for Urban Sensor Networks

    Jun 29, 2025Hanlin Dong, Arian Prabowo, Hao Xue +4Spatiotemporal ForecastingDiffusion Model Inference Acceleration

    University of New South Wales Sydney, Australia · University of Maryland College Park, United States · The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China

  14. Backdoor Attacks on Discrete Graph Diffusion Models

    Mar 8, 2025Jiawen Wang, Samin Bin Karim, Yuan Hong +1Graph GenerationBackdoor Attacks

    Department of Computer Science, Illinois Institute of Technology · School of Computing, University of Connecticut

  15. Parametrized Power-Iteration Clustering for Directed Graphs

    Oct 1, 2022Gwendal Debaussart-Joniec, Harry Sevi, Matthieu Jonckheere +1Graph ClusteringGraph Embedding

    Universit´e Paris-Saclay, ENS Paris-Saclay, Centre Borelli, CNRS, France · CNRS, LAAS, France