mlsanityData to 14 Oct 2026

From Graph Diffusion to Graph Classification

arXiv 2411.17236 ↗First posted 26 Nov 2024cs.LG cs.AIcited by 2

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Generative models such as diffusion models have achieved remarkable success in state-of-the-art image and text tasks. Recently, score-based diffusion models have extended their success beyond image generation, showing competitive performance with discriminative methods in image em classification tasks~citezimmermann2021score. However, their application to classification in the em graph domain, which presents unique challenges such as complex topologies, remains underexplored. We show how graph diffusion models can be applied for graph classification. We find that to achieve competitive classification accuracy, score-based graph diffusion models should be trained with a novel training objective that is tailored to graph classification. In experiments with a sampling-based inference method, our discriminative training objective achieves state-of-the-art graph classification accuracy.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 20 of its 29 references that are in the map. First posted on arXiv 26 Nov 2024.

Builds on

20 of 29 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Autoregressive Diffusion Model for Graph Generation17 Jul
  2. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design11 Oct
  3. 2022DiGress: Discrete Denoising diffusion for graph generation29 Sep
  4. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations5 Feb

Other references · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  6. 2017Inductive Representation Learning on Large Graphscited by 6,320
  7. 2018How Powerful are Graph Neural Networks?cited by 4,393
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  10. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  11. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  12. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 313
4 more
  1. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 310
  2. 2023Your Diffusion Model is Secretly a Zero-Shot Classifiercited by 306
  3. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  4. 2021Score-Based Generative Classifierscited by 53

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026DiffImaginE: Imagine to Verify Entity Types with Diffusioncited by 0
  2. 2026From topology learning to graph generation: A unifying perspectivecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Graph Representation Learning with Diffusion Generative Models
  2. 2023Generative Diffusion Models on Graphs: Methods and Applications
  3. 2025Graffe: Graph Representation Learning via Diffusion Probabilistic Models
  4. 2024Diffusion-based Graph Generative Methods
  5. 2024Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
  6. 2024Towards understanding Diffusion Models (on Graphs)
  7. 2025Do Graph Diffusion Models Accurately Capture and Generate Substructure Distributions?
  8. 2025Diffusion on Graph: Augmentation of Graph Structure for Node Classification