mlsanityData to 7 Oct 2026

Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models

arXiv 2406.01899 ↗First posted 4 Jun 2024cs.LGcited by 8

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

Abstract (arXiv)

Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This 'better with more' phenomenon enables the effectiveness of large-scale pre-training on vast amounts of data. However, current graph pre-training methods struggle to scale up data due to heterogeneity across graphs. To achieve effective data scaling, we aim to develop a general model that is able to capture diverse data patterns of graphs and can be utilized to adaptively help the downstream tasks. To this end, we propose UniAug, a universal graph structure augmentor built on a diffusion model. We first pre-train a discrete diffusion model on thousands of graphs across domains to learn the graph structural patterns. In the downstream phase, we provide adaptive enhancement by conducting graph structure augmentation with the help of the pre-trained diffusion model via guided generation. By leveraging the pre-trained diffusion model for structure augmentation, we consistently achieve performance improvements across various downstream tasks in a plug-and-play manner. To the best of our knowledge, this study represents the first demonstration of a data-scaling graph structure augmentor on graphs across domains.

Key facts. Cited by 8 papers 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 75 of its 106 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

75 of 106 references.

Closest ancestors · 8

Same direction, newest first

  1. 2023Protein Design with Guided Discrete Diffusion31 May
  2. 2023Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling6 May
  3. 2023Data-Centric Learning from Unlabeled Graphs with Diffusion Model17 Mar
  4. 2022Diffusion Models for Graphs Benefit From Discrete State Spaces4 Oct
  5. 2022DiGress: Discrete Denoising diffusion for graph generation29 Sep
  6. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar
  7. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations5 Feb
  8. 2020Permutation Invariant Graph Generation via Score-Based Generative Modeling2 Mar

Other references · 67

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2023Segment Anythingcited by 8,158
  9. 2020Scaling Laws for Neural Language Modelscited by 6,411
  10. 2022Classifier-Free Diffusion Guidancecited by 5,717
  11. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  12. 2018How Powerful are Graph Neural Networks?cited by 4,355
38 more
  1. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  2. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  3. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  4. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  5. 2021Scaling Vision Transformerscited by 993
  6. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  7. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  8. 2018Link Prediction Based on Graph Neural Networkscited by 829
  9. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  10. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  11. 2020Contrastive Multi-View Representation Learning on Graphscited by 651
  12. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  13. 2020Deep Graph Contrastive Representation Learningcited by 535
  14. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  15. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  16. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  17. 2022A Continuous Time Framework for Discrete Denoising Modelscited by 437
  18. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
  19. 2022Is synthetic data from generative models ready for image recognition?cited by 320
  20. 2021Graph Contrastive Learning Automatedcited by 287
  21. 2023Effective Data Augmentation With Diffusion Modelscited by 282
  22. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  23. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 184
  24. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
  25. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
  26. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
  27. 2021Self-supervised Graph-level Representation Learning with Local and Global Structurecited by 125
  28. 2021Exploring the Limits of Large Scale Pre-trainingcited by 104
  29. 2021Large-scale Unsupervised Semantic Segmentationcited by 98
  30. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 84
  31. 2022Graph Rationalization with Environment-based Augmentationscited by 70
  32. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  33. 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
  34. 2023Neural Common Neighbor with Completion for Link Predictioncited by 64
  35. 2020Robust Optimization as Data Augmentation for Large-scale Graphscited by 58
  36. 2021Local Augmentation for Graph Neural Networkscited by 52
  37. 2023Rethinking Tokenizer and Decoder in Masked Graph Modeling for Moleculescited by 49
  38. 2020L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networkscited by 48

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 3.

8 papers.

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2024GLBench: A Comprehensive Benchmark for Graph with Large Language Modelscited by 36
  3. 2025GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuningcited by 13
  4. 2026RAG-GFM: Overcoming In-Memory Bottlenecks in Graph Foundation Models via Retrieval-Augmented Generationcited by 4
  5. 2025A Survey of Cross-domain Graph Learning: Progress and Future Directionscited by 2
  6. 2025GraphProp: Training the Graph Foundation Models using Graph Propertiescited by 1
  7. 2026Mochi: Aligning Pre-training and Inference for Efficient Graph Foundation Models via Meta-Learningcited by 0
  8. 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. 2025DiffGraph: Heterogeneous Graph Diffusion Model
  3. 2024Generative Modelling of Structurally Constrained Graphs
  4. 2025Do Graph Diffusion Models Accurately Capture and Generate Substructure Distributions?
  5. 2024From Graph Diffusion to Graph Classification
  6. 2025SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion
  7. 2026Discrete Diffusion for Large Graph Generation via Structural Candidate Restriction
  8. 2024Unifying Generation and Prediction on Graphs with Latent Graph Diffusion