mlsanityData to 7 Oct 2026

Data-Centric Learning from Unlabeled Graphs with Diffusion Model

arXiv 2303.10108 ↗First posted 17 Mar 2023cs.LGcited by 19

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

Abstract (arXiv)

Graph property prediction tasks are important and numerous. While each task offers a small size of labeled examples, unlabeled graphs have been collected from various sources and at a large scale. A conventional approach is training a model with the unlabeled graphs on self-supervised tasks and then fine-tuning the model on the prediction tasks. However, the self-supervised task knowledge could not be aligned or sometimes conflicted with what the predictions needed. In this paper, we propose to extract the knowledge underlying the large set of unlabeled graphs as a specific set of useful data points to augment each property prediction model. We use a diffusion model to fully utilize the unlabeled graphs and design two new objectives to guide the model's denoising process with each task's labeled data to generate task-specific graph examples and their labels. Experiments demonstrate that our data-centric approach performs significantly better than fifteen existing various methods on fifteen tasks. The performance improvement brought by unlabeled data is visible as the generated labeled examples unlike the self-supervised learning.

Key facts. Cited by 19 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 46 of its 71 references that are in the map. First posted on arXiv 17 Mar 2023.

Builds on

46 of 71 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022DiGress: Discrete Denoising diffusion for graph generation29 Sep
  2. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations5 Feb
  3. 2020Permutation Invariant Graph Generation via Score-Based Generative Modeling2 Mar

Other references · 43

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  8. 2018How Powerful are Graph Neural Networks?cited by 4,355
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  10. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  11. 2018Deep Graph Infomaxcited by 1,101
  12. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
31 more
  1. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  2. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  3. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  4. 2019On Variational Bounds of Mutual Informationcited by 550
  5. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  6. 2019Deep Evidential Regressioncited by 354
  7. 2019Label Propagation for Deep Semi-supervised Learningcited by 287
  8. 2021Graph Contrastive Learning Automatedcited by 287
  9. 2017Data Augmentation Generative Adversarial Networkscited by 278
  10. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 258
  11. 2020Data Augmentation for Graph Neural Networkscited by 200
  12. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  13. 2021Motif-based Graph Self-Supervised Learning for Molecular Property Predictioncited by 159
  14. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
  15. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  16. 2021Self-supervised Graph-level Representation Learning with Local and Global Structurecited by 125
  17. 2018GAN Augmentation: Augmenting Training Data using Generative Adversarial Networkscited by 107
  18. 2021Multi-Task Self-Training for Learning General Representationscited by 85
  19. 2022Graph Rationalization with Environment-based Augmentationscited by 70
  20. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  21. 2022The Effects of Regularization and Data Augmentation are Class Dependentcited by 67
  22. 2019Mol-CycleGAN - a generative model for molecular optimizationcited by 66
  23. 2021MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graphcited by 65
  24. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  25. 2022Does GNN Pretraining Help Molecular Representation?cited by 59
  26. 2020Robust Optimization as Data Augmentation for Large-scale Graphscited by 58
  27. 2021Local Augmentation for Graph Neural Networkscited by 52
  28. 2018Feature Space Transfer for Data Augmentationcited by 21
  29. 2022Graph Self-supervised Learning with Accurate Discrepancy Learningcited by 21
  30. 2022Automated Data Augmentations for Graph Classificationcited by 19
  31. 2022Analyzing Data-Centric Properties for Graph Contrastive Learningcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 10; 2025: 4.

19 papers.

Sort:

By area:

  1. 2023Large Language Models on Graphs: A Comprehensive Surveycited by 190
  2. 2024Position: Graph Foundation Models are Already Herecited by 84
  3. 2024Discrete-state Continuous-time Diffusion for Graph Generationcited by 73
  4. 2024Graph Diffusion Transformers for Multi-Conditional Molecular Generationcited by 44
  5. 2024Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planningcited by 29
  6. 2024Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Modelscited by 21
  7. 2023Motif-aware Attribute Masking for Molecular Graph Pre-trainingcited by 16
  8. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  9. 2023Semi-Supervised Graph Imbalanced Regressioncited by 14
  10. 2023Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networkscited by 14
  11. 2024Cross-Domain Graph Data Scaling: A Showcase with Diffusion Modelscited by 8
  12. 2024Learning Molecular Representation in a Cellcited by 8
7 more
  1. 2025MolTextNet: A Two-Million Molecule-Text Dataset for Multimodal Molecular Learningcited by 6
  2. 2025Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidancecited by 5
  3. 2024TDNetGen: Empowering Complex Network Resilience Prediction with Generative Augmentation of Topology and Dynamicscited by 3
  4. 2024Large Generative Graph Modelscited by 2
  5. 2024Enhancing Node Representations for Real-World Complex Networks with Topological Augmentationcited by 0
  6. 2025Toward Data-centric Directed Graph Learning: An Entropy-driven Approachcited by 0
  7. 2025Scaffold-Aware Generative Augmentation and Reranking for Enhanced Virtual Screeningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Graffe: Graph Representation Learning via Diffusion Probabilistic Models
  2. 2023Directional diffusion models for graph representation learning
  3. 2024From Graph Diffusion to Graph Classification
  4. 2025Graph Representation Learning with Diffusion Generative Models
  5. 2024Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
  6. 2025DiffGraph: Heterogeneous Graph Diffusion Model
  7. 2026Generative Diffusion Models of Stochastic Graph Signals
  8. 2023Diffusion Probabilistic Models for Structured Node Classification