mlsanityData to 14 Oct 2026

A Survey on Deep Graph Generation: Methods and Applications

arXiv 2203.06714 ↗First posted 13 Mar 2022cs.LG cs.SI q-bio.MNcited by 69

Not on the map. Why?

Abstract (arXiv)

Graphs are ubiquitous in encoding relational information of real-world objects in many domains. Graph generation, whose purpose is to generate new graphs from a distribution similar to the observed graphs, has received increasing attention thanks to the recent advances of deep learning models. In this paper, we conduct a comprehensive review on the existing literature of deep graph generation from a variety of emerging methods to its wide application areas. Specifically, we first formulate the problem of deep graph generation and discuss its difference with several related graph learning tasks. Secondly, we divide the state-of-the-art methods into three categories based on model architectures and summarize their generation strategies. Thirdly, we introduce three key application areas of deep graph generation. Lastly, we highlight challenges and opportunities in the future study of deep graph generation. We hope that our survey will be useful for researchers and practitioners who are interested in this exciting and rapidly-developing field.

Key facts. Cited by 69 papers in the map (data through 14 Oct 2026). Builds on 84 of its 140 references that are in the map. First posted on arXiv 13 Mar 2022.

Builds on

84 of 140 references.

References · 84

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Generative Adversarial Networkscited by 5,627
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2016Density estimation using Real NVPcited by 2,042
  9. 2017The Kinetics Human Action Video Datasetcited by 1,909
  10. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  11. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  12. 2018Link Prediction Based on Graph Neural Networkscited by 832
38 more
  1. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  2. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  3. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  4. 2017Masked Autoregressive Flow for Density Estimationcited by 684
  5. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  6. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  7. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 413
  8. 2018MolGAN: An implicit generative model for small molecular graphscited by 393
  9. 2018Deep Learning on Graphs: A Surveycited by 393
  10. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 383
  11. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  12. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 364
  13. 2018Neural Relational Inference for Interacting Systemscited by 339
  14. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
  15. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 297
  16. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 283
  17. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 275
  18. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 270
  19. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 250
  20. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 234
  21. 2018Learning Deep Generative Models of Graphscited by 229
  22. 2017Learning to Represent Programs with Graphscited by 220
  23. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 208
  24. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 185
  25. 2020MoFlow: An Invertible Flow Model for Generating Molecular Graphscited by 185
  26. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 180
  27. 2018NetGAN: Generating Graphs via Random Walkscited by 131
  28. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  29. 2017GraphGAN: Graph Representation Learning with Generative Adversarial Netscited by 121
  30. 2018Syntax-Directed Variational Autoencoder for Structured Datacited by 103
  31. 2019D-VAE: A Variational Autoencoder for Directed Acyclic Graphscited by 98
  32. 2020A Systematic Survey on Deep Generative Models for Graph Generationcited by 94
  33. 2018Learning Multimodal Graph-to-Graph Translation for Molecular Optimizationcited by 88
  34. 2021Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-designcited by 86
  35. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  36. 2019MolecularRNN: Generating realistic molecular graphs with optimized propertiescited by 82
  37. 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 71
  38. 2018NeVAE: A Deep Generative Model for Molecular Graphscited by 67

50 most cited of 84 All 84 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 13; 2024: 17; 2025: 25; 2026: 8.

69 papers.

Sort:

By area:

  1. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
  2. 2023Autoregressive Diffusion Model for Graph Generationcited by 83
  3. 2023Generative Diffusion Models on Graphs: Methods and Applicationscited by 81
  4. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  5. 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
  6. 2025AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologiescited by 37
  7. 2023GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentationcited by 31
  8. 2024Graph Condensation: A Surveycited by 23
  9. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  10. 2023Data-centric Graph Learning: A Surveycited by 22
  11. 2023A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availabilitycited by 21
  12. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
38 more
  1. 2025Graph Generative Pre-trained Transformercited by 17
  2. 2025MADGEN: Mass-Spec attends to De Novo Molecular generationcited by 16
  3. 2024Exploring the Potential of Large Language Models in Graph Generationcited by 15
  4. 2025Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networkscited by 14
  5. 2025Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Basescited by 11
  6. 2024HYGENE: A Diffusion-based Hypergraph Generation Methodcited by 9
  7. 2025Bures-Wasserstein Flow Matching for Graph Generationcited by 9
  8. 2024Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networkscited by 8
  9. 2024Neural Graph Generator: Feature-Conditioned Graph Generation using Latent Diffusion Modelscited by 8
  10. 2025HOG-Diff: Higher-Order Guided Diffusion for Graph Generationcited by 8
  11. 2025The quest for the GRAph Level autoEncoder (GRALE)cited by 8
  12. 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapescited by 7
  13. 2024Machine Learning Insides OptVerse AI Solver: Design Principles and Applicationscited by 7
  14. 2023The power of motifs as inductive bias for learning molecular distributionscited by 6
  15. 2024Reviving Life on the Edge: Joint Score-Based Graph Generation of Rich Edge Attributescited by 6
  16. 2025Graph Synthetic Out-of-Distribution Exposure with Large Language Modelscited by 6
  17. 2025Graph Diffusion that can Insert and Deletecited by 6
  18. 2022Realistic Synthetic Social Networks with Graph Neural Networkscited by 5
  19. 2024Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learningcited by 4
  20. 2023Towards Invertible Semantic-Preserving Embeddings of Logical Formulaecited by 3
  21. 2023Size Matters: Large Graph Generation with HiGGscited by 3
  22. 2023On the Role of Edge Dependency in Graph Generative Modelscited by 3
  23. 2024Overcoming Order in Autoregressive Graph Generationcited by 3
  24. 2024Random Walk Diffusion for Efficient Large-Scale Graph Generationcited by 3
  25. 2024Entropy Coding of Unordered Data Structurescited by 3
  26. 2024Knowledge-aware Evolutionary Graph Neural Architecture Searchcited by 3
  27. 2025Graph-Conditional Flow Matching for Relational Data Generationcited by 3
  28. 2025Vector Representations of Vessel Treescited by 3
  29. 2025Fine-Grained Traffic Inference from Road to Lane via Spatio-Temporal Graph Node Generationcited by 3
  30. 2025Accurate and Consistent Graph Model Generation from Text with Large Language Modelscited by 3
  31. 2025A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equationscited by 3
  32. 2026Flowette: Flow Matching with Graphette Priors for Graph Generationcited by 3
  33. 2022Self Supervised Clustering of Traffic Scenes using Graph Representationscited by 2
  34. 2023Random Edge Coding: One-Shot Bits-Back Coding of Large Labeled Graphscited by 2
  35. 2024Large Generative Graph Modelscited by 2
  36. 2026Structural Bias Beyond Homophily: A Study of Fairness in Link Predictioncited by 2
  37. 2023Leveraging Graph Diffusion Models for Network Refinement Taskscited by 1
  38. 2024GraphRCG: Self-Conditioned Graph Generationcited by 1

50 most cited of 69 All 69 (JSON)