mlsanityData to 7 Oct 2026

SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

arXiv 2204.01613 ↗First posted 4 Apr 2022cs.LG cs.AI stat.MLcited by 96

Not on the map. Why?

Cited by 38 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We approach the graph generation problem from a spectral perspective by first generating the dominant parts of the graph Laplacian spectrum and then building a graph matching these eigenvalues and eigenvectors. Spectral conditioning allows for direct modeling of the global and local graph structure and helps to overcome the expressivity and mode collapse issues of one-shot graph generators. Our novel GAN, called SPECTRE, enables the one-shot generation of much larger graphs than previously possible with one-shot models. SPECTRE outperforms state-of-the-art deep autoregressive generators in terms of modeling fidelity, while also avoiding expensive sequential generation and dependence on node ordering. A case in point, in sizable synthetic and real-world graphs SPECTRE achieves a 4-to-170 fold improvement over the best competitor that does not overfit and is 23-to-30 times faster than autoregressive generators.

Key facts. Cited by 96 papers in the map (data through 7 Oct 2026). Builds on 49 of its 83 references that are in the map. First posted on arXiv 4 Apr 2022.

Builds on

49 of 83 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Layer Normalizationcited by 5,579
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2017Improved Training of Wasserstein GANscited by 2,223
  9. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  10. 2016Variational Graph Auto-Encoderscited by 1,373
  11. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  12. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
37 more
  1. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  2. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  3. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  4. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  5. 2019Provably Powerful Graph Networkscited by 385
  6. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  7. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  8. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
  9. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  10. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 231
  11. 2018Learning Deep Generative Models of Graphscited by 227
  12. 2018Adversarial Audio Synthesiscited by 222
  13. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 204
  14. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
  15. 2021E(n) Equivariant Normalizing Flowscited by 165
  16. 2021Equivariant Subgraph Aggregation Networkscited by 154
  17. 2021Nested Graph Neural Networkscited by 136
  18. 2018NetGAN: Generating Graphs via Random Walkscited by 129
  19. 2017GraphGAN: Graph Representation Learning with Generative Adversarial Netscited by 121
  20. 2021DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networkscited by 117
  21. 2019Graph Normalizing Flowscited by 103
  22. 2017Learning Structural Node Embeddings Via Diffusion Waveletscited by 97
  23. 2020Building powerful and equivariant graph neural networks with structural message-passingcited by 95
  24. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  25. 2017On the regularization of Wasserstein GANscited by 65
  26. 2020Scalable Deep Generative Modeling for Sparse Graphscited by 63
  27. 2019On Universal Equivariant Set Networkscited by 45
  28. 2021Top-N: Equivariant set and graph generation without exchangeabilitycited by 36
  29. 2017Bayesian stochastic blockmodelingcited by 27
  30. 2019A Two-Step Graph Convolutional Decoder for Molecule Generationcited by 25
  31. 2021Ego-GNNs: Exploiting Ego Structures in Graph Neural Networkscited by 17
  32. 2020Set2Graph: Learning Graphs From Setscited by 16
  33. 2021A Graph VAE and Graph Transformer Approach to Generating Molecular Graphscited by 16
  34. 2019Effective Decoding in Graph Auto-Encoder using Triadic Closurecited by 13
  35. 2016Graphons, mergeons, and so on!cited by 10
  36. 2020Merge-split Markov chain Monte Carlo for community detectioncited by 10
  37. 2018Spectral Graph Forge: Graph Generation Targeting Modularitycited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 20; 2024: 24; 2025: 25; 2026: 24.

96 papers.

Sort:

By area:

  1. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  2. 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Priorcited by 110
  3. 2023Autoregressive Diffusion Model for Graph Generationcited by 82
  4. 2024Variational Flow Matching for Graph Generationcited by 78
  5. 2024Discrete-state Continuous-time Diffusion for Graph Generationcited by 73
  6. 2022Diffusion Models for Graphs Benefit From Discrete State Spacescited by 69
  7. 2023Graph Generation with Diffusion Mixturecited by 52
  8. 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarkscited by 52
  9. 2023AbDiffuser: Full-Atom Generation of in vitro Functioning Antibodiescited by 35
  10. 2023Efficient and Scalable Graph Generation through Iterative Local Expansioncited by 35
  11. 2024Cometh: A continuous-time discrete-state graph diffusion modelcited by 29
  12. 2023SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generationcited by 26
38 more
  1. 2023Sparse Training of Discrete Diffusion Models for Graph Generationcited by 26
  2. 2023Data-centric Graph Learning: A Surveycited by 22
  3. 2024Generative Modelling of Structurally Constrained Graphscited by 17
  4. 2023Graph Distillation with Eigenbasis Matchingcited by 16
  5. 2025Graph Generative Pre-trained Transformercited by 16
  6. 2023A Simple and Scalable Representation for Graph Generationcited by 15
  7. 2024EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editingcited by 14
  8. 2024Advancing Graph Generation through Beta Diffusioncited by 13
  9. 2024Graph Diffusion Policy Optimizationcited by 12
  10. 2025Flatten Graphs as Sequences: Transformers are Scalable Graph Generatorscited by 12
  11. 2024LLM-Based Multi-Agent Systems are Scalable Graph Generative Modelscited by 11
  12. 2024A Graph is Worth K Words: Euclideanizing Graph using Pure Transformercited by 10
  13. 2023E(n)-equivariant Graph Neural Cellular Automatacited by 9
  14. 2025Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generationcited by 9
  15. 2024Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matchingcited by 8
  16. 2024Generating Graphs via Spectral Diffusioncited by 8
  17. 2024HYGENE: A Diffusion-based Hypergraph Generation Methodcited by 8
  18. 2025Bures-Wasserstein Flow Matching for Graph Generationcited by 7
  19. 2023GraphGUIDE: interpretable and controllable conditional graph generation with discrete Bernoulli diffusioncited by 6
  20. 2024Reviving Life on the Edge: Joint Score-Based Graph Generation of Rich Edge Attributescited by 6
  21. 2024InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis with Semantic Graph Priorcited by 6
  22. 2024Challenges of Generating Structurally Diverse Graphscited by 6
  23. 2025HOG-Diff: Higher-Order Guided Diffusion for Graph Generationcited by 6
  24. 2025Learning Flexible Forward Trajectories for Masked Molecular Diffusioncited by 6
  25. 2022A Framework for Large Scale Synthetic Graph Dataset Generationcited by 5
  26. 2023HiGen: Hierarchical Graph Generative Networkscited by 5
  27. 2023Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoningcited by 4
  28. 2023W2SAT: Learning to generate SAT instances from Weighted Literal Incidence Graphscited by 3
  29. 2023Size Matters: Large Graph Generation with HiGGscited by 3
  30. 2024Improving Molecule Generation and Drug Discovery with a Knowledge-enhanced Generative Modelcited by 3
  31. 2025Generating Directed Graphs with Dual Attention and Asymmetric Encodingcited by 3
  32. 2023Graph Generation with K2-treescited by 2
  33. 2023CDGraph: Dual Conditional Social Graph Synthesizing via Diffusion Modelcited by 2
  34. 2024Random Walk Diffusion for Efficient Large-Scale Graph Generationcited by 2
  35. 2024NetDiff: Graph Diffusion with Improved Global Capabilities to Generate and Update Mobile Network Topologiescited by 2
  36. 2025Fast Graph Generation via Autoregressive Noisy Filtration Modelingcited by 2
  37. 2025SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusioncited by 2
  38. 2025Graph Generation with Spectral Geodesic Flow Matchingcited by 2

50 most cited of 96 All 96 (JSON)