mlsanityData to 14 Oct 2026

Graphically Structured Diffusion Models

arXiv 2210.11633 ↗First posted 20 Oct 2022cs.LG cs.NE cs.PLcited by 11

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

We introduce a framework for automatically defining and learning deep generative models with problem-specific structure. We tackle problem domains that are more traditionally solved by algorithms such as sorting, constraint satisfaction for Sudoku, and matrix factorization. Concretely, we train diffusion models with an architecture tailored to the problem specification. This problem specification should contain a graphical model describing relationships between variables, and often benefits from explicit representation of subcomputations. Permutation invariances can also be exploited. Across a diverse set of experiments we improve the scaling relationship between problem dimension and our model's performance, in terms of both training time and final accuracy. Our code can be found at https://github.com/plai-group/gsdm.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 40 of its 60 references that are in the map. First posted on arXiv 20 Oct 2022.

Builds on

40 of 60 references.

Closest ancestors · 7

Same direction, newest first

  1. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  3. 2021Structured Denoising Diffusion Models in Discrete State-Spaces7 Jul
  4. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  6. 2020Denoising Diffusion Implicit Models6 Oct
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2022Training language models to follow instructions with human feedbackcited by 15,971
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  9. 2020Longformer: The Long-Document Transformercited by 3,413
  10. 2022Video Diffusion Modelscited by 2,305
  11. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  12. 2020Big Bird: Transformers for Longer Sequencescited by 1,684
21 more
  1. 2020Reformer: The Efficient Transformercited by 1,668
  2. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  3. 2019Generating Long Sequences with Sparse Transformerscited by 1,546
  4. 2015Automatic differentiation in machine learning: a surveycited by 855
  5. 2020Efficient Transformers: A Surveycited by 790
  6. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
  7. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  8. 2021Rethinking Graph Transformers with Spectral Attentioncited by 473
  9. 2020Efficient Content-Based Sparse Attention with Routing Transformerscited by 471
  10. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  11. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 262
  12. 2021Autoregressive Diffusion Modelscited by 210
  13. 2018Learning a SAT Solver from Single-Bit Supervisioncited by 200
  14. 2019SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solvercited by 173
  15. 2017Recurrent Relational Networkscited by 72
  16. 2018An Introduction to Probabilistic Programmingcited by 63
  17. 2016Inference Compilation and Universal Probabilistic Programmingcited by 32
  18. 2017Faithful Inversion of Generative Models for Effective Amortized Inferencecited by 29
  19. 2022One Model, Any CSP: Graph Neural Networks as Fast Global Search Heuristics for Constraint Satisfactioncited by 27
  20. 2016Deep Amortized Inference for Probabilistic Programscited by 23
  21. 2017Using Synthetic Data to Train Neural Networks is Model-Based Reasoningcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 3; 2026: 3.

11 papers.

  1. 2024All-in-one simulation-based inferencecited by 74
  2. 2025Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Modelscited by 13
  3. 2023Visual Chain-of-Thought Diffusion Modelscited by 12
  4. 2024Compositional simulation-based inference for time seriescited by 9
  5. 2023Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidancecited by 6
  6. 2026Do Diffusion Models Dream of Electric Planes? Discrete and Continuous Simulation-Based Inference for Aircraft Designcited by 2
  7. 2024Predicting Long-Term Allograft Survival in Liver Transplant Recipientscited by 1
  8. 2025Causal Posterior Estimationcited by 1
  9. 2025A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarioscited by 1
  10. 2026Annealed Co-Generation: Disentangling Variables via Progressive Pairwise Modelingcited by 0
  11. 2026Flexible Flows for Biological Sequence Designcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
  2. 2023A Comprehensive Survey on Generative Diffusion Models for Structured Data
  3. 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Models
  4. 2025Graph Representation Learning with Diffusion Generative Models
  5. 2022Understanding Diffusion Models: A Unified Perspective
  6. 2022Diffusion Models: A Comprehensive Survey of Methods and Applications
  7. 2023Diffusion Models for Generative Artificial Intelligence: An Introduction for Applied Mathematicians
  8. 2024Diffusion Model for Data-Driven Black-Box Optimization