mlsanityData to 14 Oct 2026

Grammar Variational Autoencoder

arXiv 1703.01925 ↗First posted 6 Mar 2017stat.MLcited by 285

Not on the map. Why?

Abstract (arXiv)

Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular structures still poses significant challenges. Crucially, state-of-the-art methods often produce outputs that are not valid. We make the key observation that frequently, discrete data can be represented as a parse tree from a context-free grammar. We propose a variational autoencoder which encodes and decodes directly to and from these parse trees, ensuring the generated outputs are always valid. Surprisingly, we show that not only does our model more often generate valid outputs, it also learns a more coherent latent space in which nearby points decode to similar discrete outputs. We demonstrate the effectiveness of our learned models by showing their improved performance in Bayesian optimization for symbolic regression and molecular synthesis.

Key facts. Cited by 285 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 60; 2022: 62; 2023: 48; 2024: 51; 2025: 43; 2026: 21.

285 papers.

Sort:

By area:

  1. 2021GFlowNet Foundationscited by 290
  2. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 264
  3. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 200
  4. 2021Neural Symbolic Regression that Scalescited by 192
  5. 2022Graph neural networks for materials science and chemistrycited by 182
  6. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 180
  7. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 177
  8. 2022A 3D Generative Model for Structure-Based Drug Designcited by 149
  9. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 141
  10. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
  11. 2022A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Languagecited by 131
  12. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
38 more
  1. 2021Symbolic Regression via Neural-Guided Genetic Programming Population Seedingcited by 101
  2. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  3. 2023Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspectivecited by 92
  4. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  5. 2022Local Latent Space Bayesian Optimization over Structured Inputscited by 79
  6. 2022Equivariant Energy-Guided SDE for Inverse Molecular Designcited by 73
  7. 2022Rediscovering orbital mechanics with machine learningcited by 71
  8. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  9. 2022Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree searchcited by 66
  10. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  11. 2024Advances in 3D Generation: A Surveycited by 63
  12. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  13. 2023CktGNN: Circuit Graph Neural Network for Electronic Design Automationcited by 58
  14. 2021High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learningcited by 54
  15. 2021Molecule Generation by Principal Subgraph Mining and Assemblingcited by 54
  16. 2021Improving black-box optimization in VAE latent space using decoder uncertaintycited by 51
  17. 2022Graph-based Molecular Representation Learningcited by 51
  18. 2022Regression Transformer: Concurrent sequence regression and generation for molecular language modelingcited by 50
  19. 2021GIBBON: General-purpose Information-Based Bayesian OptimisatioNcited by 47
  20. 2023Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generationcited by 46
  21. 2023De Novo Molecular Generation via Connection-aware Motif Miningcited by 46
  22. 2021Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spacescited by 45
  23. 2022Retrieval-based Controllable Molecule Generationcited by 44
  24. 2023IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformationcited by 41
  25. 2022LIMO: Latent Inceptionism for Targeted Molecule Generationcited by 40
  26. 2022Recent Advances for Quantum Neural Networks in Generative Learningcited by 39
  27. 20223DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Designcited by 33
  28. 2021JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Designcited by 32
  29. 2022gLaSDI: Parametric Physics-informed Greedy Latent Space Dynamics Identificationcited by 30
  30. 2023Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaborationcited by 30
  31. 2024A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generationcited by 29
  32. 2021Artificial Intelligence in Drug Discovery: Applications and Techniquescited by 28
  33. 2024Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimizationcited by 25
  34. 2021Directional Message Passing on Molecular Graphs via Synthetic Coordinatescited by 24
  35. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3Dcited by 24
  36. 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequencescited by 23
  37. 2024UniMoT: Unified Molecule-Text Language Model with Discrete Token Representationcited by 23
  38. 2024Molecule Generation with Fragment Retrieval Augmentationcited by 23

50 most cited of 285 All 285 (JSON)