mlsanityData to 7 Oct 2026

MolGrow: A Graph Normalizing Flow for Hierarchical Molecular Generation

arXiv 2106.05856 ↗First posted 3 Feb 2021physics.chem-ph cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

We propose a hierarchical normalizing flow model for generating molecular graphs. The model produces new molecular structures from a single-node graph by recursively splitting every node into two. All operations are invertible and can be used as plug-and-play modules. The hierarchical nature of the latent codes allows for precise changes in the resulting graph: perturbations in the top layer cause global structural changes, while perturbations in the consequent layers change the resulting molecule marginally. The proposed model outperforms existing generative graph models on the distribution learning task. We also show successful experiments on global and constrained optimization of chemical properties using latent codes of the model.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 3 Feb 2021.

Builds on

31 of 45 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Graph Attention Networkscited by 8,854
  3. 2015Continuous control with deep reinforcement learningcited by 3,279
  4. 2016Density estimation using Real NVPcited by 2,029
  5. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  6. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  7. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  8. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  9. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  10. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  11. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  12. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
19 more
  1. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  2. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  3. 2017Grammar Variational Autoencodercited by 283
  4. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 270
  5. 2019Stabilizing Transformers for Reinforcement Learningcited by 262
  6. 2015Order Matters: Sequence to sequence for setscited by 236
  7. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 204
  8. 2018Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discoverycited by 191
  9. 2020MoFlow: An Invertible Flow Model for Generating Molecular Graphscited by 183
  10. 2017Learning to Plan Chemical Synthesescited by 175
  11. 2019GraphNVP: An Invertible Flow Model for Generating Molecular Graphscited by 115
  12. 2018Syntax-Directed Variational Autoencoder for Structured Datacited by 103
  13. 2019Attention Guided Graph Convolutional Networks for Relation Extractioncited by 82
  14. 2019MolecularRNN: Generating realistic molecular graphs with optimized propertiescited by 80
  15. 2019Discrete Flows: Invertible Generative Models of Discrete Datacited by 68
  16. 2017SMILES Enumeration as Data Augmentation for Neural Network Modeling of Moleculescited by 58
  17. 2019Emerging Convolutions for Generative Normalizing Flowscited by 31
  18. 2019Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representationcited by 22
  19. 2020Deterministic Decoding for Discrete Data in Variational Autoencoderscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 7; 2024: 5; 2025: 5; 2026: 1.

22 papers.

Sort:

By area:

  1. 2023Efficient and Scalable Graph Generation through Iterative Local Expansioncited by 35
  2. 2023nach0: Multimodal Natural and Chemical Languages Foundation Modelcited by 26
  3. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3Dcited by 24
  4. 2024Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Modelscited by 21
  5. 2022Target-aware Molecular Graph Generationcited by 18
  6. 2022Gradual Domain Adaptation via Normalizing Flowscited by 11
  7. 2024GP-MoLFormer: A Foundation Model For Molecular Generationcited by 11
  8. 2022Improving Small Molecule Generation using Mutual Information Machinecited by 10
  9. 2023Discrete Graph Auto-Encodercited by 10
  10. 2023MolHF: A Hierarchical Normalizing Flow for Molecular Graph Generationcited by 6
  11. 2023HiGen: Hierarchical Graph Generative Networkscited by 5
  12. 2023RGCVAE: Relational Graph Conditioned Variational Autoencoder for Molecule Designcited by 3
10 more
  1. 2024ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encodingcited by 3
  2. 2025Backdoor Attacks on Discrete Graph Diffusion Modelscited by 3
  3. 2024Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Modelcited by 2
  4. 2021An In-depth Summary of Recent Artificial Intelligence Applications in Drug Designcited by 1
  5. 2024Open-Source Molecular Processing Pipeline for Generating Moleculescited by 0
  6. 2025Feature-Aware (Hyper)graph Generation via Next-Scale Predictioncited by 0
  7. 2025MODA: A Unified 3D Diffusion Framework for Multi-Task Target-Aware Molecular Generationcited by 0
  8. 2025NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generationcited by 0
  9. 2025NovoMolGen: Rethinking Molecular Language Model Pretrainingcited by 0
  10. 2026Hierarchy-Guided Topology Latent Flow for Molecular Graph Generationcited by 0