mlsanityData to 7 Oct 2026

Molecule Generation by Principal Subgraph Mining and Assembling

arXiv 2106.15098 ↗First posted 29 Jun 2021cs.LG q-bio.QMcited by 53

Not on the map. Why?

Abstract (arXiv)

Molecule generation is central to a variety of applications. Current attention has been paid to approaching the generation task as subgraph prediction and assembling. Nevertheless, these methods usually rely on hand-crafted or external subgraph construction, and the subgraph assembling depends solely on local arrangement. In this paper, we define a novel notion, principal subgraph, that is closely related to the informative pattern within molecules. Interestingly, our proposed merge-and-update subgraph extraction method can automatically discover frequent principal subgraphs from the dataset, while previous methods are incapable of. Moreover, we develop a two-step subgraph assembling strategy, which first predicts a set of subgraphs in a sequence-wise manner and then assembles all generated subgraphs globally as the final output molecule. Built upon graph variational auto-encoder, our model is demonstrated to be effective in terms of several evaluation metrics and efficiency, compared with state-of-the-art methods on distribution learning and (constrained) property optimization tasks.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 23 of its 51 references that are in the map. First posted on arXiv 29 Jun 2021.

Builds on

23 of 51 references.

References · 23

  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  3. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  4. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  5. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  6. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  7. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  8. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  9. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  10. 2017Grammar Variational Autoencodercited by 283
  11. 2018Learning Deep Generative Models of Graphscited by 227
  12. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 204
11 more
  1. 2018Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discoverycited by 191
  2. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 177
  3. 2018Neural Architecture Optimizationcited by 164
  4. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  5. 2014word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding methodcited by 109
  6. 2018Multi-Objective De Novo Drug Design with Conditional Graph Generative Modelcited by 101
  7. 2019MolecularRNN: Generating realistic molecular graphs with optimized propertiescited by 80
  8. 2019Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Spacecited by 66
  9. 2020Guiding Deep Molecular Optimization with Genetic Explorationcited by 51
  10. 2017Molecular Generation with Recurrent Neural Networks (RNNs)cited by 36
  11. 2016The word entropy of natural languagescited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 9; 2024: 16; 2025: 14; 2026: 13.

53 papers.

Sort:

By area:

  1. 2025GenMol: A Drug Discovery Generalist with Discrete Diffusioncited by 47
  2. 2024Molecule Generation with Fragment Retrieval Augmentationcited by 22
  3. 2023Fragment-based Pretraining and Finetuning on Molecular Graphscited by 20
  4. 2023Drug Discovery with Dynamic Goal-aware Fragmentscited by 19
  5. 2023Generalist Equivariant Transformer Towards 3D Molecular Interaction Learningcited by 18
  6. 2024Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?cited by 18
  7. 2024Saturn: Sample-efficient Generative Molecular Design using Memory Manipulationcited by 14
  8. 2022Molecule Generation for Drug Design: a Graph Learning Perspectivecited by 13
  9. 2025GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuningcited by 13
  10. 2024Text-guided multi-property molecular optimization with a diffusion language modelcited by 11
  11. 2024Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneckcited by 11
  12. 2025UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Designcited by 11
38 more
  1. 20243M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generationcited by 8
  2. 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapescited by 7
  3. 2024Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Spacecited by 7
  4. 2024GraphBPE: Molecular Graphs Meet Byte-Pair Encodingcited by 7
  5. 2025Unified Guidance for Geometry-Conditioned Molecular Generationcited by 7
  6. 2023MolHF: A Hierarchical Normalizing Flow for Molecular Graph Generationcited by 6
  7. 2023The power of motifs as inductive bias for learning molecular distributionscited by 6
  8. 2025Graph Diffusion Transformers are In-Context Molecular Designerscited by 6
  9. 2025FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matchingcited by 5
  10. 2024Diffusion Twigs with Loop Guidance for Conditional Graph Generationcited by 4
  11. 2024MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insightscited by 4
  12. 2024Data-Efficient Molecular Generation with Hierarchical Textual Inversioncited by 3
  13. 2024A Review on Fragment-based De Novo 2D Molecule Generationcited by 3
  14. 2025Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generationcited by 3
  15. 2025Universally Invariant Learning in Equivariant GNNscited by 3
  16. 2025Toward Closed-loop Molecular Discovery via Language Model, Property Alignment and Strategic Searchcited by 3
  17. 20263D Molecule Generation from Rigid Motifs via SE(3) Flowscited by 3
  18. 2026Graph Tokenization for Bridging Graphs and Transformerscited by 3
  19. 2023MotifRetro: Exploring the Combinability-Consistency Trade-offs in retrosynthesis via Dynamic Motif Editingcited by 2
  20. 2024Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generationcited by 2
  21. 2025MolSnap: Snap-Fast Molecular Generation with Latent Variational Mean Flowcited by 2
  22. 2026CombiMOTS: Combinatorial Multi-Objective Tree Search for Dual-Target Molecule Generationcited by 2
  23. 2024Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learningcited by 1
  24. 2025Training Text-to-Molecule Models with Context-Aware Tokenizationcited by 1
  25. 2025Transport-Coupled Bayesian Flows for Molecular Graph Generationcited by 1
  26. 2026Active Learning for Generalizable Detonation Performance Prediction of Energetic Materialscited by 1
  27. 2026FlashMol: High-Quality Molecule Generation in as Few as Four Stepscited by 1
  28. 2026Controllable Molecular Generative Foundation Modelscited by 1
  29. 2023Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learningcited by 0
  30. 2023PepLand: a large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acidscited by 0
  31. 2024Empirical Evidence for the Fragment level Understanding on Drug Molecular Structure of LLMscited by 0
  32. 2024M3-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discoverycited by 0
  33. 2025Concept-Driven Deep Learning for Enhanced Protein-Specific Molecular Generationcited by 0
  34. 2025NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generationcited by 0
  35. 2026Multi-scale Graph Autoregressive Modeling: Molecular Property Prediction via Next Token Predictioncited by 0
  36. 2026From Tokens to Blocks: A Block-Diffusion Perspective on Molecular Generationcited by 0
  37. 2026Amortized Molecular Optimization via Group Relative Policy Optimizationcited by 0
  38. 2026h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Networkcited by 0

50 most cited of 53 All 53 (JSON)