mlsanityData to 14 Oct 2026

VQ-SAD: Vector Quantized Structure Aware Diffusion For Molecule Generation

arXiv 2605.00354 ↗First posted 1 May 2026cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Many diffusion based molecule generation methods ignore the symbolic information of molecules and represent the atom and bond type as one hot representation. Methods based on Morgan fingerprints produce hash collisions and are hard to embed into a continuous space without information loss and random fingerprints correspond to no valid molecule. To circumvent this issue we use another paradigm and consider atom and bond codes as latent variables of VQ-VAE. We introduce VQ-SAD which first trains a VQ-VAE and uses the frozen pretrained VQ-VAE model and considers the codebooks for both atom and bond types as tokenizers for the downstream diffusion process. VQ-SAD is a neuro-symbolic model that utilizes both symbolic and neural structural information for a diffusion based model with learnable forward process. The large discrete code space provides a more balanced atom and bond types which enhances the denoising process. VQ-VAE slightly outperforms SOTA models for diffusion based molecule generation on QM9 and ZINC250k datasets.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 30 references that are in the map. First posted on arXiv 1 May 2026.

Builds on

25 of 30 references.

References · 25

  1. 2022Classifier-Free Diffusion Guidancecited by 5,847
  2. 2017Neural Discrete Representation Learningcited by 4,712
  3. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  4. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  5. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  6. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 774
  7. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  8. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
  9. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
  10. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
  11. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 333
  12. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 283
13 more
  1. 2018Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discoverycited by 194
  2. 2023Graph Inductive Biases in Transformers without Message Passingcited by 153
  3. 2023Autoregressive Diffusion Model for Graph Generationcited by 83
  4. 2023Graph Generation with Diffusion Mixturecited by 55
  5. 2024Graph Diffusion Transformers for Multi-Conditional Molecular Generationcited by 45
  6. 2024Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modellingcited by 45
  7. 2023VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPscited by 35
  8. 2024Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generationcited by 25
  9. 2023Neural Diffusion Modelscited by 21
  10. 2025Learning Flexible Forward Trajectories for Masked Molecular Diffusioncited by 7
  11. 2025Hierarchical Vector Quantized Graph Autoencoder with Annealing-Based Code Selectioncited by 5
  12. 2025Improved Molecular Generation through Attribute-Driven Integrative Embeddings and GAN Selectivitycited by 1
  13. 2025Hash Collisions in Molecular Fingerprints: Effects on Property Prediction and Bayesian Optimizationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026VQ-Atom: Semantic Discretization of Local Atomic Environments for Molecular Representation Learningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Chemistry-Inspired Diffusion with Non-Differentiable Guidance
  2. 2025All-atom Diffusion Transformers: Unified generative modelling of molecules and materials
  3. 2025Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
  4. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation
  5. 2025DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra
  6. 20243M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation
  7. 2024Training-Free Guidance for Discrete Diffusion Models for Molecular Generation
  8. 2025DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform