mlsanityData to 14 Oct 2026

Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints

arXiv 2203.14352 ↗First posted 27 Mar 2022cond-mat.mtrl-sci cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Discovering new materials is a challenging task in materials science crucial to the progress of human society. Conventional approaches based on experiments and simulations are labor-intensive or costly with success heavily depending on experts' heuristic knowledge. Here, we propose a deep learning based Physics Guided Crystal Generative Model (PGCGM) for efficient crystal material design with high structural diversity and symmetry. Our model increases the generation validity by more than 700% compared to FTCP, one of the latest structure generators and by more than 45% compared to our previous CubicGAN model. Density Functional Theory (DFT) calculations are used to validate the generated structures with 1,869 materials out of 2,000 are successfully optimized and deposited into the Carolina Materials Database urlwww.carolinamatdb.org, of which 39.6% have negative formation energy and 5.3% have energy-above-hull less than 0.25 eV/atom, indicating their thermodynamic stability and potential synthesizability.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 12 of its 47 references that are in the map. First posted on arXiv 27 Mar 2022.

Builds on

12 of 47 references.

References · 12

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2017Improved Training of Wasserstein GANscited by 2,235
  5. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 270
  6. 2020An invertible crystallographic representation for general inverse design of inorganic crystals with targeted propertiescited by 53
  7. 2019Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materialscited by 46
  8. 2021Normalizing flows for atomic solidscited by 39
  9. 2019Data-Driven Approach to Encoding and Decoding 3-D Crystal Structurescited by 34
  10. 2018CrystalGAN: Learning to Discover Crystallographic Structures with Generative Adversarial Networkscited by 31
  11. 2019Generative Models for Automatic Chemical Designcited by 23
  12. 2019Study of Deep Generative Models for Inorganic Chemical Compositionscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 8; 2025: 12; 2026: 5.

30 papers.

Sort:

By area:

  1. 2024Space Group Constrained Crystal Generationcited by 73
  2. 2023Crystal-GFN: sampling crystals with desirable properties and constraintscited by 31
  3. 2025LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Modelscited by 23
  4. 2024Structure-based out-of-distribution (OOD) materials property prediction: a benchmark studycited by 17
  5. 2024Ab Initio Structure Solutions from Nanocrystalline Powder Diffraction Datacited by 12
  6. 2025Materials Generation in the Era of Artificial Intelligence: A Comprehensive Surveycited by 10
  7. 2023Vector Field Oriented Diffusion Model for Crystal Material Generationcited by 9
  8. 2026Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modelingcited by 7
  9. 2025Graph Diffusion that can Insert and Deletecited by 6
  10. 2025Continuous SUN (Stable, Unique, and Novel) Metric for Generative Modeling of Inorganic Crystalscited by 6
  11. 2024Generative Design of Crystal Structures by Point Cloud Representations and Diffusion Modelcited by 4
  12. 2025InvDesFlow-AL: active learning-based workflow for inverse design of functional materialscited by 4
18 more
  1. 2025Generative Models for Crystalline Materialscited by 4
  2. 2024Self-supervised learning for crystal property prediction via denoisingcited by 3
  3. 2024Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networkscited by 3
  4. 2025Towards an automated workflow in materials science for combining multi-modal simulative and experimental information using data mining and large language modelscited by 3
  5. 2023Evaluating the diversity and utility of materials proposed by generative modelscited by 2
  6. 2023Data-Driven Score-Based Models for Generating Stable Structures with Adaptive Crystal Cellscited by 2
  7. 2025L^2M^3OF: A Large Language Multimodal Model for Metal-Organic Frameworkscited by 2
  8. 2023PerCNet: Periodic Complete Representation for Crystal Graphscited by 1
  9. 2024ADA-GNN: Atom-Distance-Angle Graph Neural Network for Crystal Material Property Predictioncited by 1
  10. 2025Autonomous Inorganic Materials Discovery via Multi-Agent Physics-Aware Scientific Reasoningcited by 1
  11. 2025Benchmarking GNNs for OOD Materials Property Prediction with Uncertainty Quantificationcited by 1
  12. 2026Chemical filters for ultra-high-throughput materials screening and generationcited by 1
  13. 2024Unleashing the power of novel conditional generative approaches for new materials discoverycited by 0
  14. 2025Design Topological Materials by Reinforcement Fine-Tuned Generative Modelcited by 0
  15. 2025Unified machine-learning framework for property prediction and time-evolution simulation of strained alloy microstructurecited by 0
  16. 2026Inverse Design of Inorganic Compounds with Generative AIcited by 0
  17. 2026Neural surrogates for crystal growth dynamics with variable supersaturation: explicit vs. implicit conditioningcited by 0
  18. 2026Text-guided flow matching enables sample-efficient crystal structure generationcited by 0