mlsanityData to 7 Oct 2026

Predicting materials properties without crystal structure: Deep representation learning from stoichiometry

arXiv 1910.00617 ↗First posted 1 Oct 2019physics.comp-ph cond-mat.mtrl-sci cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

Machine learning has the potential to accelerate materials discovery by accurately predicting materials properties at a low computational cost. However, the model inputs remain a key stumbling block. Current methods typically use descriptors constructed from knowledge of either the full crystal structure -- therefore only applicable to materials with already characterised structures -- or structure-agnostic fixed-length representations hand-engineered from the stoichiometry. We develop a machine learning approach that takes only the stoichiometry as input and automatically learns appropriate and systematically improvable descriptors from data. Our key insight is to treat the stoichiometric formula as a dense weighted graph between elements. Compared to the state of the art for structure-agnostic methods, our approach achieves lower errors with less data.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 13; 2023: 10; 2024: 9; 2025: 12; 2026: 9.

60 papers.

Sort:

By area:

  1. 2022Graph neural networks for materials science and chemistrycited by 181
  2. 2021Geometric Deep Learning on Molecular Representationscited by 113
  3. 2022Periodic Graph Transformers for Crystal Material Property Predictioncited by 87
  4. 2023Efficient Approximations of Complete Interatomic Potentials for Crystal Property Predictioncited by 37
  5. 2023Matbench Discovery -- A framework to evaluate machine learning crystal stability predictionscited by 34
  6. 2021Scalable deeper graph neural networks for high-performance materials property predictioncited by 26
  7. 2022Deep Reinforcement Learning for Inverse Inorganic Materials Designcited by 18
  8. 2024Structure-based out-of-distribution (OOD) materials property prediction: a benchmark studycited by 17
  9. 2022Large-scale machine-learning-assisted exploration of the whole materials spacecited by 13
  10. 2023Precursor recommendation for inorganic synthesis by machine learning materials similarity from scientific literaturecited by 12
  11. 2025DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and moleculescited by 12
  12. 2024Regression with Large Language Models for Materials and Molecular Property Predictioncited by 10
38 more
  1. 2021Distributed Representations of Atoms and Materials for Machine Learningcited by 8
  2. 2022Crystal Transformer: Self-learning neural language model for Generative and Tinkering Design of Materialscited by 8
  3. 2024Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledgecited by 8
  4. 2021Materials Representation and Transfer Learning for Multi-Property Predictioncited by 7
  5. 2022Formula graph self-attention network for representation-domain independent materials discoverycited by 7
  6. 2022Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materialscited by 7
  7. 2023Materials Informatics Transformer: A Language Model for Interpretable Materials Properties Predictioncited by 7
  8. 2025Known Unknowns: Out-of-Distribution Property Prediction in Materials and Moleculescited by 7
  9. 2025A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Toolscited by 7
  10. 2025Space Group Conditional Flow Matchingcited by 7
  11. 2025Language Models Enable Data-Augmented Synthesis Planning for Inorganic Materialscited by 6
  12. 2021MaterialsAtlas.org: A Materials Informatics Web App Platform for Materials Discovery and Survey of State-of-the-Artcited by 5
  13. 2024CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learningcited by 5
  14. 2024Neural Network Emulator for Atmospheric Chemical ODEcited by 5
  15. 2026Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectoriecited by 5
  16. 2026Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfercited by 5
  17. 2023Multimodal machine learning for materials science: composition-structure bimodal learning for experimentally measured propertiescited by 4
  18. 2024Self-supervised learning for crystal property prediction via denoisingcited by 3
  19. 2025CLOUD: A Scalable and Physics-Informed Foundation Model for Crystal Representation Learningcited by 3
  20. 2022Neural Structure Fields with Application to Crystal Structure Autoencoderscited by 2
  21. 2023Leveraging Language Representation for Material Recommendation, Ranking, and Explorationcited by 2
  22. 2023Evaluating the diversity and utility of materials proposed by generative modelscited by 2
  23. 2025Predicting band gap from chemical composition: A simple learned model for a material property with atypical statisticscited by 2
  24. 2025Learning simple heuristic rules for classifying materials based on chemical compositioncited by 2
  25. 2021Active learning based generative design for the discovery of wide bandgap materialscited by 1
  26. 2021Semi-supervised teacher-student deep neural network for materials discoverycited by 1
  27. 2022Materials Transformers Language Models for Generative Materials Design: a benchmark studycited by 1
  28. 2022Artificial Intelligence in Material Engineering: A review on applications of AI in Material Engineeringcited by 1
  29. 2022Composition based oxidation state prediction of materials using deep learningcited by 1
  30. 2023Closed-loop Error Correction Learning Accelerates Experimental Discovery of Thermoelectric Materialscited by 1
  31. 2024Diverse Explanations From Data-Driven and Domain-Driven Perspectives in the Physical Sciencescited by 1
  32. 2025ReciNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Predictioncited by 1
  33. 2025Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretabilitycited by 1
  34. 2026MEIDNet: Multimodal generative AI framework for inverse materials designcited by 1
  35. 2026Agentic Design of Compositional Descriptors via Autoresearch for Materials Science Applicationscited by 1
  36. 2026TriForces: Augmenting Atomistic GNNs for Transferable Representationscited by 1
  37. 2022Element selection for functional materials discovery by integrated machine learning of elemental contributions to propertiescited by 0
  38. 2022Machine Learning guided high-throughput search of non-oxide garnetscited by 0

50 most cited of 60 All 60 (JSON)