Transfer learning on large datasets for the accurate prediction of material properties

Pretraining on large, lower-fidelity datasets enables extremely effective training of graph neural networks on smaller, high-fidelity datasets.

Materials Science Computer Science Engineering Physics

View graph Source

Paper

References (62)

01Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular SimulationsXiang Fu, Zhenghao Wu, Wujie Wang et al.2022 · Trans. Mach. Learn. Res. · 232 citations In Library

02Large-scale machine-learning-assisted exploration of the whole materials spaceJonathan Schmidt, Noah Hoffmann, Hai-Chen Wang et al.2022 · arXiv.org · 30 citations In Library

03Machine learning guided high-throughput search of non-oxide garnetsJonathan Schmidt, Haichen Wang, Georg Schmidt et al.2022 · npj Computational Materials · 9 citations In Library

04Transfer learning using attentions across atomic systems with graph neural networks (TAAG).Adeesh Kolluru, Nima Shoghi, M. Shuaibi et al.2022 · Journal of Chemical Physics · 33 citations

05A dataset of 175k stable and metastable materials calculated with the PBEsol and SCAN functionalsJonathan Schmidt, Hai-Chen Wang, Tiago F. T. Cerqueira et al.2022 · Scientific Data · 69 citations

06Roadmap on Machine learning in electronic structureH. Kulik, T. Hammerschmidt, Jonathan Schmidt et al.2022 · Electronic Structure · 163 citations

07A universal graph deep learning interatomic potential for the periodic tableChi Chen, S. Ong2022 · Nature Computational Science · 1.0k citations In Library

08Transfer (machine) learning approaches coupled with target data augmentation to predict the mechanical properties of concreteEmily Ford, Kailasnath Maneparambil, Aditya Kumar et al.2022 · Machine Learning with Applications · 25 citations

09Crystal graph attention networks for the prediction of stable materialsJonathan Schmidt, Love A. Pettersson, C. Verdozzi et al.2021 · Science Advances · 140 citations

10Cross-property deep transfer learning framework for enhanced predictive analytics on small materials dataVishu Gupta, K. Choudhary, F. Tavazza et al.2021 · Nature Communications · 149 citations

11Machine-learning correction to density-functional crystal structure optimizationR. Hussein, Jonathan Schmidt, Tomás Barros et al.2021 · MRS bulletin · 12 citations In Library

12Performance comparison of r2SCAN and SCAN metaGGA density functionals for solid materials via an automated, high-throughput computational workflowR. Kingsbury, Ayush S. Gupta, Christopher J. Bartel et al.2021 · PHYSICAL REVIEW MATERIALS · 79 citations

Scroll for more · 38 remaining

Similar papers

Lightweight and high-precision materials property prediction using pre-trained Graph Neural Networks and its application to a small datasetKento Nishio, Kiyou Shibata, Teruyasu Mizoguchi2024 · Applied Physics Express · 5 citations In Library

Transfer learning for materials informatics using crystal graph convolutional neural networkJoohwi Lee, R. Asahi2020 · Computational materials science · 76 citations In Library

Improving neural network predictions of material properties with limited data using transfer learningSchuyler Krawczuk, D. Venturi2020 · Journal of Machine Learning for Modeling and Computing · 4 citations In Library

Supervised Pretraining for Material Property PredictionChowdhury Mohammad Abid Rahman, Aldo H Romero, P. Gyawali2025 · Communications Materials · 4 citations In Library

Pretraining Strategies for Structure Agnostic Material Property PredictionHongshuo Huang, Rishikesh Magar, A. Farimani2024 · Journal of Chemical Information and Modeling · 19 citations In Library

Pre-training Graph Neural Networks with Structural Fingerprints for Materials DiscoveryShuyi Jia, Shitij Govil, Manav Ramprasad et al.2025 · arXiv.org · 2 citations In Library

Strategies for Pre-training Graph Neural NetworksWeihua Hu, Bowen Liu, Joseph Gomes et al.2019 · International Conference on Learning Representations · 1.8k citations In Library

Cross-property deep transfer learning framework for enhanced predictive analytics on small materials dataVishu Gupta, K. Choudhary, F. Tavazza et al.2021 · Nature Communications · 148 citations In Library

Transfer learning with graph neural networks for improved molecular property prediction in the multi-fidelity settingDavid Buterez, J. Janet, Steven J Kiddle et al.2024 · Nature Communications · 116 citations In Library

Scalable deeper graph neural networks for high-performance materials property predictionSadman Sadeed Omee, Steph-Yves M. Louis, Nihang Fu et al.2021 · Patterns · 113 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal