IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v16y2025i1d10.1038_s41467-025-57101-4.html
   My bibliography  Save this article

Online test-time adaptation for better generalization of interatomic potentials to out-of-distribution data

Author

Listed:
  • Taoyong Cui

    (Shanghai Artificial Intelligence Laboratory
    The Chinese University of Hong Kong)

  • Chenyu Tang

    (Shanghai Artificial Intelligence Laboratory)

  • Dongzhan Zhou

    (Shanghai Artificial Intelligence Laboratory)

  • Yuqiang Li

    (Shanghai Artificial Intelligence Laboratory)

  • Xingao Gong

    (Fudan University
    Shanghai Qi Zhi Institute)

  • Wanli Ouyang

    (Shanghai Artificial Intelligence Laboratory)

  • Mao Su

    (Shanghai Artificial Intelligence Laboratory)

  • Shufei Zhang

    (Shanghai Artificial Intelligence Laboratory)

Abstract

Machine learning interatomic potentials (MLIPs) enable more efficient molecular dynamics (MD) simulations with ab initio accuracy, which have been used in various domains of physical science. However, distribution shift between training and test data causes deterioration of the test performance of MLIPs, and even leads to collapse of MD simulations. In this work, we propose an online Test-time Adaptation Interatomic Potential (TAIP) framework to improve the generalization on test data. Specifically, we design a dual-level self-supervised learning approach that leverages global structure and atomic local environment information to align the model with the test data. Extensive experiments demonstrate TAIP’s capability to bridge the domain gap between training and test dataset without additional data. TAIP enhances the test performance on various benchmarks, from small molecule datasets to complex periodic molecular systems with various types of elements. TAIP also enables stable MD simulations where the corresponding baseline models collapse.

Suggested Citation

  • Taoyong Cui & Chenyu Tang & Dongzhan Zhou & Yuqiang Li & Xingao Gong & Wanli Ouyang & Mao Su & Shufei Zhang, 2025. "Online test-time adaptation for better generalization of interatomic potentials to out-of-distribution data," Nature Communications, Nature, vol. 16(1), pages 1-11, December.
  • Handle: RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-57101-4
    DOI: 10.1038/s41467-025-57101-4
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-025-57101-4
    File Function: Abstract
    Download Restriction: no

    File URL: https://libkey.io/10.1038/s41467-025-57101-4?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Haiyang Niu & Luigi Bonati & Pablo M. Piaggi & Michele Parrinello, 2020. "Ab initio phase diagram and nucleation of gallium," Nature Communications, Nature, vol. 11(1), pages 1-9, December.
    2. Simon Batzner & Albert Musaelian & Lixin Sun & Mario Geiger & Jonathan P. Mailoa & Mordechai Kornbluth & Nicola Molinari & Tess E. Smidt & Boris Kozinsky, 2022. "E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials," Nature Communications, Nature, vol. 13(1), pages 1-11, December.
    3. Di Zhang & Peiyun Yi & Xinmin Lai & Linfa Peng & Hao Li, 2024. "Active machine learning model for the dynamic simulation and growth mechanisms of carbon on metal surface," Nature Communications, Nature, vol. 15(1), pages 1-10, December.
    4. Keith T. Butler & Daniel W. Davies & Hugh Cartwright & Olexandr Isayev & Aron Walsh, 2018. "Machine learning for molecular and materials science," Nature, Nature, vol. 559(7715), pages 547-555, July.
    5. Yusong Wang & Tong Wang & Shaoning Li & Xinheng He & Mingyu Li & Zun Wang & Nanning Zheng & Bin Shao & Tie-Yan Liu, 2024. "Enhancing geometric representations for molecules with equivariant vector-scalar interactive message passing," Nature Communications, Nature, vol. 15(1), pages 1-13, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Mingfeng Liu & Jiantao Wang & Junwei Hu & Peitao Liu & Haiyang Niu & Xuexi Yan & Jiangxu Li & Haile Yan & Bo Yang & Yan Sun & Chunlin Chen & Georg Kresse & Liang Zuo & Xing-Qiu Chen, 2024. "Layer-by-layer phase transformation in Ti3O5 revealed by machine-learning molecular dynamics simulations," Nature Communications, Nature, vol. 15(1), pages 1-10, December.
    2. J. Thorben Frank & Oliver T. Unke & Klaus-Robert Müller & Stefan Chmiela, 2024. "A Euclidean transformer for fast and stable machine learned force fields," Nature Communications, Nature, vol. 15(1), pages 1-16, December.
    3. Chao Liang & Yilimiranmu Rouzhahong & Caiyuan Ye & Chong Li & Biao Wang & Huashan Li, 2023. "Material symmetry recognition and property prediction accomplished by crystal capsule representation," Nature Communications, Nature, vol. 14(1), pages 1-11, December.
    4. Han Li & Ruotian Zhang & Yaosen Min & Dacheng Ma & Dan Zhao & Jianyang Zeng, 2023. "A knowledge-guided pre-training framework for improving molecular representation learning," Nature Communications, Nature, vol. 14(1), pages 1-13, December.
    5. Li, Yi & Liu, Kailong & Foley, Aoife M. & Zülke, Alana & Berecibar, Maitane & Nanini-Maury, Elise & Van Mierlo, Joeri & Hoster, Harry E., 2019. "Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 113(C), pages 1-1.
    6. Sarmad Dashti Latif & Ali Najah Ahmed, 2023. "A review of deep learning and machine learning techniques for hydrological inflow forecasting," Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, Springer, vol. 25(11), pages 12189-12216, November.
    7. Keke Song & Rui Zhao & Jiahui Liu & Yanzhou Wang & Eric Lindgren & Yong Wang & Shunda Chen & Ke Xu & Ting Liang & Penghua Ying & Nan Xu & Zhiqiang Zhao & Jiuyang Shi & Junjie Wang & Shuang Lyu & Zezhu, 2024. "General-purpose machine-learned potential for 16 elemental metals and their alloys," Nature Communications, Nature, vol. 15(1), pages 1-15, December.
    8. Xinyu Chen & Shuaihua Lu & Qian Chen & Qionghua Zhou & Jinlan Wang, 2024. "From bulk effective mass to 2D carrier mobility accurate prediction via adversarial transfer learning," Nature Communications, Nature, vol. 15(1), pages 1-9, December.
    9. Niklas W. A. Gebauer & Michael Gastegger & Stefaan S. P. Hessmann & Klaus-Robert Müller & Kristof T. Schütt, 2022. "Inverse design of 3d molecular structures with conditional generative neural networks," Nature Communications, Nature, vol. 13(1), pages 1-11, December.
    10. Gang Wang & Shinya Mine & Duotian Chen & Yuan Jing & Kah Wei Ting & Taichi Yamaguchi & Motoshi Takao & Zen Maeno & Ichigaku Takigawa & Koichi Matsushita & Ken-ichi Shimizu & Takashi Toyao, 2023. "Accelerated discovery of multi-elemental reverse water-gas shift catalysts using extrapolative machine learning approach," Nature Communications, Nature, vol. 14(1), pages 1-12, December.
    11. Bo Lin & Jian Jiang & Xiao Cheng Zeng & Lei Li, 2023. "Temperature-pressure phase diagram of confined monolayer water/ice at first-principles accuracy with a machine-learning force field," Nature Communications, Nature, vol. 14(1), pages 1-11, December.
    12. Xingyuan San & Junwei Hu & Mingyi Chen & Haiyang Niu & Paul J. M. Smeets & Christos D. Malliakas & Jie Deng & Kunmo Koo & Roberto Reis & Vinayak P. Dravid & Xiaobing Hu, 2023. "Unlocking the mysterious polytypic features within vaterite CaCO3," Nature Communications, Nature, vol. 14(1), pages 1-11, December.
    13. Huziel E. Sauceda & Luis E. Gálvez-González & Stefan Chmiela & Lauro Oliver Paz-Borbón & Klaus-Robert Müller & Alexandre Tkatchenko, 2022. "BIGDML—Towards accurate quantum machine learning force fields for materials," Nature Communications, Nature, vol. 13(1), pages 1-16, December.
    14. Sukriti Manna & Troy D. Loeffler & Rohit Batra & Suvo Banik & Henry Chan & Bilvin Varughese & Kiran Sasikumar & Michael Sternberg & Tom Peterka & Mathew J. Cherukara & Stephen K. Gray & Bobby G. Sumpt, 2022. "Learning in continuous action space for developing high dimensional potential energy models," Nature Communications, Nature, vol. 13(1), pages 1-10, December.
    15. Ribeiro, Haroldo V. & Lopes, Diego D. & Pessa, Arthur A.B. & Martins, Alvaro F. & da Cunha, Bruno R. & Gonçalves, Sebastián & Lenzi, Ervin K. & Hanley, Quentin S. & Perc, Matjaž, 2023. "Deep learning criminal networks," Chaos, Solitons & Fractals, Elsevier, vol. 172(C).
    16. Luis M. Antunes & Keith T. Butler & Ricardo Grau-Crespo, 2024. "Crystal structure generation with autoregressive large language modeling," Nature Communications, Nature, vol. 15(1), pages 1-16, December.
    17. Zeyin Yan & Dacong Wei & Xin Li & Lung Wa Chung, 2024. "Accelerating reliable multiscale quantum refinement of protein–drug systems enabled by machine learning," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    18. Bin Han & Kuang Yu, 2025. "Refining potential energy surface through dynamical properties via differentiable molecular simulation," Nature Communications, Nature, vol. 16(1), pages 1-12, December.
    19. Alessio Fallani & Leonardo Medrano Sandonas & Alexandre Tkatchenko, 2024. "Inverse mapping of quantum properties to structures for chemical space of small organic molecules," Nature Communications, Nature, vol. 15(1), pages 1-14, December.
    20. Xinyu Chen & Yufeng Xie & Yaochen Sheng & Hongwei Tang & Zeming Wang & Yu Wang & Yin Wang & Fuyou Liao & Jingyi Ma & Xiaojiao Guo & Ling Tong & Hanqi Liu & Hao Liu & Tianxiang Wu & Jiaxin Cao & Sitong, 2021. "Wafer-scale functional circuits based on two dimensional semiconductors with fabrication optimized by machine learning," Nature Communications, Nature, vol. 12(1), pages 1-8, December.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-57101-4. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.