Optimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials
Department of Materials Science and Engineering, Seoul National University(首尔大学材料科学与工程系);Research Institute of Advanced Materials, Seoul National University(首尔大学先进材料研究所);Department of Computer Science and Engineering, Seoul National University(首尔大学计算机工程系);AI Center, Samsung Electronics(三星电子人工智能中心);Center for AI and Natural Sciences, Korea Institute of Advanced Study(韩国高级研究院人工智能与自然科学中心)
Jaesun Kim, Jinmu You, Yutack Park, Yunsung Lim, Yujin Kang, Jisu Kim, Haekwan Jeon, Suyeon Ju, Deokgi Hong, Seung Yul Lee, Saerom Choi, Yongdeok Kim, Jae W. Lee, Seungwu Han
备注:
23 pages, 5 figures, 2 tables, Supplementary information included as ancillary file (+32 pages)
Accurate yet transferable machine-learning interatomic potentials (MLIPs) are essential for accelerating materials and chemical discovery. However, most universal MLIPs overfit to narrow datasets or computational protocols, limiting their reliability across chemical and functional domains. We introduce a transferable multi-domain training strategy that jointly optimizes universal and task-specific parameters through selective regularization, coupled with a domain-bridging set (DBS) that aligns potential-energy surfaces across datasets. Systematic ablation experiments show that small DBS fractions (0.1%) and targeted regularization synergistically enhance out-of-distribution generalization while preserving in-domain fidelity. Trained on fifteen open databases spanning molecules, crystals, and surfaces, our model, SevenNet-Omni, achieves state-of-the-art cross-domain accuracy, including adsorption-energy errors below 0.06 eV on metallic surfaces and 0.1 eV on metal-organic frameworks. Despite containing only 0.5% r$^2$SCAN data, SevenNet-Omni reproduces high-fidelity r$^2$SCAN energetics, demonstrating effective cross-functional transfer from large PBE datasets. This framework offers a scalable route toward universal, transferable MLIPs that bridge quantum-mechanical fidelities and chemical domains.
Benchmarking Universal Machine Learning Interatomic Potentials for Elastic Property Prediction
School of Intelligence Science and Technology, Nanjing University of Science and Technology(南京理工大学智能科学与技术学院);School of Physics, Hefei University of Technology(合肥工业大学物理学院)
Evaluating Mechanical Property Prediction across Material Classes using Molecular Dynamics Simulations with Universal Machine-Learned Interatomic Potentials
School of Physics, Chemistry and Earth Sciences, The University of Adelaide(阿德莱德大学物理、化学与地球科学学院)
Expanding Universal Machine Learning Interatomic Potentials to 97 Elements Towards Nuclear Applications
Center for Quantum Information and Quantum Biology, The University of Osaka(大阪大学量子信息与量子生物学中心);Graduate School of Science, The University of Osaka(大阪大学理学研究科)
Towards Accurate and Scalable High-throughput MOF Adsorption Screening: Merging Classical Force Fields and Universal Machine Learned Interatomic Potentials
Global Universal Scaling and Ultra-Small Parameterization in Machine Learning Interatomic Potentials with Super-Linearity
Southern University of Science and Technology(南方科技大学);Shanghai University(上海大学);Materials Genome Institute(材料基因组研究院);Institute of Innovative Materials(创新材料研究院)
Universal Interatomic Potentials as Configuration-Space Generators for One-Shot and Iterative Fine-Tuning of Ab Initio-Accurate Material-Specific Models
MP-ALOE: An r2SCAN dataset for universal machine learning interatomic potentials
Lawrence Berkeley National Laboratory(伯克利国家实验室);University of California, Berkeley(加州大学伯克利分校);Department of Materials Science and Engineering(材料科学与工程系)
PySlice: Routine Vibrational Electron Energy Loss Spectroscopy Prediction with Universal Interatomic Potentials
Vanderbilt University(范德堡大学);Oak Ridge National Laboratory(橡树岭国家实验室);University of Virginia(弗吉尼亚大学);University of Washington(华盛顿大学);Uppsala University(乌普萨拉大学)
FastTrack: a fast method to evaluate mass transport in solid leveraging universal machine learning interatomic potential
Beijing National Laboratory for Condensed Matter Physics, Institute of Physics, Chinese Academy of Sciences(中国科学院物理研究所凝聚态物理国家实验室);Songshan Lake Materials Laboratory(松山湖材料实验室)
本文提出 FastTrack 框架,结合通用 MLFF、三维 PES 采样与插值快速计算晶体原子迁移势垒,无需预定义 NEB 图像,并在十二类材料上验证其精度与百倍加速。
Ready-to-Use Polymerization Simulations Combining Universal Machine Learning Interatomic Potential with Time-Dependent Bond Boosting for Polymer and Interface Design
A general-purpose atomic cluster expansion interatomic potential for niobium
Center for Advanced Systems Understanding (CASUS)(先进系统理解中心);Helmholtz-Zentrum Dresden-Rossendorf (HZDR)(德累斯顿-罗斯多夫亥姆霍兹中心);ICAMS, Ruhr-Universität Bochum(波鸿鲁尔大学综合分析与建模中心)
Comparing the latent features of universal machine-learning interatomic potentials
Laboratory of Computational Science and Modeling(计算科学与建模实验室);Department of Energy Conversion and Storage(能源转换与存储部门);Technical University of Denmark(丹麦技术大学)