Optimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917066735353856 |
|---|---|
| author | Kim, Jaesun You, Jinmu Park, Yutack Lim, Yunsung Kang, Yujin Kim, Jisu Jeon, Haekwan Ju, Suyeon Hong, Deokgi Lee, Seung Yul Choi, Saerom Kim, Yongdeok Lee, Jae W. Han, Seungwu |
| author_facet | Kim, Jaesun You, Jinmu Park, Yutack Lim, Yunsung Kang, Yujin Kim, Jisu Jeon, Haekwan Ju, Suyeon Hong, Deokgi Lee, Seung Yul Choi, Saerom Kim, Yongdeok Lee, Jae W. Han, Seungwu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_11241 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials Kim, Jaesun You, Jinmu Park, Yutack Lim, Yunsung Kang, Yujin Kim, Jisu Jeon, Haekwan Ju, Suyeon Hong, Deokgi Lee, Seung Yul Choi, Saerom Kim, Yongdeok Lee, Jae W. Han, Seungwu Materials Science 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. |
| title | Optimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials |
| topic | Materials Science |
| url | https://arxiv.org/abs/2510.11241 |