Fast and Scalable Neural Network Quantum States Method for Molecular Potential Energy Surfaces
文献类型：期刊论文
| 作者 | Wu, Yangjun1; Cao, Wanlu2; Zhao, Jiacheng2; Shang, Honghui1 |
| 刊名 | IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
 |
| 出版日期 | 2025-07-01 |
| 卷号 | 36期号:7页码:1431-1443 |
| 关键词 | Artificial neural networks Computational efficiency Training Wave functions Quantum state Computational modeling Optimization Electrons Convergence Potential energy Quantum computational chemistry many-body Schr & ouml neural network quantum state transformer based architecture autoregressive sampling potential energy surfaces dinger equation |
| ISSN号 | 1045-9219 |
| DOI | 10.1109/TPDS.2025.3568360 |
| 英文摘要 | The Neural Network Quantum States (NNQS) method is highly promising for accurately solving the Schr & ouml;dinger equation, yet it encounters challenges such as computational demands and slow rates of convergence. To address the high computational requirements, we introduce optimizations including a cross-sample KV cache sharing technique to enhance sampling efficiency, Quantum Bitwise and BloomHash methods for more efficient local energy computation, and mixed-precision training strategies to boost computational efficiency. To overcome the issue of slow convergence, we propose a parallel training algorithm for NNQS under second quantization to accelerate the training of base models for molecular potential surfaces. Our approach achieves up to 27-fold acceleration specifically in local energy calculations in systems with 154 spin orbitals and demonstrates strong and weak scaling efficiencies of 98% and 97%, respectively, on the H$_{2}$2O$_{2}$2 potential surface training set. The parallelized implementation of transformer-based NNQS is highly portable on various high-performance computing architectures, offering new perspectives on quantum chemistry simulations. |
| 资助项目 | National Natural Science Foundation of China[T2222026] ; National Natural Science Foundation of China[U23B2020] ; National Natural Science Foundation of China[62302479] ; National Natural Science Foundation of China[62232015] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001498254200002 |
| 出版者 | IEEE COMPUTER SOC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42311]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Shang, Honghui |
| 作者单位 | 1.Univ Sci & Technol China, State Key Lab Precis & Intelligent Chem, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wu, Yangjun,Cao, Wanlu,Zhao, Jiacheng,et al. Fast and Scalable Neural Network Quantum States Method for Molecular Potential Energy Surfaces[J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS,2025,36(7):1431-1443. |
| APA | Wu, Yangjun,Cao, Wanlu,Zhao, Jiacheng,&Shang, Honghui.(2025).Fast and Scalable Neural Network Quantum States Method for Molecular Potential Energy Surfaces.IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS,36(7),1431-1443. |
| MLA | Wu, Yangjun,et al."Fast and Scalable Neural Network Quantum States Method for Molecular Potential Energy Surfaces".IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 36.7(2025):1431-1443. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。