Bridging the Gap between Transformer-Based Neural Networks and Tensor Networks for Quantum Chemistry

doi:10.1021/acs.jctc.4c01703

	Bridging the Gap between Transformer-Based Neural Networks and Tensor Networks for Quantum Chemistry
	Kan, Bowen 1,2; Tian, Yingqi 1; Wu, Yangjun 3; Zhang, Yunquan 1; Shang, Honghui 3
	2025-03-02
发表期刊	JOURNAL OF CHEMICAL THEORY AND COMPUTATION
ISSN	1549-9618
页码	14
摘要	The neural network quantum state (NNQS) method has demonstrated promising results in ab initio quantum chemistry, achieving remarkable accuracy in molecular systems. However, efficient calculation of systems with large active spaces remains challenging. This study introduces a novel approach that bridges tensor network states with the transformer-based NNQS-Transformer (QiankunNet) to enhance accuracy and convergence for systems with relatively large active spaces. By transforming tensor network states into active space configuration interaction type wave functions, QiankunNet achieves accuracy surpassing both the pretraining density matrix renormalization group (DMRG) results and traditional coupled cluster methods, particularly in strongly correlated regimes. We investigate two configuration transformation methods: the sweep-based direct conversion (Conv.) method and the entanglement-driven genetic algorithm (EDGA) method, with Conv. showing superior efficiency. The effectiveness of this approach is validated on H2O with a large active space (10e, 24o) in the cc-pVDZ basis set, demonstrating an efficient routine between DMRG and QiankunNet and also offering a promising direction for advancing quantum state representation in complex molecular systems.
DOI	10.1021/acs.jctc.4c01703
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[22403100] ; National Natural Science Foundation of China ; Supercomputing Center of the USTC
WOS研究方向	Chemistry ; Physics
WOS类目	Chemistry, Physical ; Physics, Atomic, Molecular & Chemical
WOS记录号	WOS:001435305400001
出版者	AMER CHEMICAL SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40699
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.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Univ Sci & Technol China, Key Lab Precis & Intelligent Chem, Hefei 230026, Peoples R China
推荐引用方式 GB/T 7714	Kan, Bowen,Tian, Yingqi,Wu, Yangjun,et al. Bridging the Gap between Transformer-Based Neural Networks and Tensor Networks for Quantum Chemistry[J]. JOURNAL OF CHEMICAL THEORY AND COMPUTATION,2025:14.
APA	Kan, Bowen,Tian, Yingqi,Wu, Yangjun,Zhang, Yunquan,&Shang, Honghui.(2025).Bridging the Gap between Transformer-Based Neural Networks and Tensor Networks for Quantum Chemistry.JOURNAL OF CHEMICAL THEORY AND COMPUTATION,14.
MLA	Kan, Bowen,et al."Bridging the Gap between Transformer-Based Neural Networks and Tensor Networks for Quantum Chemistry".JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2025):14.