Back to Search Start Over

DeepH-2: Enhancing deep-learning electronic structure via an equivariant local-coordinate transformer

Authors :
Wang, Yuxiang
Li, He
Tang, Zechen
Tao, Honggeng
Wang, Yanzhen
Yuan, Zilong
Chen, Zezhou
Duan, Wenhui
Xu, Yong
Publication Year :
2024

Abstract

Deep-learning electronic structure calculations show great potential for revolutionizing the landscape of computational materials research. However, current neural-network architectures are not deemed suitable for widespread general-purpose application. Here we introduce a framework of equivariant local-coordinate transformer, designed to enhance the deep-learning density functional theory Hamiltonian referred to as DeepH-2. Unlike previous models such as DeepH and DeepH-E3, DeepH-2 seamlessly integrates the simplicity of local-coordinate transformations and the mathematical elegance of equivariant neural networks, effectively overcoming their respective disadvantages. Based on our comprehensive experiments, DeepH-2 demonstrates superiority over its predecessors in both efficiency and accuracy, showcasing state-of-the-art performance. This advancement opens up opportunities for exploring universal neural network models or even large materials models.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2401.17015
Document Type :
Working Paper