no code implementations • 9 May 2024 • Shi Yin, Xinyang Pan, Fengyan Wang, Feng Wu, Lixin He
We present both a theoretical and a methodological framework that addresses a critical challenge in applying deep learning to physical systems: the reconciliation of non-linear expressiveness with SO(3)-equivariance in predictions of SO(3)-equivariant quantities, such as the electronic-structure Hamiltonian.
no code implementations • 1 Jan 2024 • Shi Yin, Xinyang Pan, XUDONG ZHU, Tianyu Gao, Haochong Zhang, Feng Wu, Lixin He
Deep learning for predicting the electronic structure Hamiltonian of quantum systems necessitates satisfying the covariance laws, among which achieving SO(3)-equivariance without sacrificing the non-linear expressive capability of networks remains unsolved.
2 code implementations • 25 Jun 2019 • Chengqiang Lu, Qi Liu, Chao Wang, Zhenya Huang, Peize Lin, Lixin He
In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction.
Ranked #6 on Graph Regression on Lipophilicity