Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian
Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian
复制标题
DOI：
10.48550/arxiv.2306.04922
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Haiyang Yu;Zhao Xu;X. Qian;Xiaoning Qian;Shuiwang Ji
中科院分区：
文献类型：
--
作者：
Haiyang Yu;Zhao Xu;X. Qian;Xiaoning Qian;Shuiwang Ji
我们考虑了哈密顿矩阵的预测，该预测发现在量子化学和凝结物理学中使用。效率和均衡性是两个重要但相互矛盾的因素。在这项工作中，我们提出了一个名为QHNET的SE（3） - 等级网络，该网络可实现效率和权衡。我们的主要进步在于QHNET体系结构的创新设计，它不仅遵守潜在的对称性，而且还可以使张量产品数量减少92 \％。此外，当涉及更多原子类型时，QHNET可以防止通道维度的指数增长。我们在MD17数据集上执行实验，包括四个分子系统。实验结果表明，我们的QHNET可以以明显更快的速度实现与最先进方法的可比性能。此外，由于其简化的架构，我们的QHNET消耗了50 \％的内存。我们的代码作为AIRS库的一部分公开可用（\ url {https://github.com/divelab/airs}）。
We consider the prediction of the Hamiltonian matrix, which finds use in quantum chemistry and condensed matter physics. Efficiency and equivariance are two important, but conflicting factors. In this work, we propose a SE(3)-equivariant network, named QHNet, that achieves efficiency and equivariance. Our key advance lies at the innovative design of QHNet architecture, which not only obeys the underlying symmetries, but also enables the reduction of number of tensor products by 92\%. In addition, QHNet prevents the exponential growth of channel dimension when more atom types are involved. We perform experiments on MD17 datasets, including four molecular systems. Experimental results show that our QHNet can achieve comparable performance to the state of the art methods at a significantly faster speed. Besides, our QHNet consumes 50\% less memory due to its streamlined architecture. Our code is publicly available as part of the AIRS library (\url{https://github.com/divelab/AIRS}).