arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.02680physics.chem-phcs.LG
收藏

电子结构的多任务学习预测和探索分子势能面

Multi-task learning for electronic structure to predict and explore molecular potential energy surfaces

California Institute of Technology(加州理工学院);Entos, Inc.(Entos公司);NVIDIA(英伟达)

Zhuoran Qiao, Feizhi Ding, Matthew Welborn, Peter J. Bygrave, Daniel G. A. Smith, Animashree Anandkumar, Frederick R. Manby, Thomas F. Miller

摘要:

我们改进了OrbNet模型,以准确预测分子的能量,力和其他响应特性,使用基于低成本近似量子算子特征的图形神经网络架构,在自适应原子轨道基础上。该模型是端到端可微的,由于所有电子结构项的分析梯度的推导,并被证明是跨化学空间的转移,由于使用特定领域的功能。通过多任务学习将物理激励约束结合在电子结构上,提高了学习效率。该模型优于现有方法的能量预测任务的QM9数据集和构象数据集的分子几何优化,在计算成本是千倍或更多的减少相比,传统的量子化学计算(如密度泛函理论),提供类似的准确性。

英文摘要:

We refine the OrbNet model to accurately predict energy, forces, and other response properties for molecules using a graph neural-network architecture based on features from low-cost approximated quantum operators in the symmetry-adapted atomic orbital basis. The model is end-to-end differentiable due to the derivation of analytic gradients for all electronic structure terms, and is shown to be transferable across chemical space due to the use of domain-specific features. The learning efficiency is improved by incorporating physically motivated constraints on the electronic structure through multi-task learning. The model outperforms existing methods on energy prediction tasks for the QM9 dataset and for molecular geometry optimizations on conformer datasets, at a computational cost that is thousand-fold or more reduced compared to conventional quantum-chemistry calculations (such as density functional theory) that offer similar accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑