arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2011.07302physics.chem-ph
收藏

用于机器学习分子和固体能量相关性质的混合局部图核

Hybrid localized graph kernel for machine learning energy-related properties of molecules and solids

Bastien Casier, Mauricio Chagas da Silva, Michael Badawi, Fabien Pascale, Tomáš Bučko, Sébastien Lebègue, Dario Rocca

摘要:

如今,电子结构和机器学习技术的结合成为预测各种体系的化学和物理性质的有力工具。为了提高预测的准确性,已经开发了大量用于机器学习应用的分子和固体的表示。在这项工作中,我们提出了一种新的描述分子图的概念的基础上。虽然图在化学信息学或生物信息学中主要用于分类问题,但它们并不经常用于回归问题,特别是与能量相关的性质。我们的方法是基于原子环境的局部分解和两个核函数的杂交:一个图形内核的贡献,描述的化学图案和库仑标签贡献,1encoded更精细的细节的局部几何结构。考虑到流行的QM7和BA10数据集,这种新的核方法在分子和凝聚相系统的能量预测的准确性进行了证明。这些示例表明,混合局部化图核优于传统方法,例如原子位置的平滑重叠(SOAP)和库仑矩阵。

英文摘要:

Nowadays, the coupling of electronic structure and machine learning techniques serves as a powerful tool to predict chemical and physical properties of a broad range of systems. With the aim of improving the accuracy of predictions, a large number of representations for molecules and solids for machine learning applications has been developed. In this work we propose a novel descriptor based on the notion of molecular graph. While graphs are largely employed in classification problems in cheminformatics or bioinformatics, they are not often used in regression problem, especially of energy-related properties. Our method is based on a local decomposition of atomic environments and on the hybridization of two kernel functions: a graph kernel contribution that describes the chemical pattern and a Coulomb label contribution that 1encodes finer details of the local geometry. The accuracy of this new kernel method in energy predictions of molecular and condensed phase systems is demonstrated by considering the popular QM7 and BA10 datasets. These examples show that the hybrid localized graph kernel outperforms traditional approaches such as, for example, the smooth overlap of atomic positions (SOAP) and the Coulomb matrices.

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。

↑