Injecting Domain Knowledge from Empirical Interatomic Potentials to Neural Networks for Predicting Material Properties-猫眼课题宝

DOI：

10.48550/arxiv.2210.08047

发表时间：

2022-10

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Zeren Shui;Daniel S. Karls;Mingjian Wen;Ilia Nikiforov;E. Tadmor;G. Karypis

几十年来，原子模型在预测从纳米技术到药物发现等众多领域的材料行为方面发挥了至关重要的作用。在这个领域最精确的方法是植根于第一性原理量子力学计算，如密度泛函理论（DFT）。由于这些方法在计算上仍然是禁止的，从业人员传统上专注于定义物理驱动的封闭形式表达式，称为经验原子间电位（eip），它近似地模拟了材料中原子之间的相互作用。近年来，基于量子力学（dft标记）数据训练的神经网络（NN）电位已成为传统eip的更准确替代方案。然而，这些模型的泛化性在很大程度上依赖于标记的训练数据的数量，这往往仍然不足以生成适合通用应用的模型。在本文中，我们提出了两种通用策略，利用未标记的训练实例将传统eip的领域知识注入到神经网络中，以提高其泛化性。第一种策略是基于弱监督学习，在EIP上训练一个辅助分类器，并选择表现最好的EIP来产生能量，以补充训练NN时的真值DFT能量。第二种策略基于迁移学习，首先在大量容易获得的EIP能量上对神经网络进行预训练，然后在真值DFT能量上对其进行微调。在三个基准数据集上的实验结果表明，第一种策略将基准神经网络性能提高了5%至51%，而第二种策略将基准神经网络性能提高了55%。将它们结合起来进一步提高性能。

For decades, atomistic modeling has played a crucial role in predicting the behavior of materials in numerous fields ranging from nanotechnology to drug discovery. The most accurate methods in this domain are rooted in first-principles quantum mechanical calculations such as density functional theory (DFT). Because these methods have remained computationally prohibitive, practitioners have traditionally focused on defining physically motivated closed-form expressions known as empirical interatomic potentials (EIPs) that approximately model the interactions between atoms in materials. In recent years, neural network (NN)-based potentials trained on quantum mechanical (DFT-labeled) data have emerged as a more accurate alternative to conventional EIPs. However, the generalizability of these models relies heavily on the amount of labeled training data, which is often still insufficient to generate models suitable for general-purpose applications. In this paper, we propose two generic strategies that take advantage of unlabeled training instances to inject domain knowledge from conventional EIPs to NNs in order to increase their generalizability. The first strategy, based on weakly supervised learning, trains an auxiliary classifier on EIPs and selects the best-performing EIP to generate energies to supplement the ground-truth DFT energies in training the NN. The second strategy, based on transfer learning, first pretrains the NN on a large set of easily obtainable EIP energies, and then fine-tunes it on ground-truth DFT energies. Experimental results on three benchmark datasets demonstrate that the first strategy improves baseline NN performance by 5% to 51% while the second improves baseline performance by up to 55%. Combining them further boosts performance.

Injecting Domain Knowledge from Empirical Interatomic Potentials to Neural Networks for Predicting Material Properties

文献摘要

相似文献