Large data sets are essential for building deep learning models. However, generating large datasets with higher theoretical levels and larger computational models remains difficult due to the high cost of first-principles calculation. Here, we propose a lightweight and highly accurate machine learning approach using pre-trained Graph Neural Networks (GNNs) for industrially important but difficult to scale models. The proposed method was applied to a small dataset of graphene surface systems containing surface defects, and achieved comparable accuracy with six orders of magnitude and faster learning than when the GNN was trained from scratch.

中文翻译：

---

使用预训练图神经网络进行轻量级高精度材料性能预测及其在小数据集上的应用

大数据集对于构建深度学习模型至关重要。然而，由于第一性原理计算的成本高昂，生成具有更高理论水平和更大计算模型的大型数据集仍然很困难。在这里，我们提出了一种轻量级且高度准确的机器学习方法，使用预先训练的图神经网络（GNN）来处理工业上重要但难以扩展的模型。所提出的方法应用于包含表面缺陷的石墨烯表面系统的小型数据集，与从头开始训练 GNN 相比，其精度提高了六个数量级，并且学习速度更快。