Machine learning assisted modeling of the inter-atomic potential energy surface (PES) is revolutionizing the field of molecular simulation. With the accumulation of high-quality electronic structure data, a model that can be pretrained on all available data and finetuned on downstream tasks with a small additional effort would bring the field to a new stage. Here we propose DPA-1, a Deep Potential model with a novel attention mechanism, which is highly effective for representing the conformation and chemical spaces of atomic systems and learning the PES. We tested DPA-1 on a number of systems and observed superior performance compared with existing benchmarks. When pretrained on large-scale datasets containing 56 elements, DPA-1 can be successfully applied to various downstream tasks with a great improvement of sample efficiency. Surprisingly, for different elements, the learned type embedding parameters form a $spiral$ in the latent space and have a natural correspondence with their positions on the periodic table, showing interesting interpretability of the pretrained DPA-1 model.
翻译:由于分子模拟领域积累了高质量的电子结构数据,这一模型可以对所有现有数据进行预先培训,再作少量努力对下游任务进行微调,这将使实地进入新的阶段。我们在这里提议DA-1,一个具有新关注机制的深层潜力模型,它非常有效,可以代表原子系统的校正和化学空间,并学习PES。我们在若干系统中测试了DPA-1,并观察到与现有基准相比的优异性能。在对包含56个要素的大型数据集进行预先培训时,DPA-1可以成功地应用于各下游任务,大大提高取样效率。令人惊讶的是,对于不同的要素,所学过的型号嵌入参数形成在潜藏空间的美元,并与他们在定期表格上的位置有自然联系,显示了事先经过训练的DPA-1模型的可解释性。