Compositionally restricted attention-based network for materials property predictions
Compositionally restricted attention-based network for materials property predictions
复制标题
DOI：
10.1038/s41524-021-00545-1
复制
发表时间：
2021-05-28
影响因子：
9.7
通讯作者：
Sparks, Taylor D.
中科院分区：
文献类型：
--
作者：
Wang, Anthony Yu-Tung;Kauwe, Steven K.;Sparks, Taylor D.
在本文中，我们展示了Transformer自注意机制在材料科学中的应用。我们的网络，基于成分限制注意力的网络（CrabNet），探索了仅提供化学式时结构不可知材料属性预测的领域。我们的研究结果表明，CrabNet的性能匹配或超过目前的最佳实践方法，几乎所有的28个基准数据集。我们还展示了CrabNet的架构如何通过显示不同的可视化方法使其设计成为可能，从而使自己对模型的可解释性。我们相信，CrabNet及其基于注意力的框架将引起未来材料信息学研究人员的浓厚兴趣。
In this paper, we demonstrate an application of the Transformer self-attention mechanism in the context of materials science. Our network, the Compositionally Restricted Attention-Based network (CrabNet), explores the area of structure-agnostic materials property predictions when only a chemical formula is provided. Our results show that CrabNet's performance matches or exceeds current best-practice methods on nearly all of 28 total benchmark datasets. We also demonstrate how CrabNet's architecture lends itself towards model interpretability by showing different visualization approaches that are made possible by its design. We feel confident that CrabNet and its attention-based framework will be of keen interest to future materials informatics researchers.