提出对称感知图神经网络，可区分晶体材料中原子排列差异。
Learning Ordering in Crystalline Materials with Symmetry-Aware Graph Neural Networks
- 设计对称等变的图神经网络，保留不同排列的晶格对称性差异。
- 实验表明传统不变模型无法分辨相同结构的不同原子排布。
- 适用于需要精确控制原子有序性的材料设计任务。
图卷积神经网络（GCNN）已成为催化与储能等领域筛选晶体材料化学空间的主流方法，通过结构预测性能。然而，多组分材料存在化学（无）序问题，同一晶格结构可呈现从高度有序到完全无序固溶体的多种元素排列。关键在于稳定性、强度和催化性能不仅依赖结构，还受原子排列影响。因此，确保GCNN能区分原子排列至关重要。但现有模型对有序性的感知能力尚不明确。本文在基于高通量原子模拟构建的定制数据集上，评估了多种神经网络架构对多组分材料有序性相关能量的捕捉能力。结果发现，传统对称不变的GCNN无法区分同一材料中多种对称不等价的原子排列差异；而对称等变模型架构能自然保留并区分不同排列的晶体学对称性特征。
原文摘要 · Abstract (English)
Graph convolutional neural networks (GCNNs) have become a machine learning workhorse for screening the chemical space of crystalline materials in fields such as catalysis and energy storage, by predicting properties from structures. Multicomponent materials, however, present a unique challenge since they can exhibit chemical (dis)order, where a given lattice structure can encompass a variety of elemental arrangements ranging from highly ordered structures to fully disordered solid solutions. Critically, properties like stability, strength, and catalytic performance depend not only on structures but also on orderings. To enable rigorous materials design, it is thus critical to ensure GCNNs are capable of distinguishing among atomic orderings. However, the ordering-aware capability of GCNNs has been poorly understood. Here, we benchmark various neural network architectures for capturing the ordering-dependent energetics of multicomponent materials in a custom-made dataset generated with high-throughput atomistic simulations. Conventional symmetry-invariant GCNNs were found unable to discern the structural difference between the diverse symmetrically inequivalent atomic orderings of the same material, while symmetry-equivariant model architectures could inherently preserve and differentiate the distinct crystallographic symmetries of various orderings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。