arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.08262cond-mat.mtrl-scics.AI
收藏

SLayerGen:一种适用于所有空间群和层群的晶格生成模型

SLayerGen: a Crystal Generative Model for all Space and Layer Groups

Department of Materials Science & Engineering, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校材料科学与工程系);Department of Computer Science, Princeton University(普林斯顿大学计算机科学系);Materials Research Laboratory, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校材料研究实验室)

Rees Chang, Andrew Novick, Ryan P Adams, Elif Ertekin

AI总结:

本文提出SLayerGen,一种能生成符合空间群或层群对称性的晶格生成模型,解决了现有模型未考虑层群影响的问题,通过改进扩散组件和构建新数据集,提升了对非周期材料的生成能力。

摘要:

晶格生成模型在加速bulk周期材料发现方面取得了快速进展。然而,许多材料系统如二维超导体、薄膜半导体和催化表面是双周期的,即沿一个晶格方向非周期性。这些系统在层群下不变,而现有模型未考虑层群的影响。本文提出SLayerGen,一种生成模型,生成的晶体被约束为对任何空间或层群不变。SLayerGen包括从粗到细的离散自回归晶格生成;基于Transformer的自回归采样Wyckoff位置、元素和对称唯一原子的数量;以及空间或层群等变的原子坐标扩散。对于扩散组件,我们修正了先前工作中因六方群在分数坐标中非正交导致的损失不一致问题。为促进双周期材料生成模型的发展,我们收集并过滤了单层和双层的数据集,提出了相关的评估指标,并开发了新的层群对称性表示。对于de novo生成双周期材料,SLayerGen在bulk晶体生成模型上实现了一致的性能提升,并在同时训练bulk和双周期材料时具有竞争力。

英文摘要:

Crystal generative models have shown rapid progress for accelerating the discovery of bulk, periodic materials. However, many material systems such as 2D superconductors, thin film semiconductors, and catalytic surfaces are diperiodic, i.e., aperiodic along one of the lattice directions. These systems are invariant under the layer groups, which are known to influence materials properties yet not considered by existing models. In this paper, we propose SLayerGen, a generative model that produces crystals constrained to be invariant to any space or layer group. SLayerGen consists of coarse-to-fine discrete autoregressive lattice generation; transformer-based autoregressive sampling of Wyckoff positions, elements, and numbers of symmetrically unique atoms; and space or layer group equivariant diffusion of atomic coordinates. For the diffusion component, we corrected an inconsistency in the loss from prior work arising from hexagonal groups being non-orthogonal in fractional coordinates. To facilitate progress in generative modeling of diperiodic materials, we assembled and filtered datasets of monolayers and bilayers, propose relevant evaluation metrics, and developed novel representations for layer group symmetries. For de novo generation of diperiodic materials, SLayerGen achieves consistent performance gains over bulk crystal generative models and is competitive when training jointly on bulk and diperiodic materials.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑