arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.12984cond-mat.mtrl-scics.AI
收藏

PDDFormer:基于晶格点集的晶格点集图变换器用于晶体材料性质预测

PDDFormer: Pairwise Distance Distribution Graph Transformer for Crystal Material Property Prediction

Software Engineering Institute, East China Normal University(东华大学软件工程院);School of Chemistry and Molecular Engineering, East China Normal University(东华大学化学与分子工程学院);School of Geospatial Information, Information Engineering University(信息工程大学测绘信息学院);School of Communication and Electronic Engineering, East China Normal University(东华大学通信与电子工程学院);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)

Xiangxiang Shen, Zheng Wan, Lingfeng Wen, Licheng Sun, Jian Yang, Xuan Tang, Shing-Ho J. Lin, Xiao He, Mingsong Chen, Xian Wei

AI总结:

PDDFormer通过引入原子加权配对距离分布和单元格配对距离分布,构建多边晶体图以提升晶体材料性质预测的准确性和效率。

摘要:

晶体结构可以简化为一个在三维空间中沿底层晶格周期性重复的周期性点集。传统上,晶体表示方法通过晶格参数、对称性和空间群等描述来表征结构。然而,实际上,材料中的原子始终在绝对零度以上振动,导致它们的位置持续波动。这种动态行为破坏了晶格的基本周期性,使基于静态晶格参数和传统描述符的晶体图在轻微扰动下变得不连续。化学家提出了配对距离分布(PDD)方法来解决这个问题。然而,PDD的完整性要求定义大量邻近原子,导致计算成本高。此外,PDD不考虑原子信息,使其难以直接应用于晶体材料性质预测任务。为了解决这些挑战,我们引入了原子加权配对距离分布(WPDD)和单元格配对距离分布(UPDD),并将它们应用于多边晶体图的构建。我们展示了在轻微原子位置扰动下晶体图的连续性和整体完整性。此外,通过将PDD建模为全局信息,并将其整合到基于矩阵的消息传递中,我们显著降低了计算成本。全面评估结果表明,WPDDFormer在Materials Project和JARVIS-DFT等基准数据集上实现了最先进的预测准确性。

英文摘要:

Crystal structures can be simplified as a periodic point set that repeats across three-dimensional space along an underlying lattice. Traditionally, crystal representation methods characterize the structure using descriptors such as lattice parameters, symmetry, and space groups. However, in reality, atoms in materials always vibrate above absolute zero, causing their positions to fluctuate continuously. This dynamic behavior disrupts the fundamental periodicity of the lattice, making crystal graphs based on static lattice parameters and conventional descriptors discontinuous under slight perturbations. Chemists proposed the pairwise distance distribution (PDD) method to address this problem. However, the completeness of PDD requires defining a large number of neighboring atoms, leading to high computational costs. Additionally, PDD does not account for atomic information, making it challenging to apply it directly to crystal material property prediction tasks. To tackle these challenges, we introduce the atom-Weighted Pairwise Distance Distribution (WPDD) and Unit cell Pairwise Distance Distribution (UPDD) and apply them to the construction of multi-edge crystal graphs. We demonstrate the continuity and general completeness of crystal graphs under slight atomic position perturbations. Moreover, by modeling PDD as global information and integrating it into matrix-based message passing, we significantly reduce computational costs. Comprehensive evaluation results show that WPDDFormer achieves state-of-the-art predictive accuracy across tasks on benchmark datasets such as the Materials Project and JARVIS-DFT.

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。

↑