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 2407.16131cond-mat.mtrl-scics.LGphysics.comp-ph
收藏

CrysToGraph:一种用于晶体材料性质的综合预测模型及基准

CrysToGraph: A Comprehensive Predictive Model for Crystal Materials Properties and the Benchmark

City University of Hong Kong(香港城市大学);ByteDance Research(字节跳动研究院);Renmin University of China(中国人民大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Guangxi University of Chinese Medicine(广西中医药大学)

Hongyi Wang, Ji Sun, Jinzhe Liang, Li Zhai, Zitian Tang, Zijian Li, Wei Zhai, Xusheng Wang, Weihao Gao, Sheng Gong

AI总结:

针对现有GNN难以捕捉晶体长程相互作用的问题,提出专门面向非常规晶系的基于transformer的几何图网络CrysToGraph,同时构建综合基准UnconvBench,在两类晶体基准上均取得最优性能。

摘要:

晶格间的离子键和有序的微观结构赋予晶体独特的对称性,并决定了其宏观性质。尤其是非常规晶体,具有非传统的晶格结构或具备奇异的物理性质,是极具研究价值的对象。因此,要准确预测晶体的物理和化学性质,考虑长程有序性至关重要。尽管GNN(图神经网络)擅长捕捉晶体中原子的局部环境,但由于其深度有限,往往难以有效捕捉长程相互作用。本文提出了CrysToGraph(即基于图上Transformer的晶体模型),这是一种专门针对非常规晶系设计的新型基于transformer的几何图网络,同时提出了UnconvBench,这是一个综合基准,用于评估模型在缺陷晶体、低维晶体和MOF(金属有机框架)等非常规晶体材料上的预测性能。CrysToGraph通过基于transformer的图卷积模块有效捕捉短程相互作用,同时通过图级transformer模块捕捉长程相互作用。CrysToGraph在多项任务中证明了其对非常规晶体材料建模的有效性,并且性能优于大多数现有方法,在非常规晶体和传统晶体的基准测试中均取得了新的SOTA(最优)结果。

英文摘要:

The ionic bonding across the lattice and ordered microscopic structures endow crystals with unique symmetry and determine their macroscopic properties. Unconventional crystals, in particular, exhibit non-traditional lattice structures or possess exotic physical properties, making them intriguing subjects for investigation. Therefore, to accurately predict the physical and chemical properties of crystals, it is crucial to consider long-range orders. While GNN excels at capturing the local environment of atoms in crystals, they often face challenges in effectively capturing longer-ranged interactions due to their limited depth. In this paper, we propose CrysToGraph ($\textbf{Crys}$tals with $\textbf{T}$ransformers $\textbf{o}$n $\textbf{Graph}$s), a novel transformer-based geometric graph network designed specifically for unconventional crystalline systems, and UnconvBench, a comprehensive benchmark to evaluate models' predictive performance on unconventional crystal materials such as defected crystals, low-dimension crystals and MOF. CrysToGraph effectively captures short-range interactions with transformer-based graph convolution blocks as well as long-range interactions with graph-wise transformer blocks. CrysToGraph proofs its effectiveness in modelling unconventional crystal materials in multiple tasks, and moreover, it outperforms most existing methods, achieving new state-of-the-art results on the benchmarks of both unconventional crystals and traditional crystals.

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。

↑