arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2406.09263cond-mat.mtrl-scics.LG
收藏

基于 Transformer 扩散模型的晶体结构生成式逆向设计

Generative Inverse Design of Crystal Structures via Diffusion Models with Transformers

Institute of Industrial Science, The University of Tokyo(东京大学工业科学研究所)

Izumi Takahara, Kiyou Shibata, Teruyasu Mizoguchi

AI总结:

本文提出一种以 Transformer 为骨干的新型扩散模型,用于晶体结构生成式逆向设计,实验表明其在按目标属性生成结构方面优于既有方法,且最优条件化策略依赖数据集。

摘要:

深度学习的最新进展使得通过在文本、图像和音频的大型数据集上训练生成模型来生成逼真数据成为可能。尽管这些模型在生成新颖且合理的数据方面表现出卓越性能,但它们能否通过数据生成有效加速科学发现,并推动多个科学领域取得重大进展,仍是一个悬而未决的问题。特别是,发现具有良好性能的新型无机材料在科学研究和工业应用方面都构成一项关键挑战。然而,与文本或图像数据不同,材料,或者更具体地说晶体结构,由多种类型的变量组成——包括晶格向量、原子位置和原子种类。这种数据复杂性催生了多种用于表示和生成此类数据的方法。因此,晶体结构生成模型的设计选择仍是一个悬而未决的问题。在本研究中,我们探索了一种用于晶体结构生成式逆向设计的新型扩散模型,其骨干网络基于 Transformer 架构。我们证明,在生成具有所需性能的晶体结构方面,我们的模型在通用性上优于以往方法。此外,我们的实证结果表明,最优条件化方法会因数据集的不同而变化。

英文摘要:

Recent advances in deep learning have enabled the generation of realistic data by training generative models on large datasets of text, images, and audio. While these models have demonstrated exceptional performance in generating novel and plausible data, it remains an open question whether they can effectively accelerate scientific discovery through the data generation and drive significant advancements across various scientific fields. In particular, the discovery of new inorganic materials with promising properties poses a critical challenge, both scientifically and for industrial applications. However, unlike textual or image data, materials, or more specifically crystal structures, consist of multiple types of variables - including lattice vectors, atom positions, and atomic species. This complexity in data give rise to a variety of approaches for representing and generating such data. Consequently, the design choices of generative models for crystal structures remain an open question. In this study, we explore a new type of diffusion model for the generative inverse design of crystal structures, with a backbone based on a Transformer architecture. We demonstrate our models are superior to previous methods in their versatility for generating crystal structures with desired properties. Furthermore, our empirical results suggest that the optimal conditioning methods vary depending on the dataset.

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。

↑