arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.06762cond-mat.mtrl-scics.AI
收藏

生成式分层材料搜索

Generative Hierarchical Materials Search

Google DeepMind(谷歌DeepMind)

Sherry Yang, Simon Batzner, Ruiqi Gao, Muratahan Aykol, Alexander L. Gaunt, Brendan McMorrow, Danilo J. Rezende, Dale Schuurmans, Igor Mordatch, Ekin D. Cubuk

AI总结:

针对材料科学中晶体结构可控生成需求,提出GenMS框架,结合语言模型、扩散模型与图神经网络,通过前向树搜索实现自然语言到晶体结构的端到端生成,性能优于直接用语言模型生成的方案,可生成多种常见晶体结构。

摘要:

大规模训练的生成模型如今已能生成文本、视频,近期还可生成晶体结构等科学数据。在将生成式方法应用于材料科学,尤其是晶体结构的场景中,领域专家以高层指令形式提供的引导,对自动化系统输出可用于下游研究的候选晶体至关重要。本研究将端到端的语言到结构生成建模为多目标优化问题,并提出Generative Hierarchical Materials Search(GenMS,生成式分层材料搜索)用于晶体结构的可控生成。GenMS包含两个核心模块:(1)一个语言模型,以高层自然语言为输入,生成关于晶体的中间文本信息(如化学式);(2)一个扩散模型,以中间信息为输入,生成低层连续值晶体结构。此外,GenMS还使用图神经网络从生成的晶体结构中预测性质(如形成能)。在推理阶段,GenMS利用这三个组件在可能的结构空间中执行前向树搜索。实验表明,在满足用户需求和生成低能结构两方面,GenMS的表现均优于其他直接使用语言模型生成结构的方案。研究证实,GenMS仅通过自然语言输入就能生成双钙钛矿、尖晶石等常见晶体结构,因此可为未来更复杂的结构生成奠定基础。

英文摘要:

Generative models trained at scale can now produce text, video, and more recently, scientific data such as crystal structures. In applications of generative approaches to materials science, and in particular to crystal structures, the guidance from the domain expert in the form of high-level instructions can be essential for an automated system to output candidate crystals that are viable for downstream research. In this work, we formulate end-to-end language-to-structure generation as a multi-objective optimization problem, and propose Generative Hierarchical Materials Search (GenMS) for controllable generation of crystal structures. GenMS consists of (1) a language model that takes high-level natural language as input and generates intermediate textual information about a crystal (e.g., chemical formulae), and (2) a diffusion model that takes intermediate information as input and generates low-level continuous value crystal structures. GenMS additionally uses a graph neural network to predict properties (e.g., formation energy) from the generated crystal structures. During inference, GenMS leverages all three components to conduct a forward tree search over the space of possible structures. Experiments show that GenMS outperforms other alternatives of directly using language models to generate structures both in satisfying user request and in generating low-energy structures. We confirm that GenMS is able to generate common crystal structures such as double perovskites, or spinels, solely from natural language input, and hence can form the foundation for more complex structure generation in near future.

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。

↑