Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation
Abstract
We consider the problem of crystal materials generation using language models (LMs). A key step is to convert 3D crystal structures into 1D sequences to be processed by LMs. Prior studies used the crystallographic information framework (CIF) file stream, which fails to ensure SE(3) and periodic invariance and may not lead to unique sequence representations for a given crystal structure. Here, we propose a novel method, known as Mat2Seq, to tackle this challenge. Mat2Seq converts 3D crystal structures into 1D sequences and ensures that different mathematical descriptions of the same crystal are represented in a single unique sequence, thereby provably achieving SE(3) and periodic invariance. Experimental results show that, with language models, Mat2Seq achieves promising performance in crystal structure generation as compared with prior methods.
Cite
Text
Yan et al. "Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation." Neural Information Processing Systems, 2024. doi:10.52202/079017-3971Markdown
[Yan et al. "Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/yan2024neurips-invariant/) doi:10.52202/079017-3971BibTeX
@inproceedings{yan2024neurips-invariant,
title = {{Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation}},
author = {Yan, Keqiang and Li, Xiner and Ling, Hongyi and Ashen, Kenna and Edwards, Carl and Arróyave, Raymundo and Zitnik, Marinka and Ji, Heng and Qian, Xiaofeng and Qian, Xiaoning and Ji, Shuiwang},
booktitle = {Neural Information Processing Systems},
year = {2024},
doi = {10.52202/079017-3971},
url = {https://mlanthology.org/neurips/2024/yan2024neurips-invariant/}
}