Xtal2DoS: Attention-Based Crystal to Sequence Learning for Density of States Prediction
Abstract
Modern machine learning techniques have been extensively applied to materials science, especially for property prediction tasks. A majority of these methods address scalar property predictions, while more challenging spectral properties remain less emphasized. We formulate a crystal-to-sequence learning task and propose a novel attention-based learning method, Xtal2DoS, which decodes the sequential representation of the material density of states (DoS) properties by incorporating the learned atomic embeddings through attention networks. Experiments show Xtal2DoS is faster than the existing models, and consistently outperforms other state-of-the-art methods on four metrics for two fundamental spectral properties, phonon and electronic DoS.
Cite
Text
Bai et al. "Xtal2DoS: Attention-Based Crystal to Sequence Learning for Density of States Prediction." NeurIPS 2022 Workshops: AI4Science, 2022.Markdown
[Bai et al. "Xtal2DoS: Attention-Based Crystal to Sequence Learning for Density of States Prediction." NeurIPS 2022 Workshops: AI4Science, 2022.](https://mlanthology.org/neuripsw/2022/bai2022neuripsw-xtal2dos/)BibTeX
@inproceedings{bai2022neuripsw-xtal2dos,
title = {{Xtal2DoS: Attention-Based Crystal to Sequence Learning for Density of States Prediction}},
author = {Bai, Junwen and Du, Yuanqi and Wang, Yingheng and Kong, Shufeng and Gregoire, John and Gomes, Carla P},
booktitle = {NeurIPS 2022 Workshops: AI4Science},
year = {2022},
url = {https://mlanthology.org/neuripsw/2022/bai2022neuripsw-xtal2dos/}
}