Equivariant Diffusion for Crystal Structure Prediction

Peijia Lin, Pin Chen, Rui Jiao, Qing Mo, Cen Jianhuan, Wenbing Huang, Yang Liu, Dan Huang, Yutong Lu
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29890-29913, 2024.

Abstract

In addressing the challenge of Crystal Structure Prediction (CSP), symmetry-aware deep learning models, particularly diffusion models, have been extensively studied, which treat CSP as a conditional generation task. However, ensuring permutation, rotation, and periodic translation equivariance during diffusion process remains incompletely addressed. In this work, we propose EquiCSP, a novel equivariant diffusion-based generative model. We not only address the overlooked issue of lattice permutation equivariance in existing models, but also develop a unique noising algorithm that rigorously maintains periodic translation equivariance throughout both training and inference processes. Our experiments indicate that EquiCSP significantly surpasses existing models in terms of generating accurate structures and demonstrates faster convergence during the training process.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-lin24b, title = {Equivariant Diffusion for Crystal Structure Prediction}, author = {Lin, Peijia and Chen, Pin and Jiao, Rui and Mo, Qing and Jianhuan, Cen and Huang, Wenbing and Liu, Yang and Huang, Dan and Lu, Yutong}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {29890--29913}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/lin24b/lin24b.pdf}, url = {https://proceedings.mlr.press/v235/lin24b.html}, abstract = {In addressing the challenge of Crystal Structure Prediction (CSP), symmetry-aware deep learning models, particularly diffusion models, have been extensively studied, which treat CSP as a conditional generation task. However, ensuring permutation, rotation, and periodic translation equivariance during diffusion process remains incompletely addressed. In this work, we propose EquiCSP, a novel equivariant diffusion-based generative model. We not only address the overlooked issue of lattice permutation equivariance in existing models, but also develop a unique noising algorithm that rigorously maintains periodic translation equivariance throughout both training and inference processes. Our experiments indicate that EquiCSP significantly surpasses existing models in terms of generating accurate structures and demonstrates faster convergence during the training process.} }
Endnote
%0 Conference Paper %T Equivariant Diffusion for Crystal Structure Prediction %A Peijia Lin %A Pin Chen %A Rui Jiao %A Qing Mo %A Cen Jianhuan %A Wenbing Huang %A Yang Liu %A Dan Huang %A Yutong Lu %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-lin24b %I PMLR %P 29890--29913 %U https://proceedings.mlr.press/v235/lin24b.html %V 235 %X In addressing the challenge of Crystal Structure Prediction (CSP), symmetry-aware deep learning models, particularly diffusion models, have been extensively studied, which treat CSP as a conditional generation task. However, ensuring permutation, rotation, and periodic translation equivariance during diffusion process remains incompletely addressed. In this work, we propose EquiCSP, a novel equivariant diffusion-based generative model. We not only address the overlooked issue of lattice permutation equivariance in existing models, but also develop a unique noising algorithm that rigorously maintains periodic translation equivariance throughout both training and inference processes. Our experiments indicate that EquiCSP significantly surpasses existing models in terms of generating accurate structures and demonstrates faster convergence during the training process.
APA
Lin, P., Chen, P., Jiao, R., Mo, Q., Jianhuan, C., Huang, W., Liu, Y., Huang, D. & Lu, Y.. (2024). Equivariant Diffusion for Crystal Structure Prediction. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:29890-29913 Available from https://proceedings.mlr.press/v235/lin24b.html.

Related Material