Gaussian Plane-Wave Neural Operator for Electron Density Estimation

Seongsu Kim, Sungsoo Ahn
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23805-23824, 2024.

Abstract

This work studies machine learning for electron density prediction, which is fundamental for understanding chemical systems and density functional theory (DFT) simulations. To this end, we introduce the Gaussian plane-wave neural operator (GPWNO), which operates in the infinite-dimensional functional space using the plane-wave and Gaussian-type orbital bases, widely recognized in the context of DFT. In particular, both high- and low-frequency components of the density can be effectively represented due to the complementary nature of the two bases. Extensive experiments on QM9, MD, and material project datasets demonstrate GPWNO’s superior performance over ten baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-kim24b, title = {{G}aussian Plane-Wave Neural Operator for Electron Density Estimation}, author = {Kim, Seongsu and Ahn, Sungsoo}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {23805--23824}, 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/kim24b/kim24b.pdf}, url = {https://proceedings.mlr.press/v235/kim24b.html}, abstract = {This work studies machine learning for electron density prediction, which is fundamental for understanding chemical systems and density functional theory (DFT) simulations. To this end, we introduce the Gaussian plane-wave neural operator (GPWNO), which operates in the infinite-dimensional functional space using the plane-wave and Gaussian-type orbital bases, widely recognized in the context of DFT. In particular, both high- and low-frequency components of the density can be effectively represented due to the complementary nature of the two bases. Extensive experiments on QM9, MD, and material project datasets demonstrate GPWNO’s superior performance over ten baselines.} }
Endnote
%0 Conference Paper %T Gaussian Plane-Wave Neural Operator for Electron Density Estimation %A Seongsu Kim %A Sungsoo Ahn %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-kim24b %I PMLR %P 23805--23824 %U https://proceedings.mlr.press/v235/kim24b.html %V 235 %X This work studies machine learning for electron density prediction, which is fundamental for understanding chemical systems and density functional theory (DFT) simulations. To this end, we introduce the Gaussian plane-wave neural operator (GPWNO), which operates in the infinite-dimensional functional space using the plane-wave and Gaussian-type orbital bases, widely recognized in the context of DFT. In particular, both high- and low-frequency components of the density can be effectively represented due to the complementary nature of the two bases. Extensive experiments on QM9, MD, and material project datasets demonstrate GPWNO’s superior performance over ten baselines.
APA
Kim, S. & Ahn, S.. (2024). Gaussian Plane-Wave Neural Operator for Electron Density Estimation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:23805-23824 Available from https://proceedings.mlr.press/v235/kim24b.html.

Related Material