This repository contains the first release of the code accompanying the NeurIPS 2022 paper Equivariant Networks for Crystal Structures.
Subsequent releases will make the code more reusable and facilitate access to the data.
If you find this code useful, please cite the paper :
@inproceedings{
kaba2022equivariant,
title={Equivariant Networks for Crystal Structures},
author={S{\'e}kou-Oumar Kaba and Siamak Ravanbakhsh},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=0Dh8dz4snu}
}
This code also makes direct use of the autoquiv
package by Mehran Shakerinava. The code for the package is available here:
https://github.com/mshakerinava/AutoEquiv