GeoEnsemble for Open Catalyst Challenge 2022

Introduction

The Open Catalyst Challenge aims for the discovery of new catalysts for driving efficient and carbon neutral means for energy storage and generation. The task for this year's challenge is to design new machine learning models to predict the outcome of catalyst simulations used to understand activity. In this year, we focus on the same task -- Initial Structure to Relaxed Energy (IS2RE) -- as last year. Addtionally, other than the 460K IS2RE data, we provide the Structure-to-Energy-Forces (S2EF) 2M training data to help to obtain the better solution.

Model Overview

GMN-OC

The Whole Framework: GeoEnsemble

Results on the Public Leaderboard

data source: Link

Useful Materials

Pretrained Models & Souce Codes

Comning soon.

Slides

Link

Videos

Comning soon.

Reference

@inproceedings{
huang2022equivariant,
title={Equivariant Graph Mechanics Networks with Constraints},
author={Wenbing Huang and Jiaqi Han and Yu Rong and Tingyang Xu and Fuchun Sun and Junzhou Huang},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=SHbhHHfePhP}
}

Contacts

If you have any questions, please contact us: Link

Disclaimer

• The source code and the pre-trained models are for research purpose only.
• This is not an officially supported Tencent product.

Last Updated: 2022-12-17