Open Catalyst 2020
Open Catalyst 2020 is a dataset for catalysis in chemical engineering. Focusing on molecules that are important in renewable energy applications, the OC20 data set comprises over 1.3 million relaxations of molecular adsorptions onto surfaces, the largest data set of electrocatalyst structures to date.
Variants: OC20
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Initial Structure to Relaxed Energy (IS2RE) | GemNet-OC | GemNet-OC: Developing Graph Neural Networks … | 2022-04-06 |
| Initial Structure to Relaxed Energy (IS2RE) | GemNet-XL | Towards Training Billion Parameter Graph … | 2022-03-18 |
| Initial Structure to Relaxed Energy (IS2RE) | SpinConv | Rotation Invariant Graph Neural Networks … | 2021-06-17 |
| Initial Structure to Relaxed Energy (IS2RE) | Noisy Nodes | Simple GNN Regularisation for 3D … | 2021-06-15 |
Recent papers with results on this dataset: