DFT energy prediction on AgAu
0.3353MAE (Config, eV)SchNet
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| SchNetLabel Augmentation=false, Multi-task Pretraining=true2022.10 | 0.3353 | 0.013 | 54.65 | |
| SchNetLabel Augmentation=true, Multi-task Pretraining=true2022.10 | 0.3496 | 0.0135 | 52.8 | |
| SOAPNetLabel Augmentation=true, Multi-task Pretraining=true2022.10 | 0.3858 | 0.0154 | 30.23 | |
| SOAPNetLabel Augmentation=false, Multi-task Pretraining=true2022.10 | 0.3962 | 0.0154 | 29.34 | |
| GemNetLabel Augmentation=false, Multi-task Pretraining=true2022.10 | 0.5057 | 0.0185 | 45.71 | |
| SOAPNetLabel Augmentation=true, Multi-task Pretraining=false2022.10 | 0.5067 | 0.0205 | 7.92 | |
| SOAPNetLabel Augmentation=false, Multi-task Pretraining=false2022.10 | 0.5422 | 0.0226 | — | |
| GemNetLabel Augmentation=true, Multi-task Pretraining=true2022.10 | 0.6074 | 0.0218 | 35.3 | |
| SchNetLabel Augmentation=true, Multi-task Pretraining=false2022.10 | 0.6815 | 0.0266 | 7.33 | |
| SchNetLabel Augmentation=false, Multi-task Pretraining=false2022.10 | 0.729 | 0.029 | — | |
| GemNetLabel Augmentation=true, Multi-task Pretraining=false2022.10 | 0.8381 | 0.03 | 10.87 | |
| GemNetLabel Augmentation=false, Multi-task Pretraining=false2022.10 | 0.9257 | 0.0342 | — | |
| CGCNNLabel Augmentation=true, Multi-task Pretraining=true2022.10 | 1.3857 | 0.0499 | 18.55 | |
| CGCNNLabel Augmentation=false, Multi-task Pretraining=true2022.10 | 1.4377 | 0.0532 | 14.38 | |
| CGCNNLabel Augmentation=true, Multi-task Pretraining=false2022.10 | 1.6065 | 0.0589 | 4.71 | |
| CGCNNLabel Augmentation=false, Multi-task Pretraining=false2022.10 | 1.6683 | 0.0625 | — | |
| Best EIPLabel Augmentation=false, Multi-task Pretraining=false2022.10 | 4.4587 | 0.2063 | — |