TorchMD-NET

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Graphs4 results

Graph Property PredictiononQM9
Standardized MAE· 2022-02-05
0.84
best: 0.52 (GotenNet (Large))
SOTA
TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials arXiv:2202.02541
Graph Property PredictiononQM9
logMAE· 2022-02-05
-5.9
best: -6.41 (GotenNet (Large))
SOTA
TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials arXiv:2202.02541
Graph Property PredictiononQM9
alpha (ma)· 2022-02-05
59
best: 71 (EGNN)
TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials arXiv:2202.02541
Graph Property PredictiononQM9
gap (meV)· 2022-02-05
36.1
best: 48 (EGNN)
TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials arXiv:2202.02541