FastCHGNet trains a CHGNet universal interatomic potential in 1.53 hours on 32 GPUs, but the fastest variant degrades force and stress accuracy.
Hierarchical modeling of molecular energies using a deep neural network,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2024 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs
FastCHGNet trains a CHGNet universal interatomic potential in 1.53 hours on 32 GPUs, but the fastest variant degrades force and stress accuracy.