Retraining molecular property predictors on active-learning batches of DFT-computed molecules enables a genetic generative model to generate molecules with properties beyond the training data and more stable molecules.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Active Learning Enables Extrapolation in Molecular Generative Models
Retraining molecular property predictors on active-learning batches of DFT-computed molecules enables a genetic generative model to generate molecules with properties beyond the training data and more stable molecules.