Adding Bertz index regression and MMFF94 strain penalty as auxiliary losses to a GINE GNN yields small but statistically significant OOD AUC improvements (up to +0.0066) on natural products when trained on drug-like molecules.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Physics-Aware Auxiliary Losses Improve Out-of-Distribution Generalization of a GNN Synthesizability Filter
Adding Bertz index regression and MMFF94 strain penalty as auxiliary losses to a GINE GNN yields small but statistically significant OOD AUC improvements (up to +0.0066) on natural products when trained on drug-like molecules.