Skip to main content

Table 1 Hyperparameter grid used in the optimization

From: Splitting chemical structure data sets for federated privacy-preserving machine learning

Hyperparameter Set of values
Hidden sizes [1200], [1600], [2000], [3000], [1600, 1600]
Dropout 0.4, 0.5, 0.6, 0.7
Weight decay 1E−5, 1E−6