Skip to main content

Table 2 Hyperparameters optimization for MPN and SAMPN

From: A self-attention based message passing neural network for predicting molecular lipophilicity and aqueous solubility

MPN and SAMPNHyperparametersRange (interval)
 Activation functionTanh, ELU, LeakyReLU ReLU, PReLU, SELU
 Steps of message passing2–6 (1)
 Graph embedding size32–512 (32)
 Dropout rate0.0–0.4 (0.05)
 Layers of fully connected network1–3 (1)