Table 3 Hyper-parameters for different graph neural network variants used in our experiments
From: GPDRP: a multimodal framework for drug response prediction with graph transformer
Hyper-parameters | Setting |
|---|---|
Activation | ReLu |
Optimizer | Adam |
Learning rate | 0.0001 |
Dropout | 0.2 |
GCN Layers | 3 |
GAT Layers | 3 |
GIN Layers | 3 |
GIN_TRANSFORMER Layers | 3 |
DNN Layers | 3 |