Skip to main content

Table 4 Chosen hyperparameters for GAT model

From: The interplay between communities and homophily in semi-supervised classification using graph neural networks

Dataset Dropout Learning rate Regularization weight Heads Attention dropout
CORA-ML 0.4 0.01 0.0100 4 0.2
Citeseer 0.4 0.01 0.0100 4 0.2
Pubmed 0.2 0.01 0.0001 8 0.3
CORA-Full 0.2 0.01 0.0001 8 0.3
Actor 0.4 0.01 0.0100 4 0.3
Squirrel 0.4 0.01 0.0001 2 0.2
Texas 0.4 0.01 0.0100 4 0.3
Wisconsin 0.4 0.01 0.0100 4 0.3