Open dkhonker opened 4 weeks ago
The code (based on docs):
from deeprobust.graph.data import Dataset from deeprobust.graph.defense import GCN data = Dataset(root='/tmp/', name='pubmed') adj, features, labels = data.adj, data.features, data.labels idx_train, idx_val, idx_test = data.idx_train, data.idx_val, data.idx_test gcn = GCN(nfeat=features.shape[1], nhid=16, nclass=labels.max().item() + 1, dropout=0.5, device='cpu') gcn = gcn.to('cpu') gcn.fit(features, adj, labels, idx_train) # train without earlystopping gcn.fit(features, adj, labels, idx_train, idx_val, patience=30) # train with earlystopping gcn.test(idx_test)
And i get the test accuracy is ~86%.
But from paperswithcode and GCN paper, the accuracy of gcn is ~80%.
Do you know what caused this?
The code (based on docs):
And i get the test accuracy is ~86%.
But from paperswithcode and GCN paper, the accuracy of gcn is ~80%.
Do you know what caused this?