Skip to main content

Table 6 Performance metrics of different models with different datasets [33, 47, 48]

From: A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions

Dataset

Model

GCN

GAT

GraphSAGE

GraphSAGE-Simple

GraphSAGE—Mean

GraphSAGE—LSTM

GraphSAGE—Pooling

CORA

81.5 (4 s)

83

76.8

78.7

79.7

80.7

Citeseer

70.3 (7 s)

72.5

74.2

77.8

78.8

79.8

Pubmed

79.0 (38 s)

79

   Â