Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning

Benchmark Model Rank Results
node-classification-on-cora-fixed-20-node-per-classSEGCN#4Accuracy: 83.5 ± 0.4
node-classification-on-citeseer-with-public-split-fixed-20-nodes-per-classSEGCN#15Accuracy: 73.4 ± 0.7
node-classification-on-pubmed-with-public-split-fixed-20-nodes-per-classSEGCN#28Accuracy: 78.9 ± 0.7
node-classification-on-coraSEGCN#30Accuracy: 83.5% ± 0.4%