Mutual Teaching for Graph Convolutional Networks

2 Sep 2020 Kun Zhan Chaoxi Niu

Graph convolutional networks produce good predictions of unlabeled samples due to its transductive label propagation. Since samples have different predicted confidences, we take high-confidence predictions as pseudo labels to expand the label set so that more samples are selected for updating models... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Node Classification CiteSeer (0.5%) MT-GCN Accuracy 67.7% # 1
Node Classification CiteSeer (1%) MT-GCN Accuracy 68.9% # 2
Node Classification Cora MT-GCN Accuracy 80.9% # 44
Node Classification Cora (0.5%) MT-GCN Accuracy 66.9% # 5
Node Classification Cora (1%) MT-GCN Accuracy 73.1% # 4
Node Classification Cora (3%) MT-GCN Accuracy 78.5% # 5
Node Classification PubMed (0.03%) MT-GCN Accuracy 65.5% # 3
Node Classification PubMed (0.05%) MT-GCN Accuracy 69.5% # 3
Node Classification PubMed (0.1%) MT-GCN Accuracy 73.1% # 6

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet