Papers › Mutual Teaching for Graph Convolutional Networks
Mutual Teaching for Graph Convolutional Networks
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. We propose a new training method named as mutual teaching, i.e., we train dual models and let them teach each other during each batch. First, each network feeds forward all samples and selects samples with high-confidence predictions. Second, each model is updated by samples selected by its peer network. We view the high-confidence predictions as useful knowledge, and the useful knowledge of one network teaches the peer network with model updating in each batch. In mutual teaching, the pseudo-label set of a network is from its peer network. Since we use the new strategy of network training, performance improves significantly. Extensive experimental results demonstrate that our method achieves superior performance over state-of-the-art methods under very low label rates.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Node Classification | CiteSeer (0.5%) | MT-GCN | Accuracy | 67.7% | #1 of 14 | Archive leaderboard | report |
| Node Classification | CiteSeer (1%) | MT-GCN | Accuracy | 68.9% | #3 of 14 | Archive leaderboard | report |
| Node Classification | Cora | MT-GCN | Accuracy | 80.9% | #63 of 73 | Archive leaderboard | report |
| Node Classification | Cora (0.5%) | MT-GCN | Accuracy | 66.9% | #7 of 15 | Archive leaderboard | report |
| Node Classification | Cora (1%) | MT-GCN | Accuracy | 73.1% | #7 of 15 | Archive leaderboard | report |
| Node Classification | Cora (3%) | MT-GCN | Accuracy | 78.5% | #7 of 15 | Archive leaderboard | report |
| Node Classification | PubMed (0.03%) | MT-GCN | Accuracy | 65.5% | #4 of 14 | Archive leaderboard | report |
| Node Classification | PubMed (0.05%) | MT-GCN | Accuracy | 69.5% | #4 of 14 | Archive leaderboard | report |
| Node Classification | PubMed (0.1%) | MT-GCN | Accuracy | 73.1% | #8 of 14 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections