Papers › Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
Yawei Luo, Tao Guan, Junqing Yu, Ping Liu, Yi Yang
Graph convolutional network (GCN) provides a powerful means for graph-based semi-supervised tasks. However, as a localized first-order approximation of spectral graph convolution, the classic GCN can not take full advantage of unlabeled data, especially when the unlabeled node is far from labeled ones. To capitalize on the information from unlabeled nodes to boost the training for GCN, we propose a novel framework named Self-Ensembling GCN (SEGCN), which marries GCN with Mean Teacher - another powerful model in semi-supervised learning. SEGCN contains a student model and a teacher model. As a student, it not only learns to correctly classify the labeled nodes, but also tries to be consistent with the teacher on unlabeled nodes in more challenging situations, such as a high dropout rate and graph collapse. As a teacher, it averages the student model weights and generates more accurate predictions to lead the student. In such a mutual-promoting process, both labeled and unlabeled samples can be fully utilized for backpropagating effective gradients to train GCN. In three article classification tasks, i.e. Citeseer, Cora and Pubmed, we validate that the proposed method matches the state of the arts in the classification accuracy.
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 with Public Split: fixed 20 nodes per class | SEGCN | Accuracy | 73.4 ± 0.7 | #15 of 40 | Archive leaderboard | report |
| Node Classification | Cora | SEGCN | Accuracy | 83.5% ± 0.4% | #39 of 73 | Archive leaderboard | report |
| Node Classification | Cora: fixed 20 node per class | SEGCN | Accuracy | 83.5 ± 0.4 | #4 of 9 | Archive leaderboard | report |
| Node Classification | PubMed with Public Split: fixed 20 nodes per class | SEGCN | Accuracy | 78.9 ± 0.7 | #24 of 37 | 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.
Methods
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