Papers › Multi-task Self-distillation for Graph-based Semi-Supervised Learning
Multi-task Self-distillation for Graph-based Semi-Supervised Learning
Yating Ren, Junzhong Ji, Lingfeng Niu, Minglong Lei
Graph convolutional networks have made great progress in graph-based semi-supervised learning. Existing methods mainly assume that nodes connected by graph edges are prone to have similar attributes and labels, so that the features smoothed by local graph structures can reveal the class similarities. However, there often exist mismatches between graph structures and labels in many real-world scenarios, where the structures may propagate misleading features or labels that eventually affect the model performance. In this paper, we propose a multi-task self-distillation framework that injects self-supervised learning and self-distillation into graph convolutional networks to separately address the mismatch problem from the structure side and the label side. First, we formulate a self-supervision pipeline based on pre-text tasks to capture different levels of similarities in graphs. The feature extraction process is encouraged to capture more complex proximity by jointly optimizing the pre-text task and the target task. Consequently, the local feature aggregations are improved from the structure side. Second, self-distillation uses soft labels of the model itself as additional supervision, which has similar effects as label smoothing. The knowledge from the classification pipeline and the self-supervision pipeline is collectively distilled to improve the generalization ability of the model from the label side. Experiment results show that the proposed method obtains remarkable performance gains under several classic graph convolutional architectures.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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 | AMZ Computers: fixed 20 node per class | SDSS-GCN | Accuracy | 84.86 | #1 of 1 | Archive leaderboard | report |
| Node Classification | Citeseer: fixed 20 node per class | SDSS-GAT | Accuracy | 76.35 | #1 of 2 | Archive leaderboard | report |
| Node Classification | Cora: fixed 20 nodes per class | SDSS-GCN | Accuracy | 86.00 | #1 of 1 | Archive leaderboard | report |
| Node Classification | Pubmed: fixed 20 node per class | SDSS-APPNP | Accuracy | 82.72 | #1 of 1 | 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