Papers › Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
Qimai Li, Zhichao Han, Xiao-Ming Wu
Many interesting problems in machine learning are being revisited with new deep learning tools. For graph-based semisupervised learning, a recent important development is graph convolutional networks (GCNs), which nicely integrate local vertex features and graph topology in the convolutional layers. Although the GCN model compares favorably with other state-of-the-art methods, its mechanisms are not clear and it still requires a considerable amount of labeled data for validation and model selection. In this paper, we develop deeper insights into the GCN model and address its fundamental limits. First, we show that the graph convolution of the GCN model is actually a special form of Laplacian smoothing, which is the key reason why GCNs work, but it also brings potential concerns of over-smoothing with many convolutional layers. Second, to overcome the limits of the GCN model with shallow architectures, we propose both co-training and self-training approaches to train GCNs. Our approaches significantly improve GCNs in learning with very few labels, and exempt them from requiring additional labels for validation. Extensive experiments on benchmarks have verified our theory and proposals.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 | Brazil Air-Traffic | Union (Li et al., 2018) | Accuracy | 0.466 | #4 of 7 | Archive leaderboard | report |
| Node Classification | Brazil Air-Traffic | Intersection (Li et al., 2018) | Accuracy | 0.459 | #5 of 7 | Archive leaderboard | report |
| Node Classification | Europe Air-Traffic | Intersection (Li et al., 2018) | Accuracy | 44.3 | #4 of 7 | Archive leaderboard | report |
| Node Classification | Intersection (Li et al., 2018) | Accuracy | 59.8 | #6 of 8 | Archive leaderboard | report | |
| Node Classification | Flickr | Intersection (Li et al., 2018) | Accuracy | 0.557 | #5 of 8 | Archive leaderboard | report |
| Node Classification | USA Air-Traffic | Union (Li et al., 2018) | Accuracy | 58.2 | #5 of 7 | Archive leaderboard | report |
| Node Classification | USA Air-Traffic | Intersection (Li et al., 2018) | Accuracy | 57.3 | #6 of 7 | Archive leaderboard | report |
| Node Classification | Wiki-Vote | Union (Li et al., 2018) | Accuracy | 46.3 | #4 of 6 | 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