Papers › From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited
From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited
Zheng Wang, Hongming Ding, Li Pan, Jianhua Li, Zhiguo Gong, Philip S. Yu
Graph-based semi-supervised learning (GSSL) has long been a hot research topic. Traditional methods are generally shallow learners, based on the cluster assumption. Recently, graph convolutional networks (GCNs) have become the predominant techniques for their promising performance. In this paper, we theoretically discuss the relationship between these two types of methods in a unified optimization framework. One of the most intriguing findings is that, unlike traditional ones, typical GCNs may not jointly consider the graph structure and label information at each layer. Motivated by this, we further propose three simple but powerful graph convolution methods. The first is a supervised method OGC which guides the graph convolution process with labels. The others are two unsupervised methods: GGC and its multi-scale version GGCM, both aiming to preserve the graph structure information during the convolution process. Finally, we conduct extensive experiments to show the effectiveness of our methods.
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 | CiteSeer with Public Split: fixed 20 nodes per class | OGC | Accuracy | 77.5 | #1 of 40 | Archive leaderboard | report |
| Node Classification | CiteSeer with Public Split: fixed 20 nodes per class | GGCM | Accuracy | 74.2 | #10 of 40 | Archive leaderboard | report |
| Node Classification | Cora with Public Split: fixed 20 nodes per class | OGC | Accuracy | 86.9% | #1 of 36 | Archive leaderboard | report |
| Node Classification | Cora with Public Split: fixed 20 nodes per class | GGCM | Accuracy | 83.6% | #17 of 36 | Archive leaderboard | report |
| Node Classification | PubMed with Public Split: fixed 20 nodes per class | OGC | Accuracy | 83.4% | #1 of 37 | Archive leaderboard | report |
| Node Classification | PubMed with Public Split: fixed 20 nodes per class | GGCM | Accuracy | 80.8% | #11 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