AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes

Ke Sun, Zhouchen Lin, Zhanxing Zhu

AAAI 2020 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 284 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add DeepCluster-based cluster alignment and self-checking to MultiStage training (ablation)GCN node classification · Cora, CiteSeer, and PubMed at reported label ratesaccuracy: Cora: MultiStage 61.1, 63.7, 74.4, 76.1, 77.2; M3S 61.5, 67.2, 75.6, 77.8, 78.0. CiteSeer: MultiStage 53.0, 57.8, 63.8, Improved
Repeat confident pseudo-label selection and training over multiple stages instead of one self-training pass (ablation)GCN self-training · Citation networks with few labeled nodesaccuracyImproved
Use more graph convolutional layers at lower label ratesGCN · Cora, CiteSeer, and PubMed at lower label ratesaccuracyImproved
Increase the number of DeepCluster clusters (ablation)M3S · Cora, CiteSeer, and PubMedaccuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy