English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Graph Convolutional Networks(GCNs) play a crucial role in graph learningtasks, however, learning graph embedding with few supervised signals is still adifficult problem. In this paper, we propose a novel training algorithm forGraph Convolutional Network, called Multi-Stage Self-Supervised(M3S) TrainingAlgorithm, combined with self-supervised learning approach, focusing onimproving the generalization performance of GCNs on graphs with few labelednodes. Firstly, a Multi-Stage Training Framework is provided as the basis ofM3S training method. Then we leverage DeepCluster technique, a popular form ofself-supervised learning, and design corresponding aligning mechanism on theembedding space to refine the Multi-Stage Training Framework, resulting in M3STraining Algorithm. Finally, extensive experimental results verify the superiorperformance of our algorithm on graphs with few labeled nodes under differentlabel rates compared with other state-of-the-art approaches.

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