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) are widely used in many applications yetstill need large amounts of labelled data for training. Besides, the adjacencymatrix of GCNs is stable, which makes the data processing strategy cannotefficiently adjust the quantity of training data from the built graphstructures.To further improve the performance and the self-learning ability ofGCNs,in this paper, we propose an efficient self-supervised learning strategyof GCNs,named randomly removed links with a fixed step at one region(RRLFSOR).RRLFSOR can be regarded as a new data augmenter to improveover-smoothing.RRLFSOR is examined on two efficient and representative GCNmodels with three public citation network datasets-Cora,PubMed,andCiteseer.Experiments on transductive link prediction tasks show that ourstrategy outperforms the baseline models consistently by up to 21.34% in termsof accuracy on three benchmark datasets.

RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks