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-based semi-supervised learning (GSSL) has long been a hot researchtopic. Traditional methods are generally shallow learners, based on the clusterassumption. Recently, graph convolutional networks (GCNs) have become thepredominant techniques for their promising performance. In this paper, wetheoretically discuss the relationship between these two types of methods in aunified optimization framework. One of the most intriguing findings is that,unlike traditional ones, typical GCNs may not jointly consider the graphstructure and label information at each layer. Motivated by this, we furtherpropose three simple but powerful graph convolution methods. The first is asupervised 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 convolutionprocess. Finally, we conduct extensive experiments to show the effectiveness ofour methods.

From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited