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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Graph-based semi-supervised learning has been shown to be one of the mosteffective approaches for classification tasks from a wide range of domains,such as image classification and text classification, as they can exploit theconnectivity patterns between labeled and unlabeled samples to improve learningperformance. In this work, we advance this effective learning paradigm towardsa scenario where labeled data are severely limited. More specifically, weaddress the problem of graph-based semi-supervised learning in the presence ofseverely limited labeled samples, and propose a new framework, called {\emShoestring}, that improves the learning performance through semantic transferfrom these very few labeled samples to large numbers of unlabeled samples.  In particular, our framework learns a metric space in which classificationcan be performed by computing the similarity to centroid embedding of eachclass. {\em Shoestring} is trained in an end-to-end fashion to learn toleverage the semantic knowledge of limited labeled samples as well as theirconnectivity patterns with large numbers of unlabeled samples simultaneously.By combining {\em Shoestring} with graph convolutional networks, labelpropagation and their recent label-efficient variations (IGCN and GLP), we areable to achieve state-of-the-art node classification performance in thepresence of very few labeled samples. In addition, we demonstrate theeffectiveness of our framework on image classification tasks in the few-shotlearning regime, with significant gains on miniImageNet ($2.57\%\sim3.59\%$)and tieredImageNet ($1.05\%\sim2.70\%$).

Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled Data