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

Most approaches that tackle the problem of node classification consider nodesto be similar, if they have shared neighbors or are close to each other in thegraph. Recent methods for attributed graphs additionally take attributes ofneighboring nodes into account. We argue that the class labels of the neighborsbear important information and considering them helps to improve classificationquality. Two nodes which are similar based on class labels in theirneighborhood do not need to be close-by in the graph and may even belong todifferent connected components. In this work, we propose a novel approach forthe semi-supervised node classification. Precisely, we propose a new nodeembedding which is based on the class labels in the local neighborhood of anode. We show that this is a different setting from attribute-based embeddingsand thus, we propose a new method to learn label-based node embeddings whichcan mirror a variety of relations between the class labels of neighboringnodes. Our experimental evaluation demonstrates that our new methods cansignificantly improve the prediction quality on real world data sets.

Semi-Supervised Learning on Graphs Based on Local Label Distributions