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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Graph representation learning is a fundamental task in various applicationsthat strives to learn low-dimensional embeddings for nodes that can preservegraph topology information. However, many existing methods focus on staticgraphs while ignoring evolving graph patterns. Inspired by the success of graphconvolutional networks(GCNs) in static graph embedding, we propose a novelk-core based temporal graph convolutional network, the CTGCN, to learn noderepresentations for dynamic graphs. In contrast to previous dynamic graphembedding methods, CTGCN can preserve both local connective proximity andglobal structural similarity while simultaneously capturing graph dynamics. Inthe proposed framework, the traditional graph convolution is generalized intotwo phases, feature transformation and feature aggregation, which gives theCTGCN more flexibility and enables the CTGCN to learn connective and structuralinformation under the same framework. Experimental results on 7 real-worldgraphs demonstrate that the CTGCN outperforms existing state-of-the-art graphembedding methods in several tasks, including link prediction and structuralrole classification. The source code of this work can be obtained from\url{https://github.com/jhljx/CTGCN}.

K-Core Based Temporal Graph Convolutional Network for Dynamic Graphs