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 clustering is a fundamental task which discovers communities or groupsin networks. Recent studies have mostly focused on developing deep learningapproaches to learn a compact graph embedding, upon which classic clusteringmethods like k-means or spectral clustering algorithms are applied. Thesetwo-step frameworks are difficult to manipulate and usually lead to suboptimalperformance, mainly because the graph embedding is not goal-directed, i.e.,designed for the specific clustering task. In this paper, we propose agoal-directed deep learning approach, Deep Attentional Embedded GraphClustering (DAEGC for short). Our method focuses on attributed graphs tosufficiently explore the two sides of information in graphs. By employing anattention network to capture the importance of the neighboring nodes to atarget node, our DAEGC algorithm encodes the topological structure and nodecontent in a graph to a compact representation, on which an inner productdecoder is trained to reconstruct the graph structure. Furthermore, soft labelsfrom the graph embedding itself are generated to supervise a self-traininggraph clustering process, which iteratively refines the clustering results. Theself-training process is jointly learned and optimized with the graph embeddingin a unified framework, to mutually benefit both components. Experimentalresults compared with state-of-the-art algorithms demonstrate the superiorityof our method.

Attributed Graph Clustering: A Deep Attentional Embedding Approach