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

Network community detection often relies on optimizing partition qualityfunctions, like modularity. This optimization appears to be a complex problemtraditionally relying on discrete heuristics. And although the problem could bereformulated as continuous optimization, direct application of the standardoptimization methods has limited efficiency in overcoming the numerous localextrema. However, the rise of deep learning and its applications to graphsoffers new opportunities. And while graph neural networks have been used forsupervised and unsupervised learning on networks, their application tomodularity optimization has not been explored yet. This paper proposes a newvariant of the recurrent graph neural network algorithm for unsupervisednetwork community detection through modularity optimization. The newalgorithm's performance is compared against a popular and fast Louvain methodand a more efficient but slower Combo algorithm recently proposed by theauthor. The approach also serves as a proof-of-concept for the broaderapplication of recurrent graph neural networks to unsupervised networkoptimization.

Recurrent Graph Neural Network Algorithm for Unsupervised Network Community Detection