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

Applying graph-based approaches in deep learning receives more attention overtime. This study presents statistical analysis on the use of graph-basedapproaches in deep learning and examines the scientific impact of the relatedarticles. Processing the data obtained from the Web of Science database,metrics such as the type of the articles, funding availability, indexing type,annual average number of citations and the number of access were analyzed toquantitatively reveal the effects on the scientific audience. It's outlinedthat deep learning-based studies gained momentum after year 2013, and the rateof graph-based approaches in all deep learning studies increased linearly from1% to 4% within the following 10 years. Conference publications scanned in theConference Proceeding Citation Index (CPCI) on the graph-based approachesreceive significantly more citations. The citation counts of the SCI-Expandedand Emerging SCI indexed publications of the two streams are close to eachother. While the citation performances of the supported and unsupportedpublications of the two sides were similar, pure deep learning studies receivedmore citations on the journal publication side and graph-based approachesreceived more citations on the conference side. Despite their similarperformance in recent years, graph-based studies show twice more citationperformance as they get older, compared to traditional approaches. Annualaverage citation performance per article for all deep learning studies is11.051 in 2014, while it is 22.483 for graph-based studies. Also, despitereceiving 16% more access, graph-based papers get almost the same overallcitation over time with the pure counterpart. This is an indication thatgraph-based approaches need a greater bunch of attention to follow, while puredeep learning counterpart is relatively simpler to get inside.

Scientific Impact of Graph-Based Approaches in Deep Learning Studies -- A Bibliometric Comparison