Discovering latent node Information by graph attention network

Abstract In this paper, we propose graph attention based network representation (GANR) which utilizes the graph attention architecture and takes graph structure as the supervised learning information. Compared with node classification based representations, GANR can be used to learn representation f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Weiwei Gu, Fei Gao, Xiaodan Lou, Jiang Zhang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/6cc8b7d1e7ee475e8834cc197515f5ee
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6cc8b7d1e7ee475e8834cc197515f5ee
record_format	dspace
spelling	oai:doaj.org-article:6cc8b7d1e7ee475e8834cc197515f5ee2021-12-02T17:04:06ZDiscovering latent node Information by graph attention network10.1038/s41598-021-85826-x2045-2322https://doaj.org/article/6cc8b7d1e7ee475e8834cc197515f5ee2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85826-xhttps://doaj.org/toc/2045-2322Abstract In this paper, we propose graph attention based network representation (GANR) which utilizes the graph attention architecture and takes graph structure as the supervised learning information. Compared with node classification based representations, GANR can be used to learn representation for any given graph. GANR is not only capable of learning high quality node representations that achieve a competitive performance on link prediction, network visualization and node classification but it can also extract meaningful attention weights that can be applied in node centrality measuring task. GANR can identify the leading venture capital investors, discover highly cited papers and find the most influential nodes in Susceptible Infected Recovered Model. We conclude that link structures in graphs are not limited on predicting linkage itself, it is capable of revealing latent node information in an unsupervised way once a appropriate learning algorithm, like GANR, is provided.Weiwei GuFei GaoXiaodan LouJiang ZhangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Weiwei Gu Fei Gao Xiaodan Lou Jiang Zhang Discovering latent node Information by graph attention network
description	Abstract In this paper, we propose graph attention based network representation (GANR) which utilizes the graph attention architecture and takes graph structure as the supervised learning information. Compared with node classification based representations, GANR can be used to learn representation for any given graph. GANR is not only capable of learning high quality node representations that achieve a competitive performance on link prediction, network visualization and node classification but it can also extract meaningful attention weights that can be applied in node centrality measuring task. GANR can identify the leading venture capital investors, discover highly cited papers and find the most influential nodes in Susceptible Infected Recovered Model. We conclude that link structures in graphs are not limited on predicting linkage itself, it is capable of revealing latent node information in an unsupervised way once a appropriate learning algorithm, like GANR, is provided.
format	article
author	Weiwei Gu Fei Gao Xiaodan Lou Jiang Zhang
author_facet	Weiwei Gu Fei Gao Xiaodan Lou Jiang Zhang
author_sort	Weiwei Gu
title	Discovering latent node Information by graph attention network
title_short	Discovering latent node Information by graph attention network
title_full	Discovering latent node Information by graph attention network
title_fullStr	Discovering latent node Information by graph attention network
title_full_unstemmed	Discovering latent node Information by graph attention network
title_sort	discovering latent node information by graph attention network
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/6cc8b7d1e7ee475e8834cc197515f5ee
work_keys_str_mv	AT weiweigu discoveringlatentnodeinformationbygraphattentionnetwork AT feigao discoveringlatentnodeinformationbygraphattentionnetwork AT xiaodanlou discoveringlatentnodeinformationbygraphattentionnetwork AT jiangzhang discoveringlatentnodeinformationbygraphattentionnetwork
_version_	1718381854573199360

Discovering latent node Information by graph attention network

Ejemplares similares