Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification

Graph convolutional network (GCN) is an efficient network for learning graph representations. However, it costs expensive to learn the high-order interaction relationships of the node neighbor. In this paper, we propose a novel graph convolutional model to learn and fuse multihop neighbor informatio...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Mathematical problems in engineering 2021, Vol.2021, p.1-9
Hauptverfasser: Lei, Fangyuan, Liu, Xun, Li, Zhengming, Dai, Qingyun, Wang, Senhong
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 9
container_issue
container_start_page 1
container_title Mathematical problems in engineering
container_volume 2021
creator Lei, Fangyuan
Liu, Xun
Li, Zhengming
Dai, Qingyun
Wang, Senhong
description Graph convolutional network (GCN) is an efficient network for learning graph representations. However, it costs expensive to learn the high-order interaction relationships of the node neighbor. In this paper, we propose a novel graph convolutional model to learn and fuse multihop neighbor information relationships. We adopt the weight-sharing mechanism to design different order graph convolutions for avoiding the potential concerns of overfitting. Moreover, we design a new multihop neighbor information fusion (MIF) operator which mixes different neighbor features from 1-hop to k-hops. We theoretically analyse the computational complexity and the number of trainable parameters of our models. Experiment on text networks shows that the proposed models achieve state-of-the-art performance than the text GCN.
doi_str_mv 10.1155/2021/6665588
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2527980903</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2527980903</sourcerecordid><originalsourceid>FETCH-LOGICAL-c337t-6df94cb59c2e3e467741868170d7175e81fe425cd03d546cde9c7b263caa49953</originalsourceid><addsrcrecordid>eNp90D1PwzAQBmALgUQpbPyASIwQ6m_HI4poqVRgKVK3yHEc4pLGwU4o_HsS2pnpTrrnTqcXgGsE7xFibIYhRjPOOWNJcgImiHESM0TF6dBDTGOEyeYcXISwhYNkKJmAzXNfd7ZybfRi7HuVOx8tm9L5neqsa6J5H8ay8KqtotQ1X67ux4GqB9_tnf-IBhytzXcXpbUKwZZW_61egrNS1cFcHesUvM0f1-lTvHpdLNOHVawJEV3Mi1JSnTOpsSGGciEoSniCBCwEEswkqDQUM11AUjDKdWGkFjnmRCtFpWRkCm4Od1vvPnsTumzrej88GDLMsJAJlJAM6u6gtHcheFNmrbc75X8yBLMxu2zMLjtmN_DbA69sU6i9_V__Anuibn0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2527980903</pqid></control><display><type>article</type><title>Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification</title><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>Wiley Online Library (Open Access Collection)</source><source>Alma/SFX Local Collection</source><creator>Lei, Fangyuan ; Liu, Xun ; Li, Zhengming ; Dai, Qingyun ; Wang, Senhong</creator><contributor>Semaničová-Feňovčíková, Andrea ; Andrea Semaničová-Feňovčíková</contributor><creatorcontrib>Lei, Fangyuan ; Liu, Xun ; Li, Zhengming ; Dai, Qingyun ; Wang, Senhong ; Semaničová-Feňovčíková, Andrea ; Andrea Semaničová-Feňovčíková</creatorcontrib><description>Graph convolutional network (GCN) is an efficient network for learning graph representations. However, it costs expensive to learn the high-order interaction relationships of the node neighbor. In this paper, we propose a novel graph convolutional model to learn and fuse multihop neighbor information relationships. We adopt the weight-sharing mechanism to design different order graph convolutions for avoiding the potential concerns of overfitting. Moreover, we design a new multihop neighbor information fusion (MIF) operator which mixes different neighbor features from 1-hop to k-hops. We theoretically analyse the computational complexity and the number of trainable parameters of our models. Experiment on text networks shows that the proposed models achieve state-of-the-art performance than the text GCN.</description><identifier>ISSN: 1024-123X</identifier><identifier>EISSN: 1563-5147</identifier><identifier>DOI: 10.1155/2021/6665588</identifier><language>eng</language><publisher>New York: Hindawi</publisher><subject>Artificial neural networks ; Classification ; Data integration ; Deep learning ; Graphical representations ; Mathematical problems ; Neural networks ; Propagation ; Text categorization</subject><ispartof>Mathematical problems in engineering, 2021, Vol.2021, p.1-9</ispartof><rights>Copyright © 2021 Fangyuan Lei et al.</rights><rights>Copyright © 2021 Fangyuan Lei et al. This is an open access article distributed under the Creative Commons Attribution License (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. https://creativecommons.org/licenses/by/4.0</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c337t-6df94cb59c2e3e467741868170d7175e81fe425cd03d546cde9c7b263caa49953</citedby><cites>FETCH-LOGICAL-c337t-6df94cb59c2e3e467741868170d7175e81fe425cd03d546cde9c7b263caa49953</cites><orcidid>0000-0002-7561-3704 ; 0000-0003-0368-7971 ; 0000-0002-7062-3233 ; 0000-0002-2059-8818 ; 0000-0001-7330-8864</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,4024,27923,27924,27925</link.rule.ids></links><search><contributor>Semaničová-Feňovčíková, Andrea</contributor><contributor>Andrea Semaničová-Feňovčíková</contributor><creatorcontrib>Lei, Fangyuan</creatorcontrib><creatorcontrib>Liu, Xun</creatorcontrib><creatorcontrib>Li, Zhengming</creatorcontrib><creatorcontrib>Dai, Qingyun</creatorcontrib><creatorcontrib>Wang, Senhong</creatorcontrib><title>Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification</title><title>Mathematical problems in engineering</title><description>Graph convolutional network (GCN) is an efficient network for learning graph representations. However, it costs expensive to learn the high-order interaction relationships of the node neighbor. In this paper, we propose a novel graph convolutional model to learn and fuse multihop neighbor information relationships. We adopt the weight-sharing mechanism to design different order graph convolutions for avoiding the potential concerns of overfitting. Moreover, we design a new multihop neighbor information fusion (MIF) operator which mixes different neighbor features from 1-hop to k-hops. We theoretically analyse the computational complexity and the number of trainable parameters of our models. Experiment on text networks shows that the proposed models achieve state-of-the-art performance than the text GCN.</description><subject>Artificial neural networks</subject><subject>Classification</subject><subject>Data integration</subject><subject>Deep learning</subject><subject>Graphical representations</subject><subject>Mathematical problems</subject><subject>Neural networks</subject><subject>Propagation</subject><subject>Text categorization</subject><issn>1024-123X</issn><issn>1563-5147</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>RHX</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp90D1PwzAQBmALgUQpbPyASIwQ6m_HI4poqVRgKVK3yHEc4pLGwU4o_HsS2pnpTrrnTqcXgGsE7xFibIYhRjPOOWNJcgImiHESM0TF6dBDTGOEyeYcXISwhYNkKJmAzXNfd7ZybfRi7HuVOx8tm9L5neqsa6J5H8ay8KqtotQ1X67ux4GqB9_tnf-IBhytzXcXpbUKwZZW_61egrNS1cFcHesUvM0f1-lTvHpdLNOHVawJEV3Mi1JSnTOpsSGGciEoSniCBCwEEswkqDQUM11AUjDKdWGkFjnmRCtFpWRkCm4Od1vvPnsTumzrej88GDLMsJAJlJAM6u6gtHcheFNmrbc75X8yBLMxu2zMLjtmN_DbA69sU6i9_V__Anuibn0</recordid><startdate>2021</startdate><enddate>2021</enddate><creator>Lei, Fangyuan</creator><creator>Liu, Xun</creator><creator>Li, Zhengming</creator><creator>Dai, Qingyun</creator><creator>Wang, Senhong</creator><general>Hindawi</general><general>Hindawi Limited</general><scope>RHU</scope><scope>RHW</scope><scope>RHX</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7TB</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>CWDGH</scope><scope>DWQXO</scope><scope>FR3</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>KR7</scope><scope>L6V</scope><scope>M7S</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><orcidid>https://orcid.org/0000-0002-7561-3704</orcidid><orcidid>https://orcid.org/0000-0003-0368-7971</orcidid><orcidid>https://orcid.org/0000-0002-7062-3233</orcidid><orcidid>https://orcid.org/0000-0002-2059-8818</orcidid><orcidid>https://orcid.org/0000-0001-7330-8864</orcidid></search><sort><creationdate>2021</creationdate><title>Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification</title><author>Lei, Fangyuan ; Liu, Xun ; Li, Zhengming ; Dai, Qingyun ; Wang, Senhong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c337t-6df94cb59c2e3e467741868170d7175e81fe425cd03d546cde9c7b263caa49953</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Artificial neural networks</topic><topic>Classification</topic><topic>Data integration</topic><topic>Deep learning</topic><topic>Graphical representations</topic><topic>Mathematical problems</topic><topic>Neural networks</topic><topic>Propagation</topic><topic>Text categorization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lei, Fangyuan</creatorcontrib><creatorcontrib>Liu, Xun</creatorcontrib><creatorcontrib>Li, Zhengming</creatorcontrib><creatorcontrib>Dai, Qingyun</creatorcontrib><creatorcontrib>Wang, Senhong</creatorcontrib><collection>Hindawi Publishing Complete</collection><collection>Hindawi Publishing Subscription Journals</collection><collection>Hindawi Publishing Open Access Journals</collection><collection>CrossRef</collection><collection>Mechanical &amp; Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>Middle East &amp; Africa Database</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>Civil Engineering Abstracts</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><jtitle>Mathematical problems in engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lei, Fangyuan</au><au>Liu, Xun</au><au>Li, Zhengming</au><au>Dai, Qingyun</au><au>Wang, Senhong</au><au>Semaničová-Feňovčíková, Andrea</au><au>Andrea Semaničová-Feňovčíková</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification</atitle><jtitle>Mathematical problems in engineering</jtitle><date>2021</date><risdate>2021</risdate><volume>2021</volume><spage>1</spage><epage>9</epage><pages>1-9</pages><issn>1024-123X</issn><eissn>1563-5147</eissn><abstract>Graph convolutional network (GCN) is an efficient network for learning graph representations. However, it costs expensive to learn the high-order interaction relationships of the node neighbor. In this paper, we propose a novel graph convolutional model to learn and fuse multihop neighbor information relationships. We adopt the weight-sharing mechanism to design different order graph convolutions for avoiding the potential concerns of overfitting. Moreover, we design a new multihop neighbor information fusion (MIF) operator which mixes different neighbor features from 1-hop to k-hops. We theoretically analyse the computational complexity and the number of trainable parameters of our models. Experiment on text networks shows that the proposed models achieve state-of-the-art performance than the text GCN.</abstract><cop>New York</cop><pub>Hindawi</pub><doi>10.1155/2021/6665588</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0002-7561-3704</orcidid><orcidid>https://orcid.org/0000-0003-0368-7971</orcidid><orcidid>https://orcid.org/0000-0002-7062-3233</orcidid><orcidid>https://orcid.org/0000-0002-2059-8818</orcidid><orcidid>https://orcid.org/0000-0001-7330-8864</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1024-123X
ispartof Mathematical problems in engineering, 2021, Vol.2021, p.1-9
issn 1024-123X
1563-5147
language eng
recordid cdi_proquest_journals_2527980903
source Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; Wiley Online Library (Open Access Collection); Alma/SFX Local Collection
subjects Artificial neural networks
Classification
Data integration
Deep learning
Graphical representations
Mathematical problems
Neural networks
Propagation
Text categorization
title Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T13%3A34%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multihop%20Neighbor%20Information%20Fusion%20Graph%20Convolutional%20Network%20for%20Text%20Classification&rft.jtitle=Mathematical%20problems%20in%20engineering&rft.au=Lei,%20Fangyuan&rft.date=2021&rft.volume=2021&rft.spage=1&rft.epage=9&rft.pages=1-9&rft.issn=1024-123X&rft.eissn=1563-5147&rft_id=info:doi/10.1155/2021/6665588&rft_dat=%3Cproquest_cross%3E2527980903%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2527980903&rft_id=info:pmid/&rfr_iscdi=true