Heterogeneous graph representation learning method based on common attention

The invention provides a heterogeneous graph representation learning method based on common attention, and the method comprises the steps: determining a local attention score of a neighbor node of a target element path based on a preset attention parameter vector, a first hidden feature vector, a se...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	NAI YUANKUN, ZHANG ZHENG, SHEN JIACHEN, CAI MING, TAO ZHENYU, JI YINGSHENG
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page
container_issue
container_start_page
container_title
container_volume
creator	NAI YUANKUN ZHANG ZHENG SHEN JIACHEN CAI MING TAO ZHENYU JI YINGSHENG
description	The invention provides a heterogeneous graph representation learning method based on common attention, and the method comprises the steps: determining a local attention score of a neighbor node of a target element path based on a preset attention parameter vector, a first hidden feature vector, a second hidden feature vector and a semantic fusion vector of the target element path; determining a global attention score of the neighbor node of the target meta-path based on the local attention score, the number of other meta-paths corresponding to the neighbor node of the target meta-path and a preset hyper-parameter; determining an updated semantic representation vector of the target node based on the global attention score, the first hidden feature vector, the second hidden feature vector and the semantic fusion vector; and determining the attention weight of each target element path based on the updated semantic representation vector of the node in each target element path in the heterogeneous graph, and deter
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116340842A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116340842A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116340842A3</originalsourceid><addsrcrecordid>eNrjZPDxSC1JLcpPT81LzS8tVkgvSizIUChKLShKLU7NK0ksyczPU8hJTSzKy8xLV8hNLcnIT1FISixOTVEASiTn5-YCqcSSEqBaoEoeBta0xJziVF4ozc2g6OYa4uyhm1qQH59aXJCYDLSmJN7Zz9DQzNjEwMLEyNGYGDUADEU2mw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Heterogeneous graph representation learning method based on common attention</title><source>esp@cenet</source><creator>NAI YUANKUN ; ZHANG ZHENG ; SHEN JIACHEN ; CAI MING ; TAO ZHENYU ; JI YINGSHENG</creator><creatorcontrib>NAI YUANKUN ; ZHANG ZHENG ; SHEN JIACHEN ; CAI MING ; TAO ZHENYU ; JI YINGSHENG</creatorcontrib><description>The invention provides a heterogeneous graph representation learning method based on common attention, and the method comprises the steps: determining a local attention score of a neighbor node of a target element path based on a preset attention parameter vector, a first hidden feature vector, a second hidden feature vector and a semantic fusion vector of the target element path; determining a global attention score of the neighbor node of the target meta-path based on the local attention score, the number of other meta-paths corresponding to the neighbor node of the target meta-path and a preset hyper-parameter; determining an updated semantic representation vector of the target node based on the global attention score, the first hidden feature vector, the second hidden feature vector and the semantic fusion vector; and determining the attention weight of each target element path based on the updated semantic representation vector of the node in each target element path in the heterogeneous graph, and deter</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2023</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230627&DB=EPODOC&CC=CN&NR=116340842A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76419</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230627&DB=EPODOC&CC=CN&NR=116340842A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>NAI YUANKUN</creatorcontrib><creatorcontrib>ZHANG ZHENG</creatorcontrib><creatorcontrib>SHEN JIACHEN</creatorcontrib><creatorcontrib>CAI MING</creatorcontrib><creatorcontrib>TAO ZHENYU</creatorcontrib><creatorcontrib>JI YINGSHENG</creatorcontrib><title>Heterogeneous graph representation learning method based on common attention</title><description>The invention provides a heterogeneous graph representation learning method based on common attention, and the method comprises the steps: determining a local attention score of a neighbor node of a target element path based on a preset attention parameter vector, a first hidden feature vector, a second hidden feature vector and a semantic fusion vector of the target element path; determining a global attention score of the neighbor node of the target meta-path based on the local attention score, the number of other meta-paths corresponding to the neighbor node of the target meta-path and a preset hyper-parameter; determining an updated semantic representation vector of the target node based on the global attention score, the first hidden feature vector, the second hidden feature vector and the semantic fusion vector; and determining the attention weight of each target element path based on the updated semantic representation vector of the node in each target element path in the heterogeneous graph, and deter</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPDxSC1JLcpPT81LzS8tVkgvSizIUChKLShKLU7NK0ksyczPU8hJTSzKy8xLV8hNLcnIT1FISixOTVEASiTn5-YCqcSSEqBaoEoeBta0xJziVF4ozc2g6OYa4uyhm1qQH59aXJCYDLSmJN7Zz9DQzNjEwMLEyNGYGDUADEU2mw</recordid><startdate>20230627</startdate><enddate>20230627</enddate><creator>NAI YUANKUN</creator><creator>ZHANG ZHENG</creator><creator>SHEN JIACHEN</creator><creator>CAI MING</creator><creator>TAO ZHENYU</creator><creator>JI YINGSHENG</creator><scope>EVB</scope></search><sort><creationdate>20230627</creationdate><title>Heterogeneous graph representation learning method based on common attention</title><author>NAI YUANKUN ; ZHANG ZHENG ; SHEN JIACHEN ; CAI MING ; TAO ZHENYU ; JI YINGSHENG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116340842A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>NAI YUANKUN</creatorcontrib><creatorcontrib>ZHANG ZHENG</creatorcontrib><creatorcontrib>SHEN JIACHEN</creatorcontrib><creatorcontrib>CAI MING</creatorcontrib><creatorcontrib>TAO ZHENYU</creatorcontrib><creatorcontrib>JI YINGSHENG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>NAI YUANKUN</au><au>ZHANG ZHENG</au><au>SHEN JIACHEN</au><au>CAI MING</au><au>TAO ZHENYU</au><au>JI YINGSHENG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Heterogeneous graph representation learning method based on common attention</title><date>2023-06-27</date><risdate>2023</risdate><abstract>The invention provides a heterogeneous graph representation learning method based on common attention, and the method comprises the steps: determining a local attention score of a neighbor node of a target element path based on a preset attention parameter vector, a first hidden feature vector, a second hidden feature vector and a semantic fusion vector of the target element path; determining a global attention score of the neighbor node of the target meta-path based on the local attention score, the number of other meta-paths corresponding to the neighbor node of the target meta-path and a preset hyper-parameter; determining an updated semantic representation vector of the target node based on the global attention score, the first hidden feature vector, the second hidden feature vector and the semantic fusion vector; and determining the attention weight of each target element path based on the updated semantic representation vector of the node in each target element path in the heterogeneous graph, and deter</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	chi ; eng
recordid	cdi_epo_espacenet_CN116340842A
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS
title	Heterogeneous graph representation learning method based on common attention
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T15%3A48%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=NAI%20YUANKUN&rft.date=2023-06-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116340842A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true