EDGE MESSAGE PASSING NEURAL NETWORK

EDGE MESSAGE PASSING NEURAL NETWORK

A method of generating graph data of an object is provided, the object is physical, audio object, text object or color object. The method can include: processing input graph data of at least one object with a graph convolution layer of an edge message passing neural network to obtain vector represen...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Leonov, Dmitry, Putin, Evgeny Olegovich, Zavoronkovs, Aleksandrs
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
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 Leonov, Dmitry
Putin, Evgeny Olegovich
Zavoronkovs, Aleksandrs
description A method of generating graph data of an object is provided, the object is physical, audio object, text object or color object. The method can include: processing input graph data of at least one object with a graph convolution layer of an edge message passing neural network to obtain vector representations of the node data and edge data of the graph data; processing the vector representations of the edge data and node data with a graph pooling layer of the edge message passing neural network that aggregates the vector representations of the node data and the vector representations of edge data to produce a vector representation of the input graph data; processing the vector representation of the input graph data with a multi-layer perception layer of the edge message passing neural network to generate predicted graph data of a predicted object; and reporting the predicted graph data in a report.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2021287067A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2021287067A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2021287067A13</originalsourceid><addsrcrecordid>eNrjZFB2dXF3VfB1DQ52BNIBjsHBnn7uCn6uoUGOPkAqJNw_yJuHgTUtMac4lRdKczMou7mGOHvophbkx6cWFyQmp-allsSHBhsZGBkaWZgbmJk7GhoTpwoA3fojpA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>EDGE MESSAGE PASSING NEURAL NETWORK</title><source>esp@cenet</source><creator>Leonov, Dmitry ; Putin, Evgeny Olegovich ; Zavoronkovs, Aleksandrs</creator><creatorcontrib>Leonov, Dmitry ; Putin, Evgeny Olegovich ; Zavoronkovs, Aleksandrs</creatorcontrib><description>A method of generating graph data of an object is provided, the object is physical, audio object, text object or color object. The method can include: processing input graph data of at least one object with a graph convolution layer of an edge message passing neural network to obtain vector representations of the node data and edge data of the graph data; processing the vector representations of the edge data and node data with a graph pooling layer of the edge message passing neural network that aggregates the vector representations of the node data and the vector representations of edge data to produce a vector representation of the input graph data; processing the vector representation of the input graph data with a multi-layer perception layer of the edge message passing neural network to generate predicted graph data of a predicted object; and reporting the predicted graph data in a report.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2021</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&amp;date=20210916&amp;DB=EPODOC&amp;CC=US&amp;NR=2021287067A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20210916&amp;DB=EPODOC&amp;CC=US&amp;NR=2021287067A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Leonov, Dmitry</creatorcontrib><creatorcontrib>Putin, Evgeny Olegovich</creatorcontrib><creatorcontrib>Zavoronkovs, Aleksandrs</creatorcontrib><title>EDGE MESSAGE PASSING NEURAL NETWORK</title><description>A method of generating graph data of an object is provided, the object is physical, audio object, text object or color object. The method can include: processing input graph data of at least one object with a graph convolution layer of an edge message passing neural network to obtain vector representations of the node data and edge data of the graph data; processing the vector representations of the edge data and node data with a graph pooling layer of the edge message passing neural network that aggregates the vector representations of the node data and the vector representations of edge data to produce a vector representation of the input graph data; processing the vector representation of the input graph data with a multi-layer perception layer of the edge message passing neural network to generate predicted graph data of a predicted object; and reporting the predicted graph data in a report.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZFB2dXF3VfB1DQ52BNIBjsHBnn7uCn6uoUGOPkAqJNw_yJuHgTUtMac4lRdKczMou7mGOHvophbkx6cWFyQmp-allsSHBhsZGBkaWZgbmJk7GhoTpwoA3fojpA</recordid><startdate>20210916</startdate><enddate>20210916</enddate><creator>Leonov, Dmitry</creator><creator>Putin, Evgeny Olegovich</creator><creator>Zavoronkovs, Aleksandrs</creator><scope>EVB</scope></search><sort><creationdate>20210916</creationdate><title>EDGE MESSAGE PASSING NEURAL NETWORK</title><author>Leonov, Dmitry ; Putin, Evgeny Olegovich ; Zavoronkovs, Aleksandrs</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2021287067A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Leonov, Dmitry</creatorcontrib><creatorcontrib>Putin, Evgeny Olegovich</creatorcontrib><creatorcontrib>Zavoronkovs, Aleksandrs</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Leonov, Dmitry</au><au>Putin, Evgeny Olegovich</au><au>Zavoronkovs, Aleksandrs</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>EDGE MESSAGE PASSING NEURAL NETWORK</title><date>2021-09-16</date><risdate>2021</risdate><abstract>A method of generating graph data of an object is provided, the object is physical, audio object, text object or color object. The method can include: processing input graph data of at least one object with a graph convolution layer of an edge message passing neural network to obtain vector representations of the node data and edge data of the graph data; processing the vector representations of the edge data and node data with a graph pooling layer of the edge message passing neural network that aggregates the vector representations of the node data and the vector representations of edge data to produce a vector representation of the input graph data; processing the vector representation of the input graph data with a multi-layer perception layer of the edge message passing neural network to generate predicted graph data of a predicted object; and reporting the predicted graph data in a report.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2021287067A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title EDGE MESSAGE PASSING NEURAL NETWORK
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T01%3A24%3A29IST&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=Leonov,%20Dmitry&rft.date=2021-09-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2021287067A1%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