Loading…

Convolutional neural network for knowledge graph completion

Knowledge Graph Embedding aims to learn the relationship between two entities by quantifying them in real-valued vector space. How-ever, there are two significant challenges with learning knowledge graph embedding: 1) How can deep learning techniques be used to construct expressive embeddings to the...

Full description

Saved in:
Bibliographic Details
Main Authors: Khobragade, Anish, Ghumbre, Shashikant, Wangde, Fawaz
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue 1
container_start_page
container_title
container_volume 2917
creator Khobragade, Anish
Ghumbre, Shashikant
Wangde, Fawaz
description Knowledge Graph Embedding aims to learn the relationship between two entities by quantifying them in real-valued vector space. How-ever, there are two significant challenges with learning knowledge graph embedding: 1) How can deep learning techniques be used to construct expressive embeddings to their full potential? 2) How to deal with the polysemy problem that multi-relational knowledge graphs produce, where relations and entities have multiple semantics depending on which predictions are used? To solve the first problem, multilayer convolutional neural networks use to create the features, which are then employed in this article to anticipate potential relations. Furthermore, the network representational power is enhanced by incorporating an effective recalibration method that preferentially amplifies relevant features. We propose learning multiple specialized relationship embeddings to solve the second difficulty. Rather than developing a single generic embedding to maintain all the data for each relation and entity, their connections are recorded to depict a cross-semantic effect from entities to relations and vice versa. The model gives higher generalization performance and better recording of potential linkages between relations and entities compared to existing knowledge graph embedding models. According to experimental results, the proposed model performs better for generic evaluation metrics on relation prediction tasks.
doi_str_mv 10.1063/5.0175625
format conference_proceeding
fullrecord <record><control><sourceid>proquest_scita</sourceid><recordid>TN_cdi_scitation_primary_10_1063_5_0175625</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2885359732</sourcerecordid><originalsourceid>FETCH-LOGICAL-p133t-a1d210a92a963926e77b55a143c05d1e8f379285f6c0679f70446e6f9400475d3</originalsourceid><addsrcrecordid>eNotkE9LwzAYh4MoWKcHv0HBm9D55s-bNHiS4lQYeFHwFmKbzm5dU5PW4bd3dTv9Lg8_Hh5CrinMKUh-h3OgCiXDE5JQRJopSeUpSQC0yJjgH-fkIsY1ANNK5Qm5L3z349txaHxn27RzY_ifYefDJq19SDed37WuWrl0FWz_lZZ-27du4i_JWW3b6K6OOyPvi8e34jlbvj69FA_LrKecD5mlFaNgNbNacs2kU-oT0VLBS8CKurzmSrMca1mCVLpWIIR0stYCQCis-IzcHH774L9HFwez9mPY60bD8hw5asXZnro9ULFsBjv5mT40Wxt-DQUzxTFojnH4H927VQg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>2885359732</pqid></control><display><type>conference_proceeding</type><title>Convolutional neural network for knowledge graph completion</title><source>American Institute of Physics:Jisc Collections:Transitional Journals Agreement 2021-23 (Reading list)</source><creator>Khobragade, Anish ; Ghumbre, Shashikant ; Wangde, Fawaz</creator><contributor>Aseer, J. Ronald ; Bahubalendruni, M V A Raju ; Mahapatra, Ansuman</contributor><creatorcontrib>Khobragade, Anish ; Ghumbre, Shashikant ; Wangde, Fawaz ; Aseer, J. Ronald ; Bahubalendruni, M V A Raju ; Mahapatra, Ansuman</creatorcontrib><description>Knowledge Graph Embedding aims to learn the relationship between two entities by quantifying them in real-valued vector space. How-ever, there are two significant challenges with learning knowledge graph embedding: 1) How can deep learning techniques be used to construct expressive embeddings to their full potential? 2) How to deal with the polysemy problem that multi-relational knowledge graphs produce, where relations and entities have multiple semantics depending on which predictions are used? To solve the first problem, multilayer convolutional neural networks use to create the features, which are then employed in this article to anticipate potential relations. Furthermore, the network representational power is enhanced by incorporating an effective recalibration method that preferentially amplifies relevant features. We propose learning multiple specialized relationship embeddings to solve the second difficulty. Rather than developing a single generic embedding to maintain all the data for each relation and entity, their connections are recorded to depict a cross-semantic effect from entities to relations and vice versa. The model gives higher generalization performance and better recording of potential linkages between relations and entities compared to existing knowledge graph embedding models. According to experimental results, the proposed model performs better for generic evaluation metrics on relation prediction tasks.</description><identifier>ISSN: 0094-243X</identifier><identifier>EISSN: 1551-7616</identifier><identifier>DOI: 10.1063/5.0175625</identifier><identifier>CODEN: APCPCS</identifier><language>eng</language><publisher>Melville: American Institute of Physics</publisher><subject>Artificial neural networks ; Deep learning ; Embedding ; Knowledge representation ; Multilayers ; Neural networks ; Semantics ; Vector spaces</subject><ispartof>AIP Conference Proceedings, 2023, Vol.2917 (1)</ispartof><rights>Author(s)</rights><rights>2023 Author(s). Published by AIP Publishing.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>309,310,314,780,784,789,790,23930,23931,25140,27924,27925</link.rule.ids></links><search><contributor>Aseer, J. Ronald</contributor><contributor>Bahubalendruni, M V A Raju</contributor><contributor>Mahapatra, Ansuman</contributor><creatorcontrib>Khobragade, Anish</creatorcontrib><creatorcontrib>Ghumbre, Shashikant</creatorcontrib><creatorcontrib>Wangde, Fawaz</creatorcontrib><title>Convolutional neural network for knowledge graph completion</title><title>AIP Conference Proceedings</title><description>Knowledge Graph Embedding aims to learn the relationship between two entities by quantifying them in real-valued vector space. How-ever, there are two significant challenges with learning knowledge graph embedding: 1) How can deep learning techniques be used to construct expressive embeddings to their full potential? 2) How to deal with the polysemy problem that multi-relational knowledge graphs produce, where relations and entities have multiple semantics depending on which predictions are used? To solve the first problem, multilayer convolutional neural networks use to create the features, which are then employed in this article to anticipate potential relations. Furthermore, the network representational power is enhanced by incorporating an effective recalibration method that preferentially amplifies relevant features. We propose learning multiple specialized relationship embeddings to solve the second difficulty. Rather than developing a single generic embedding to maintain all the data for each relation and entity, their connections are recorded to depict a cross-semantic effect from entities to relations and vice versa. The model gives higher generalization performance and better recording of potential linkages between relations and entities compared to existing knowledge graph embedding models. According to experimental results, the proposed model performs better for generic evaluation metrics on relation prediction tasks.</description><subject>Artificial neural networks</subject><subject>Deep learning</subject><subject>Embedding</subject><subject>Knowledge representation</subject><subject>Multilayers</subject><subject>Neural networks</subject><subject>Semantics</subject><subject>Vector spaces</subject><issn>0094-243X</issn><issn>1551-7616</issn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2023</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNotkE9LwzAYh4MoWKcHv0HBm9D55s-bNHiS4lQYeFHwFmKbzm5dU5PW4bd3dTv9Lg8_Hh5CrinMKUh-h3OgCiXDE5JQRJopSeUpSQC0yJjgH-fkIsY1ANNK5Qm5L3z349txaHxn27RzY_ifYefDJq19SDed37WuWrl0FWz_lZZ-27du4i_JWW3b6K6OOyPvi8e34jlbvj69FA_LrKecD5mlFaNgNbNacs2kU-oT0VLBS8CKurzmSrMca1mCVLpWIIR0stYCQCis-IzcHH774L9HFwez9mPY60bD8hw5asXZnro9ULFsBjv5mT40Wxt-DQUzxTFojnH4H927VQg</recordid><startdate>20231102</startdate><enddate>20231102</enddate><creator>Khobragade, Anish</creator><creator>Ghumbre, Shashikant</creator><creator>Wangde, Fawaz</creator><general>American Institute of Physics</general><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>20231102</creationdate><title>Convolutional neural network for knowledge graph completion</title><author>Khobragade, Anish ; Ghumbre, Shashikant ; Wangde, Fawaz</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p133t-a1d210a92a963926e77b55a143c05d1e8f379285f6c0679f70446e6f9400475d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial neural networks</topic><topic>Deep learning</topic><topic>Embedding</topic><topic>Knowledge representation</topic><topic>Multilayers</topic><topic>Neural networks</topic><topic>Semantics</topic><topic>Vector spaces</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Khobragade, Anish</creatorcontrib><creatorcontrib>Ghumbre, Shashikant</creatorcontrib><creatorcontrib>Wangde, Fawaz</creatorcontrib><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Khobragade, Anish</au><au>Ghumbre, Shashikant</au><au>Wangde, Fawaz</au><au>Aseer, J. Ronald</au><au>Bahubalendruni, M V A Raju</au><au>Mahapatra, Ansuman</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Convolutional neural network for knowledge graph completion</atitle><btitle>AIP Conference Proceedings</btitle><date>2023-11-02</date><risdate>2023</risdate><volume>2917</volume><issue>1</issue><issn>0094-243X</issn><eissn>1551-7616</eissn><coden>APCPCS</coden><abstract>Knowledge Graph Embedding aims to learn the relationship between two entities by quantifying them in real-valued vector space. How-ever, there are two significant challenges with learning knowledge graph embedding: 1) How can deep learning techniques be used to construct expressive embeddings to their full potential? 2) How to deal with the polysemy problem that multi-relational knowledge graphs produce, where relations and entities have multiple semantics depending on which predictions are used? To solve the first problem, multilayer convolutional neural networks use to create the features, which are then employed in this article to anticipate potential relations. Furthermore, the network representational power is enhanced by incorporating an effective recalibration method that preferentially amplifies relevant features. We propose learning multiple specialized relationship embeddings to solve the second difficulty. Rather than developing a single generic embedding to maintain all the data for each relation and entity, their connections are recorded to depict a cross-semantic effect from entities to relations and vice versa. The model gives higher generalization performance and better recording of potential linkages between relations and entities compared to existing knowledge graph embedding models. According to experimental results, the proposed model performs better for generic evaluation metrics on relation prediction tasks.</abstract><cop>Melville</cop><pub>American Institute of Physics</pub><doi>10.1063/5.0175625</doi><tpages>10</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0094-243X
ispartof AIP Conference Proceedings, 2023, Vol.2917 (1)
issn 0094-243X
1551-7616
language eng
recordid cdi_scitation_primary_10_1063_5_0175625
source American Institute of Physics:Jisc Collections:Transitional Journals Agreement 2021-23 (Reading list)
subjects Artificial neural networks
Deep learning
Embedding
Knowledge representation
Multilayers
Neural networks
Semantics
Vector spaces
title Convolutional neural network for knowledge graph completion
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T11%3A03%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_scita&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Convolutional%20neural%20network%20for%20knowledge%20graph%20completion&rft.btitle=AIP%20Conference%20Proceedings&rft.au=Khobragade,%20Anish&rft.date=2023-11-02&rft.volume=2917&rft.issue=1&rft.issn=0094-243X&rft.eissn=1551-7616&rft.coden=APCPCS&rft_id=info:doi/10.1063/5.0175625&rft_dat=%3Cproquest_scita%3E2885359732%3C/proquest_scita%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-p133t-a1d210a92a963926e77b55a143c05d1e8f379285f6c0679f70446e6f9400475d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2885359732&rft_id=info:pmid/&rfr_iscdi=true