Knowledge Graph Embedding by Bias Vectors

Knowledge graph completion can predict the possible relation between entities. Previous work such as TransE, TransR, TransPES and GTrans embed knowledge graph into vector space and treat relations between entities as translations. In most cases, the more complex the algorithm is, the better the resu...

Full description

Saved in:
Bibliographic Details
Main Authors: Ding, Minjie, Tong, Weiqin, Ding, Xuehai, Zhi, Xiaoli, Wang, Xiao, Zhang, Guoqing
Format: Conference Proceeding
Language:English
Subjects:
knowledge completion
knowledge embedding
link prediction
triplets
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1302
container_issue
container_start_page 1296
container_title
container_volume
creator Ding, Minjie
Tong, Weiqin
Ding, Xuehai
Zhi, Xiaoli
Wang, Xiao
Zhang, Guoqing
description Knowledge graph completion can predict the possible relation between entities. Previous work such as TransE, TransR, TransPES and GTrans embed knowledge graph into vector space and treat relations between entities as translations. In most cases, the more complex the algorithm is, the better the result will be, but it is difficult to apply to large-scale knowledge graphs. Therefore, we propose TransB, an efficient model, in this paper. We avoid the complex matrix or vector multiplication operation. Meanwhile, we make the representation of entities not too simple, which can satisfy the operation in the case of non-one-to-one relation. We use link prediction to evaluate the performance of our model in the experiment. The experimental results show that our model is valid and has low time complexity.
doi_str_mv 10.1109/ICTAI.2019.00180
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8995354</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8995354</ieee_id><sourcerecordid>8995354</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-c2ce5ce9a54833300594767b6948278c8dbe2fa180ddda8b1dfb2b03370dca713</originalsourceid><addsrcrecordid>eNotjj1LA0EUAFdBMCbpBZtrLe58u-82-7aMRxIPA2mibdiPd3ElX9wGJP_egFbTDMMI8SihkhLsS9usp22lQNoKQBLciLE1JI0iicYS3YqBQqPLq2DuxUPO3wAKtMKBeH4_HH92HLdcLHp3-ipme88xpsO28JfiNblcfHI4H_s8Ened22Ue_3MoPuazdfNWLleLtpkuy6QAz2VQgXVg63RNiAigbW0mxk9sTcpQoOhZde56GWN05GXsvPKAaCAGZyQOxdNfNzHz5tSnvesvG7JWo67xF-SgQFI</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Knowledge Graph Embedding by Bias Vectors</title><source>IEEE Xplore All Conference Series</source><creator>Ding, Minjie ; Tong, Weiqin ; Ding, Xuehai ; Zhi, Xiaoli ; Wang, Xiao ; Zhang, Guoqing</creator><creatorcontrib>Ding, Minjie ; Tong, Weiqin ; Ding, Xuehai ; Zhi, Xiaoli ; Wang, Xiao ; Zhang, Guoqing</creatorcontrib><description>Knowledge graph completion can predict the possible relation between entities. Previous work such as TransE, TransR, TransPES and GTrans embed knowledge graph into vector space and treat relations between entities as translations. In most cases, the more complex the algorithm is, the better the result will be, but it is difficult to apply to large-scale knowledge graphs. Therefore, we propose TransB, an efficient model, in this paper. We avoid the complex matrix or vector multiplication operation. Meanwhile, we make the representation of entities not too simple, which can satisfy the operation in the case of non-one-to-one relation. We use link prediction to evaluate the performance of our model in the experiment. The experimental results show that our model is valid and has low time complexity.</description><identifier>EISSN: 2375-0197</identifier><identifier>EISBN: 9781728137988</identifier><identifier>EISBN: 1728137985</identifier><identifier>DOI: 10.1109/ICTAI.2019.00180</identifier><language>eng</language><publisher>IEEE</publisher><subject>knowledge completion ; knowledge embedding ; link prediction ; triplets</subject><ispartof>2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), 2019, p.1296-1302</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8995354$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8995354$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ding, Minjie</creatorcontrib><creatorcontrib>Tong, Weiqin</creatorcontrib><creatorcontrib>Ding, Xuehai</creatorcontrib><creatorcontrib>Zhi, Xiaoli</creatorcontrib><creatorcontrib>Wang, Xiao</creatorcontrib><creatorcontrib>Zhang, Guoqing</creatorcontrib><title>Knowledge Graph Embedding by Bias Vectors</title><title>2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)</title><addtitle>TAI</addtitle><description>Knowledge graph completion can predict the possible relation between entities. Previous work such as TransE, TransR, TransPES and GTrans embed knowledge graph into vector space and treat relations between entities as translations. In most cases, the more complex the algorithm is, the better the result will be, but it is difficult to apply to large-scale knowledge graphs. Therefore, we propose TransB, an efficient model, in this paper. We avoid the complex matrix or vector multiplication operation. Meanwhile, we make the representation of entities not too simple, which can satisfy the operation in the case of non-one-to-one relation. We use link prediction to evaluate the performance of our model in the experiment. The experimental results show that our model is valid and has low time complexity.</description><subject>knowledge completion</subject><subject>knowledge embedding</subject><subject>link prediction</subject><subject>triplets</subject><issn>2375-0197</issn><isbn>9781728137988</isbn><isbn>1728137985</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2019</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjj1LA0EUAFdBMCbpBZtrLe58u-82-7aMRxIPA2mibdiPd3ElX9wGJP_egFbTDMMI8SihkhLsS9usp22lQNoKQBLciLE1JI0iicYS3YqBQqPLq2DuxUPO3wAKtMKBeH4_HH92HLdcLHp3-ipme88xpsO28JfiNblcfHI4H_s8Ened22Ue_3MoPuazdfNWLleLtpkuy6QAz2VQgXVg63RNiAigbW0mxk9sTcpQoOhZde56GWN05GXsvPKAaCAGZyQOxdNfNzHz5tSnvesvG7JWo67xF-SgQFI</recordid><startdate>201911</startdate><enddate>201911</enddate><creator>Ding, Minjie</creator><creator>Tong, Weiqin</creator><creator>Ding, Xuehai</creator><creator>Zhi, Xiaoli</creator><creator>Wang, Xiao</creator><creator>Zhang, Guoqing</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201911</creationdate><title>Knowledge Graph Embedding by Bias Vectors</title><author>Ding, Minjie ; Tong, Weiqin ; Ding, Xuehai ; Zhi, Xiaoli ; Wang, Xiao ; Zhang, Guoqing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-c2ce5ce9a54833300594767b6948278c8dbe2fa180ddda8b1dfb2b03370dca713</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2019</creationdate><topic>knowledge completion</topic><topic>knowledge embedding</topic><topic>link prediction</topic><topic>triplets</topic><toplevel>online_resources</toplevel><creatorcontrib>Ding, Minjie</creatorcontrib><creatorcontrib>Tong, Weiqin</creatorcontrib><creatorcontrib>Ding, Xuehai</creatorcontrib><creatorcontrib>Zhi, Xiaoli</creatorcontrib><creatorcontrib>Wang, Xiao</creatorcontrib><creatorcontrib>Zhang, Guoqing</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ding, Minjie</au><au>Tong, Weiqin</au><au>Ding, Xuehai</au><au>Zhi, Xiaoli</au><au>Wang, Xiao</au><au>Zhang, Guoqing</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Knowledge Graph Embedding by Bias Vectors</atitle><btitle>2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)</btitle><stitle>TAI</stitle><date>2019-11</date><risdate>2019</risdate><spage>1296</spage><epage>1302</epage><pages>1296-1302</pages><eissn>2375-0197</eissn><eisbn>9781728137988</eisbn><eisbn>1728137985</eisbn><abstract>Knowledge graph completion can predict the possible relation between entities. Previous work such as TransE, TransR, TransPES and GTrans embed knowledge graph into vector space and treat relations between entities as translations. In most cases, the more complex the algorithm is, the better the result will be, but it is difficult to apply to large-scale knowledge graphs. Therefore, we propose TransB, an efficient model, in this paper. We avoid the complex matrix or vector multiplication operation. Meanwhile, we make the representation of entities not too simple, which can satisfy the operation in the case of non-one-to-one relation. We use link prediction to evaluate the performance of our model in the experiment. The experimental results show that our model is valid and has low time complexity.</abstract><pub>IEEE</pub><doi>10.1109/ICTAI.2019.00180</doi><tpages>7</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2375-0197
ispartof 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), 2019, p.1296-1302
issn 2375-0197
language eng
recordid cdi_ieee_primary_8995354
source IEEE Xplore All Conference Series
subjects knowledge completion
knowledge embedding
link prediction
triplets
title Knowledge Graph Embedding by Bias Vectors
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T20%3A40%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Knowledge%20Graph%20Embedding%20by%20Bias%20Vectors&rft.btitle=2019%20IEEE%2031st%20International%20Conference%20on%20Tools%20with%20Artificial%20Intelligence%20(ICTAI)&rft.au=Ding,%20Minjie&rft.date=2019-11&rft.spage=1296&rft.epage=1302&rft.pages=1296-1302&rft.eissn=2375-0197&rft_id=info:doi/10.1109/ICTAI.2019.00180&rft.eisbn=9781728137988&rft.eisbn_list=1728137985&rft_dat=%3Cieee_CHZPO%3E8995354%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i203t-c2ce5ce9a54833300594767b6948278c8dbe2fa180ddda8b1dfb2b03370dca713%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8995354&rfr_iscdi=true