DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning

Knowledge graphs (KGs), as structured representations of real world facts, are intelligent databases incorporating human knowledge that can help machine imitate the way of human problem solving. However, KGs are usually huge and there are inevitably missing facts in KGs, thus undermining application...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Haotian, Liu, Hongri, Wang, Yao, Xin, Guodong, Wei, Yuliang
Format: Artikel
Sprache:eng
Schlagworte:
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 Li, Haotian
Liu, Hongri
Wang, Yao
Xin, Guodong
Wei, Yuliang
description Knowledge graphs (KGs), as structured representations of real world facts, are intelligent databases incorporating human knowledge that can help machine imitate the way of human problem solving. However, KGs are usually huge and there are inevitably missing facts in KGs, thus undermining applications such as question answering and recommender systems that are based on knowledge graph reasoning. Link prediction for knowledge graphs is the task aiming to complete missing facts by reasoning based on the existing knowledge. Two main streams of research are widely studied: one learns low-dimensional embeddings for entities and relations that can explore latent patterns, and the other gains good interpretability by mining logical rules. Unfortunately, the heterogeneity of modern KGs that involve entities and relations of various types is not well considered in the previous studies. In this paper, we propose DegreEmbed, a model that combines embedding-based learning and logic rule mining for inferring on KGs. Specifically, we study the problem of predicting missing links in heterogeneous KGs from the perspective of the degree of nodes. Experimentally, we demonstrate that our DegreEmbed model outperforms the state-of-the-art methods on real world datasets and the rules mined by our model are of high quality and interpretability.
doi_str_mv 10.48550/arxiv.2112.09933
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2112_09933</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2112_09933</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-3bc49693f2c09852bdda2285b35ade9ac3a0ad00f338009594487c396ab97a703</originalsourceid><addsrcrecordid>eNotj8tqwzAQRbXpoqT9gK6qH7Arayzb6q6k6QMC3WRvxtLYEXEkM3Ef-fvitKsL98CBI8RdofKyMUY9IP-Er1wXhc6VtQDXAp9pYNocO_KPMkSXeEqMc4iDpDiH-SxpYX45QpyTHNMQnOTPkeRIyHEBfWJ5iOl7JD-QHBinvWTCU1rojbjqcTzR7f-uxO5ls1u_ZduP1_f10zbDqoYMOlfaykKvnbKN0Z33qHVjOjDoyaIDVOiV6gEapayxZdnUDmyFna2xVrAS93_aS2M7cTgin9ultb20wi_LKlBL</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning</title><source>arXiv.org</source><creator>Li, Haotian ; Liu, Hongri ; Wang, Yao ; Xin, Guodong ; Wei, Yuliang</creator><creatorcontrib>Li, Haotian ; Liu, Hongri ; Wang, Yao ; Xin, Guodong ; Wei, Yuliang</creatorcontrib><description>Knowledge graphs (KGs), as structured representations of real world facts, are intelligent databases incorporating human knowledge that can help machine imitate the way of human problem solving. However, KGs are usually huge and there are inevitably missing facts in KGs, thus undermining applications such as question answering and recommender systems that are based on knowledge graph reasoning. Link prediction for knowledge graphs is the task aiming to complete missing facts by reasoning based on the existing knowledge. Two main streams of research are widely studied: one learns low-dimensional embeddings for entities and relations that can explore latent patterns, and the other gains good interpretability by mining logical rules. Unfortunately, the heterogeneity of modern KGs that involve entities and relations of various types is not well considered in the previous studies. In this paper, we propose DegreEmbed, a model that combines embedding-based learning and logic rule mining for inferring on KGs. Specifically, we study the problem of predicting missing links in heterogeneous KGs from the perspective of the degree of nodes. Experimentally, we demonstrate that our DegreEmbed model outperforms the state-of-the-art methods on real world datasets and the rules mined by our model are of high quality and interpretability.</description><identifier>DOI: 10.48550/arxiv.2112.09933</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning</subject><creationdate>2021-12</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2112.09933$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2112.09933$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Li, Haotian</creatorcontrib><creatorcontrib>Liu, Hongri</creatorcontrib><creatorcontrib>Wang, Yao</creatorcontrib><creatorcontrib>Xin, Guodong</creatorcontrib><creatorcontrib>Wei, Yuliang</creatorcontrib><title>DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning</title><description>Knowledge graphs (KGs), as structured representations of real world facts, are intelligent databases incorporating human knowledge that can help machine imitate the way of human problem solving. However, KGs are usually huge and there are inevitably missing facts in KGs, thus undermining applications such as question answering and recommender systems that are based on knowledge graph reasoning. Link prediction for knowledge graphs is the task aiming to complete missing facts by reasoning based on the existing knowledge. Two main streams of research are widely studied: one learns low-dimensional embeddings for entities and relations that can explore latent patterns, and the other gains good interpretability by mining logical rules. Unfortunately, the heterogeneity of modern KGs that involve entities and relations of various types is not well considered in the previous studies. In this paper, we propose DegreEmbed, a model that combines embedding-based learning and logic rule mining for inferring on KGs. Specifically, we study the problem of predicting missing links in heterogeneous KGs from the perspective of the degree of nodes. Experimentally, we demonstrate that our DegreEmbed model outperforms the state-of-the-art methods on real world datasets and the rules mined by our model are of high quality and interpretability.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tqwzAQRbXpoqT9gK6qH7Arayzb6q6k6QMC3WRvxtLYEXEkM3Ef-fvitKsL98CBI8RdofKyMUY9IP-Er1wXhc6VtQDXAp9pYNocO_KPMkSXeEqMc4iDpDiH-SxpYX45QpyTHNMQnOTPkeRIyHEBfWJ5iOl7JD-QHBinvWTCU1rojbjqcTzR7f-uxO5ls1u_ZduP1_f10zbDqoYMOlfaykKvnbKN0Z33qHVjOjDoyaIDVOiV6gEapayxZdnUDmyFna2xVrAS93_aS2M7cTgin9ultb20wi_LKlBL</recordid><startdate>20211218</startdate><enddate>20211218</enddate><creator>Li, Haotian</creator><creator>Liu, Hongri</creator><creator>Wang, Yao</creator><creator>Xin, Guodong</creator><creator>Wei, Yuliang</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20211218</creationdate><title>DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning</title><author>Li, Haotian ; Liu, Hongri ; Wang, Yao ; Xin, Guodong ; Wei, Yuliang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-3bc49693f2c09852bdda2285b35ade9ac3a0ad00f338009594487c396ab97a703</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Li, Haotian</creatorcontrib><creatorcontrib>Liu, Hongri</creatorcontrib><creatorcontrib>Wang, Yao</creatorcontrib><creatorcontrib>Xin, Guodong</creatorcontrib><creatorcontrib>Wei, Yuliang</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Li, Haotian</au><au>Liu, Hongri</au><au>Wang, Yao</au><au>Xin, Guodong</au><au>Wei, Yuliang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning</atitle><date>2021-12-18</date><risdate>2021</risdate><abstract>Knowledge graphs (KGs), as structured representations of real world facts, are intelligent databases incorporating human knowledge that can help machine imitate the way of human problem solving. However, KGs are usually huge and there are inevitably missing facts in KGs, thus undermining applications such as question answering and recommender systems that are based on knowledge graph reasoning. Link prediction for knowledge graphs is the task aiming to complete missing facts by reasoning based on the existing knowledge. Two main streams of research are widely studied: one learns low-dimensional embeddings for entities and relations that can explore latent patterns, and the other gains good interpretability by mining logical rules. Unfortunately, the heterogeneity of modern KGs that involve entities and relations of various types is not well considered in the previous studies. In this paper, we propose DegreEmbed, a model that combines embedding-based learning and logic rule mining for inferring on KGs. Specifically, we study the problem of predicting missing links in heterogeneous KGs from the perspective of the degree of nodes. Experimentally, we demonstrate that our DegreEmbed model outperforms the state-of-the-art methods on real world datasets and the rules mined by our model are of high quality and interpretability.</abstract><doi>10.48550/arxiv.2112.09933</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2112.09933
ispartof
issn
language eng
recordid cdi_arxiv_primary_2112_09933
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Learning
title DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T01%3A50%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=DegreEmbed:%20incorporating%20entity%20embedding%20into%20logic%20rule%20learning%20for%20knowledge%20graph%20reasoning&rft.au=Li,%20Haotian&rft.date=2021-12-18&rft_id=info:doi/10.48550/arxiv.2112.09933&rft_dat=%3Carxiv_GOX%3E2112_09933%3C/arxiv_GOX%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