ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment
Entity alignment (EA) aims to identify entities across different knowledge graphs that represent the same real-world objects. Recent embedding-based EA methods have achieved state-of-the-art performance in EA yet faced interpretability challenges as they purely rely on the embedding distance and neg...
Gespeichert in:
Hauptverfasser: | , , , , , , |
---|---|
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 | Luo, Yangyifei Chen, Zhuo Guo, Lingbing Li, Qian Zeng, Wenxuan Cai, Zhixin Li, Jianxin |
description | Entity alignment (EA) aims to identify entities across different knowledge
graphs that represent the same real-world objects. Recent embedding-based EA
methods have achieved state-of-the-art performance in EA yet faced
interpretability challenges as they purely rely on the embedding distance and
neglect the logic rules behind a pair of aligned entities. In this paper, we
propose the Align-Subgraph Entity Alignment (ASGEA) framework to exploit logic
rules from Align-Subgraphs. ASGEA uses anchor links as bridges to construct
Align-Subgraphs and spreads along the paths across KGs, which distinguishes it
from the embedding-based methods. Furthermore, we design an interpretable
Path-based Graph Neural Network, ASGNN, to effectively identify and integrate
the logic rules across KGs. We also introduce a node-level multi-modal
attention mechanism coupled with multi-modal enriched anchors to augment the
Align-Subgraph. Our experimental results demonstrate the superior performance
of ASGEA over the existing embedding-based methods in both EA and Multi-Modal
EA (MMEA) tasks. |
doi_str_mv | 10.48550/arxiv.2402.11000 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2402_11000</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2402_11000</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-de337f28027a00fd67ad0b11ad242e3ef9a93a177a5c44b601591de2a49e894c3</originalsourceid><addsrcrecordid>eNotz8tqwzAUBFBtuihpPqCr6gfsXj1sWd2Z4LgFQ6DJ3lxbkivwC8Upyd8nTboamIGBQ8grg1hmSQLvGM7-N-YSeMwYADyTMt-XRf5Bi_PcT37xY0erqfMt_T719khdmAaa974bo_2p6QLOP7dyCrQYF79cHtNgx-WFPDnsj3b9nyty2BaHzWdU7cqvTV5FmCqIjBVCOZ4BVwjgTKrQQMMYGi65FdZp1AKZUpi0UjYpsEQzYzlKbTMtW7Eib4_bu6Segx8wXOo_UX0XiSuBOUUm</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment</title><source>arXiv.org</source><creator>Luo, Yangyifei ; Chen, Zhuo ; Guo, Lingbing ; Li, Qian ; Zeng, Wenxuan ; Cai, Zhixin ; Li, Jianxin</creator><creatorcontrib>Luo, Yangyifei ; Chen, Zhuo ; Guo, Lingbing ; Li, Qian ; Zeng, Wenxuan ; Cai, Zhixin ; Li, Jianxin</creatorcontrib><description>Entity alignment (EA) aims to identify entities across different knowledge
graphs that represent the same real-world objects. Recent embedding-based EA
methods have achieved state-of-the-art performance in EA yet faced
interpretability challenges as they purely rely on the embedding distance and
neglect the logic rules behind a pair of aligned entities. In this paper, we
propose the Align-Subgraph Entity Alignment (ASGEA) framework to exploit logic
rules from Align-Subgraphs. ASGEA uses anchor links as bridges to construct
Align-Subgraphs and spreads along the paths across KGs, which distinguishes it
from the embedding-based methods. Furthermore, we design an interpretable
Path-based Graph Neural Network, ASGNN, to effectively identify and integrate
the logic rules across KGs. We also introduce a node-level multi-modal
attention mechanism coupled with multi-modal enriched anchors to augment the
Align-Subgraph. Our experimental results demonstrate the superior performance
of ASGEA over the existing embedding-based methods in both EA and Multi-Modal
EA (MMEA) tasks.</description><identifier>DOI: 10.48550/arxiv.2402.11000</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computation and Language</subject><creationdate>2024-02</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</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/2402.11000$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2402.11000$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Luo, Yangyifei</creatorcontrib><creatorcontrib>Chen, Zhuo</creatorcontrib><creatorcontrib>Guo, Lingbing</creatorcontrib><creatorcontrib>Li, Qian</creatorcontrib><creatorcontrib>Zeng, Wenxuan</creatorcontrib><creatorcontrib>Cai, Zhixin</creatorcontrib><creatorcontrib>Li, Jianxin</creatorcontrib><title>ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment</title><description>Entity alignment (EA) aims to identify entities across different knowledge
graphs that represent the same real-world objects. Recent embedding-based EA
methods have achieved state-of-the-art performance in EA yet faced
interpretability challenges as they purely rely on the embedding distance and
neglect the logic rules behind a pair of aligned entities. In this paper, we
propose the Align-Subgraph Entity Alignment (ASGEA) framework to exploit logic
rules from Align-Subgraphs. ASGEA uses anchor links as bridges to construct
Align-Subgraphs and spreads along the paths across KGs, which distinguishes it
from the embedding-based methods. Furthermore, we design an interpretable
Path-based Graph Neural Network, ASGNN, to effectively identify and integrate
the logic rules across KGs. We also introduce a node-level multi-modal
attention mechanism coupled with multi-modal enriched anchors to augment the
Align-Subgraph. Our experimental results demonstrate the superior performance
of ASGEA over the existing embedding-based methods in both EA and Multi-Modal
EA (MMEA) tasks.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz8tqwzAUBFBtuihpPqCr6gfsXj1sWd2Z4LgFQ6DJ3lxbkivwC8Upyd8nTboamIGBQ8grg1hmSQLvGM7-N-YSeMwYADyTMt-XRf5Bi_PcT37xY0erqfMt_T719khdmAaa974bo_2p6QLOP7dyCrQYF79cHtNgx-WFPDnsj3b9nyty2BaHzWdU7cqvTV5FmCqIjBVCOZ4BVwjgTKrQQMMYGi65FdZp1AKZUpi0UjYpsEQzYzlKbTMtW7Eib4_bu6Segx8wXOo_UX0XiSuBOUUm</recordid><startdate>20240216</startdate><enddate>20240216</enddate><creator>Luo, Yangyifei</creator><creator>Chen, Zhuo</creator><creator>Guo, Lingbing</creator><creator>Li, Qian</creator><creator>Zeng, Wenxuan</creator><creator>Cai, Zhixin</creator><creator>Li, Jianxin</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240216</creationdate><title>ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment</title><author>Luo, Yangyifei ; Chen, Zhuo ; Guo, Lingbing ; Li, Qian ; Zeng, Wenxuan ; Cai, Zhixin ; Li, Jianxin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-de337f28027a00fd67ad0b11ad242e3ef9a93a177a5c44b601591de2a49e894c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Luo, Yangyifei</creatorcontrib><creatorcontrib>Chen, Zhuo</creatorcontrib><creatorcontrib>Guo, Lingbing</creatorcontrib><creatorcontrib>Li, Qian</creatorcontrib><creatorcontrib>Zeng, Wenxuan</creatorcontrib><creatorcontrib>Cai, Zhixin</creatorcontrib><creatorcontrib>Li, Jianxin</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Luo, Yangyifei</au><au>Chen, Zhuo</au><au>Guo, Lingbing</au><au>Li, Qian</au><au>Zeng, Wenxuan</au><au>Cai, Zhixin</au><au>Li, Jianxin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment</atitle><date>2024-02-16</date><risdate>2024</risdate><abstract>Entity alignment (EA) aims to identify entities across different knowledge
graphs that represent the same real-world objects. Recent embedding-based EA
methods have achieved state-of-the-art performance in EA yet faced
interpretability challenges as they purely rely on the embedding distance and
neglect the logic rules behind a pair of aligned entities. In this paper, we
propose the Align-Subgraph Entity Alignment (ASGEA) framework to exploit logic
rules from Align-Subgraphs. ASGEA uses anchor links as bridges to construct
Align-Subgraphs and spreads along the paths across KGs, which distinguishes it
from the embedding-based methods. Furthermore, we design an interpretable
Path-based Graph Neural Network, ASGNN, to effectively identify and integrate
the logic rules across KGs. We also introduce a node-level multi-modal
attention mechanism coupled with multi-modal enriched anchors to augment the
Align-Subgraph. Our experimental results demonstrate the superior performance
of ASGEA over the existing embedding-based methods in both EA and Multi-Modal
EA (MMEA) tasks.</abstract><doi>10.48550/arxiv.2402.11000</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2402.11000 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2402_11000 |
source | arXiv.org |
subjects | Computer Science - Artificial Intelligence Computer Science - Computation and Language |
title | ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T21%3A43%3A36IST&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=ASGEA:%20Exploiting%20Logic%20Rules%20from%20Align-Subgraphs%20for%20Entity%20Alignment&rft.au=Luo,%20Yangyifei&rft.date=2024-02-16&rft_id=info:doi/10.48550/arxiv.2402.11000&rft_dat=%3Carxiv_GOX%3E2402_11000%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 |