File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Cross-platform product matching based on entity alignment of knowledge graph with raea model

TitleCross-platform product matching based on entity alignment of knowledge graph with raea model
Authors
KeywordsEntity alignment
Graph neural network
Knowledge graph
Product matching
Issue Date2023
Citation
World Wide Web, 2023, v. 26, n. 4, p. 2215-2235 How to Cite?
AbstractProduct matching aims to identify identical or similar products sold on different platforms. By building knowledge graphs (KGs), the product matching problem can be converted to the Entity Alignment (EA) task, which aims to discover the equivalent entities from diverse KGs. The existing EA methods inadequately utilize both attribute triples and relation triples simultaneously, especially the interactions between them. This paper introduces a two-stage pipeline consisting of rough filter and fine filter to match products from eBay and Amazon. For fine filtering, a new framework for Entity Alignment, R elation-aware and A ttribute-aware Graph Attention Networks for E ntity A lignment (RAEA), is employed. RAEA focuses on the interactions between attribute triples and relation triples, where the entity representation aggregates the alignment signals from attributes and relations with Attribute-aware Entity Encoder and Relation-aware Graph Attention Networks. The experimental results indicate that the RAEA model achieves significant improvements over 12 baselines on EA task in the cross-lingual dataset DBP15K (6.59% on average Hits@1) and delivers competitive results in the monolingual dataset DWY100K. The source code for experiments on DBP15K and DWY100K is available at github (https://github.com/Mockingjay-liu/RAEA-model-for-Entity-Alignment).
Persistent Identifierhttp://hdl.handle.net/10722/330903
ISSN
2023 Impact Factor: 2.7
2023 SCImago Journal Rankings: 1.122
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLiu, Wenlong-
dc.contributor.authorPan, Jiahua-
dc.contributor.authorZhang, Xingyu-
dc.contributor.authorGong, Xinxin-
dc.contributor.authorYe, Yang-
dc.contributor.authorZhao, Xujin-
dc.contributor.authorWang, Xin-
dc.contributor.authorWu, Kent-
dc.contributor.authorXiang, Hua-
dc.contributor.authorYan, Houmin-
dc.contributor.authorZhang, Qingpeng-
dc.date.accessioned2023-09-05T12:15:47Z-
dc.date.available2023-09-05T12:15:47Z-
dc.date.issued2023-
dc.identifier.citationWorld Wide Web, 2023, v. 26, n. 4, p. 2215-2235-
dc.identifier.issn1386-145X-
dc.identifier.urihttp://hdl.handle.net/10722/330903-
dc.description.abstractProduct matching aims to identify identical or similar products sold on different platforms. By building knowledge graphs (KGs), the product matching problem can be converted to the Entity Alignment (EA) task, which aims to discover the equivalent entities from diverse KGs. The existing EA methods inadequately utilize both attribute triples and relation triples simultaneously, especially the interactions between them. This paper introduces a two-stage pipeline consisting of rough filter and fine filter to match products from eBay and Amazon. For fine filtering, a new framework for Entity Alignment, R elation-aware and A ttribute-aware Graph Attention Networks for E ntity A lignment (RAEA), is employed. RAEA focuses on the interactions between attribute triples and relation triples, where the entity representation aggregates the alignment signals from attributes and relations with Attribute-aware Entity Encoder and Relation-aware Graph Attention Networks. The experimental results indicate that the RAEA model achieves significant improvements over 12 baselines on EA task in the cross-lingual dataset DBP15K (6.59% on average Hits@1) and delivers competitive results in the monolingual dataset DWY100K. The source code for experiments on DBP15K and DWY100K is available at github (https://github.com/Mockingjay-liu/RAEA-model-for-Entity-Alignment).-
dc.languageeng-
dc.relation.ispartofWorld Wide Web-
dc.subjectEntity alignment-
dc.subjectGraph neural network-
dc.subjectKnowledge graph-
dc.subjectProduct matching-
dc.titleCross-platform product matching based on entity alignment of knowledge graph with raea model-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/s11280-022-01134-y-
dc.identifier.scopuseid_2-s2.0-85147334599-
dc.identifier.volume26-
dc.identifier.issue4-
dc.identifier.spage2215-
dc.identifier.epage2235-
dc.identifier.eissn1573-1413-
dc.identifier.isiWOS:000925703600001-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats