An Approach to Semantic-Aware Heterogeneous Network Embedding for Recommender Systems
Recent studies on heterogeneous information network (HIN) embedding-based recommendations have encountered challenges. These challenges are related to the data heterogeneity of the associated unstructured attribute or content (e.g., text-based summary/description) of users and items in the context o...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on cybernetics 2023-09, Vol.53 (9), p.6027-6040 |
---|---|
Hauptverfasser: | , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 6040 |
---|---|
container_issue | 9 |
container_start_page | 6027 |
container_title | IEEE transactions on cybernetics |
container_volume | 53 |
creator | Pham, Phu Nguyen, Loan T. T. Nguyen, Ngoc-Thanh Pedrycz, Witold Yun, Unil Lin, Jerry Chun-Wei Vo, Bay |
description | Recent studies on heterogeneous information network (HIN) embedding-based recommendations have encountered challenges. These challenges are related to the data heterogeneity of the associated unstructured attribute or content (e.g., text-based summary/description) of users and items in the context of HIN. In order to address these challenges, in this article, we propose a novel approach of semantic-aware HIN embedding-based recommendation, called SemHE4Rec. In our proposed SemHE4Rec model, we define two embedding techniques for efficiently learning the representations of both users and items in the context of HIN. These rich-structural user and item representations are then used to facilitate the matrix factorization (MF) process. The first embedding technique is a traditional co-occurrence representation learning (CoRL) approach which aims to learn the co-occurrence of structural features of users and items. These structural features are represented for their interconnections in terms of meta-paths. In order to do that, we adopt the well-known meta-path-based random walk strategy and heterogeneous Skip-gram architecture. The second embedding approach is a semantic-aware representation learning (SRL) method. The SRL embedding technique is designed to focus on capturing the unstructured semantic relations between users and item content for the recommendation task. Finally, all the learned representations of users and items are then jointly combined and optimized while integrating with the extended MF for the recommendation task. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed SemHE4Rec in comparison with the recent state-of-the-art HIN embedding-based recommendation techniques, and reveal that the joint text-based and co-occurrence-based representation learning can help to improve the recommendation performance. |
doi_str_mv | 10.1109/TCYB.2022.3233819 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TCYB_2022_3233819</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10025389</ieee_id><sourcerecordid>2797144894</sourcerecordid><originalsourceid>FETCH-LOGICAL-c350t-5cc888b5698a44055c55a392fff1b843df29136ada1005c9d94e96a54d9c82683</originalsourceid><addsrcrecordid>eNpdkE1LAzEQhoMoWrQ_QBAJePGyNZ-7ybEWtYIo2HrwFNLsrG7tbmqyRfz3praKmMuE8MybmQehY0oGlBJ9MR09Xw4YYWzAGeeK6h3UYzRXGWOF3P2958UB6sc4J-mo9KTVPjrgBWFUK9FDT8MWD5fL4K17xZ3HE2hs29UuG37YAHgMHQT_Ai34VcT30H348IavmhmUZd2-4MoH_AjONw20JQQ8-YwdNPEI7VV2EaG_rYfo6fpqOhpndw83t6PhXea4JF0mnVNKzWSulRWCSOmktFyzqqroTAleVkxTntvSUkKk06UWoHMrRamdYrnih-h8k5sWeF9B7ExTRweLhf0e2LBCF1QIpUVCz_6hc78KbZrOMCU5YUXBZKLohnLBxxigMstQNzZ8GkrMWrtZazdr7WarPfWcbpNXswbK344fyQk42QA1APwJJOlDpfkXykaE5Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2853027725</pqid></control><display><type>article</type><title>An Approach to Semantic-Aware Heterogeneous Network Embedding for Recommender Systems</title><source>IEEE Electronic Library (IEL)</source><creator>Pham, Phu ; Nguyen, Loan T. T. ; Nguyen, Ngoc-Thanh ; Pedrycz, Witold ; Yun, Unil ; Lin, Jerry Chun-Wei ; Vo, Bay</creator><creatorcontrib>Pham, Phu ; Nguyen, Loan T. T. ; Nguyen, Ngoc-Thanh ; Pedrycz, Witold ; Yun, Unil ; Lin, Jerry Chun-Wei ; Vo, Bay</creatorcontrib><description>Recent studies on heterogeneous information network (HIN) embedding-based recommendations have encountered challenges. These challenges are related to the data heterogeneity of the associated unstructured attribute or content (e.g., text-based summary/description) of users and items in the context of HIN. In order to address these challenges, in this article, we propose a novel approach of semantic-aware HIN embedding-based recommendation, called SemHE4Rec. In our proposed SemHE4Rec model, we define two embedding techniques for efficiently learning the representations of both users and items in the context of HIN. These rich-structural user and item representations are then used to facilitate the matrix factorization (MF) process. The first embedding technique is a traditional co-occurrence representation learning (CoRL) approach which aims to learn the co-occurrence of structural features of users and items. These structural features are represented for their interconnections in terms of meta-paths. In order to do that, we adopt the well-known meta-path-based random walk strategy and heterogeneous Skip-gram architecture. The second embedding approach is a semantic-aware representation learning (SRL) method. The SRL embedding technique is designed to focus on capturing the unstructured semantic relations between users and item content for the recommendation task. Finally, all the learned representations of users and items are then jointly combined and optimized while integrating with the extended MF for the recommendation task. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed SemHE4Rec in comparison with the recent state-of-the-art HIN embedding-based recommendation techniques, and reveal that the joint text-based and co-occurrence-based representation learning can help to improve the recommendation performance.</description><identifier>ISSN: 2168-2267</identifier><identifier>EISSN: 2168-2275</identifier><identifier>DOI: 10.1109/TCYB.2022.3233819</identifier><identifier>PMID: 37021984</identifier><identifier>CODEN: ITCEB8</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Context ; Data mining ; Electronic mail ; Embedding ; Feature extraction ; Heterogeneity ; Heterogeneous information network (HIN) ; Learning ; network embedding ; Random walk ; recommendation system ; Recommender systems ; Representation learning ; Representations ; Semantics ; Task analysis</subject><ispartof>IEEE transactions on cybernetics, 2023-09, Vol.53 (9), p.6027-6040</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c350t-5cc888b5698a44055c55a392fff1b843df29136ada1005c9d94e96a54d9c82683</citedby><cites>FETCH-LOGICAL-c350t-5cc888b5698a44055c55a392fff1b843df29136ada1005c9d94e96a54d9c82683</cites><orcidid>0000-0001-8768-9709 ; 0000-0001-6440-6462 ; 0000-0002-9335-9930 ; 0000-0002-9246-4587 ; 0000-0002-0701-5438 ; 0000-0002-3720-0861 ; 0000-0002-3247-2948</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10025389$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10025389$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37021984$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Pham, Phu</creatorcontrib><creatorcontrib>Nguyen, Loan T. T.</creatorcontrib><creatorcontrib>Nguyen, Ngoc-Thanh</creatorcontrib><creatorcontrib>Pedrycz, Witold</creatorcontrib><creatorcontrib>Yun, Unil</creatorcontrib><creatorcontrib>Lin, Jerry Chun-Wei</creatorcontrib><creatorcontrib>Vo, Bay</creatorcontrib><title>An Approach to Semantic-Aware Heterogeneous Network Embedding for Recommender Systems</title><title>IEEE transactions on cybernetics</title><addtitle>TCYB</addtitle><addtitle>IEEE Trans Cybern</addtitle><description>Recent studies on heterogeneous information network (HIN) embedding-based recommendations have encountered challenges. These challenges are related to the data heterogeneity of the associated unstructured attribute or content (e.g., text-based summary/description) of users and items in the context of HIN. In order to address these challenges, in this article, we propose a novel approach of semantic-aware HIN embedding-based recommendation, called SemHE4Rec. In our proposed SemHE4Rec model, we define two embedding techniques for efficiently learning the representations of both users and items in the context of HIN. These rich-structural user and item representations are then used to facilitate the matrix factorization (MF) process. The first embedding technique is a traditional co-occurrence representation learning (CoRL) approach which aims to learn the co-occurrence of structural features of users and items. These structural features are represented for their interconnections in terms of meta-paths. In order to do that, we adopt the well-known meta-path-based random walk strategy and heterogeneous Skip-gram architecture. The second embedding approach is a semantic-aware representation learning (SRL) method. The SRL embedding technique is designed to focus on capturing the unstructured semantic relations between users and item content for the recommendation task. Finally, all the learned representations of users and items are then jointly combined and optimized while integrating with the extended MF for the recommendation task. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed SemHE4Rec in comparison with the recent state-of-the-art HIN embedding-based recommendation techniques, and reveal that the joint text-based and co-occurrence-based representation learning can help to improve the recommendation performance.</description><subject>Context</subject><subject>Data mining</subject><subject>Electronic mail</subject><subject>Embedding</subject><subject>Feature extraction</subject><subject>Heterogeneity</subject><subject>Heterogeneous information network (HIN)</subject><subject>Learning</subject><subject>network embedding</subject><subject>Random walk</subject><subject>recommendation system</subject><subject>Recommender systems</subject><subject>Representation learning</subject><subject>Representations</subject><subject>Semantics</subject><subject>Task analysis</subject><issn>2168-2267</issn><issn>2168-2275</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkE1LAzEQhoMoWrQ_QBAJePGyNZ-7ybEWtYIo2HrwFNLsrG7tbmqyRfz3praKmMuE8MybmQehY0oGlBJ9MR09Xw4YYWzAGeeK6h3UYzRXGWOF3P2958UB6sc4J-mo9KTVPjrgBWFUK9FDT8MWD5fL4K17xZ3HE2hs29UuG37YAHgMHQT_Ai34VcT30H348IavmhmUZd2-4MoH_AjONw20JQQ8-YwdNPEI7VV2EaG_rYfo6fpqOhpndw83t6PhXea4JF0mnVNKzWSulRWCSOmktFyzqqroTAleVkxTntvSUkKk06UWoHMrRamdYrnih-h8k5sWeF9B7ExTRweLhf0e2LBCF1QIpUVCz_6hc78KbZrOMCU5YUXBZKLohnLBxxigMstQNzZ8GkrMWrtZazdr7WarPfWcbpNXswbK344fyQk42QA1APwJJOlDpfkXykaE5Q</recordid><startdate>20230901</startdate><enddate>20230901</enddate><creator>Pham, Phu</creator><creator>Nguyen, Loan T. T.</creator><creator>Nguyen, Ngoc-Thanh</creator><creator>Pedrycz, Witold</creator><creator>Yun, Unil</creator><creator>Lin, Jerry Chun-Wei</creator><creator>Vo, Bay</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-8768-9709</orcidid><orcidid>https://orcid.org/0000-0001-6440-6462</orcidid><orcidid>https://orcid.org/0000-0002-9335-9930</orcidid><orcidid>https://orcid.org/0000-0002-9246-4587</orcidid><orcidid>https://orcid.org/0000-0002-0701-5438</orcidid><orcidid>https://orcid.org/0000-0002-3720-0861</orcidid><orcidid>https://orcid.org/0000-0002-3247-2948</orcidid></search><sort><creationdate>20230901</creationdate><title>An Approach to Semantic-Aware Heterogeneous Network Embedding for Recommender Systems</title><author>Pham, Phu ; Nguyen, Loan T. T. ; Nguyen, Ngoc-Thanh ; Pedrycz, Witold ; Yun, Unil ; Lin, Jerry Chun-Wei ; Vo, Bay</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c350t-5cc888b5698a44055c55a392fff1b843df29136ada1005c9d94e96a54d9c82683</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Context</topic><topic>Data mining</topic><topic>Electronic mail</topic><topic>Embedding</topic><topic>Feature extraction</topic><topic>Heterogeneity</topic><topic>Heterogeneous information network (HIN)</topic><topic>Learning</topic><topic>network embedding</topic><topic>Random walk</topic><topic>recommendation system</topic><topic>Recommender systems</topic><topic>Representation learning</topic><topic>Representations</topic><topic>Semantics</topic><topic>Task analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Pham, Phu</creatorcontrib><creatorcontrib>Nguyen, Loan T. T.</creatorcontrib><creatorcontrib>Nguyen, Ngoc-Thanh</creatorcontrib><creatorcontrib>Pedrycz, Witold</creatorcontrib><creatorcontrib>Yun, Unil</creatorcontrib><creatorcontrib>Lin, Jerry Chun-Wei</creatorcontrib><creatorcontrib>Vo, Bay</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on cybernetics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Pham, Phu</au><au>Nguyen, Loan T. T.</au><au>Nguyen, Ngoc-Thanh</au><au>Pedrycz, Witold</au><au>Yun, Unil</au><au>Lin, Jerry Chun-Wei</au><au>Vo, Bay</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An Approach to Semantic-Aware Heterogeneous Network Embedding for Recommender Systems</atitle><jtitle>IEEE transactions on cybernetics</jtitle><stitle>TCYB</stitle><addtitle>IEEE Trans Cybern</addtitle><date>2023-09-01</date><risdate>2023</risdate><volume>53</volume><issue>9</issue><spage>6027</spage><epage>6040</epage><pages>6027-6040</pages><issn>2168-2267</issn><eissn>2168-2275</eissn><coden>ITCEB8</coden><abstract>Recent studies on heterogeneous information network (HIN) embedding-based recommendations have encountered challenges. These challenges are related to the data heterogeneity of the associated unstructured attribute or content (e.g., text-based summary/description) of users and items in the context of HIN. In order to address these challenges, in this article, we propose a novel approach of semantic-aware HIN embedding-based recommendation, called SemHE4Rec. In our proposed SemHE4Rec model, we define two embedding techniques for efficiently learning the representations of both users and items in the context of HIN. These rich-structural user and item representations are then used to facilitate the matrix factorization (MF) process. The first embedding technique is a traditional co-occurrence representation learning (CoRL) approach which aims to learn the co-occurrence of structural features of users and items. These structural features are represented for their interconnections in terms of meta-paths. In order to do that, we adopt the well-known meta-path-based random walk strategy and heterogeneous Skip-gram architecture. The second embedding approach is a semantic-aware representation learning (SRL) method. The SRL embedding technique is designed to focus on capturing the unstructured semantic relations between users and item content for the recommendation task. Finally, all the learned representations of users and items are then jointly combined and optimized while integrating with the extended MF for the recommendation task. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed SemHE4Rec in comparison with the recent state-of-the-art HIN embedding-based recommendation techniques, and reveal that the joint text-based and co-occurrence-based representation learning can help to improve the recommendation performance.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>37021984</pmid><doi>10.1109/TCYB.2022.3233819</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0001-8768-9709</orcidid><orcidid>https://orcid.org/0000-0001-6440-6462</orcidid><orcidid>https://orcid.org/0000-0002-9335-9930</orcidid><orcidid>https://orcid.org/0000-0002-9246-4587</orcidid><orcidid>https://orcid.org/0000-0002-0701-5438</orcidid><orcidid>https://orcid.org/0000-0002-3720-0861</orcidid><orcidid>https://orcid.org/0000-0002-3247-2948</orcidid></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 2168-2267 |
ispartof | IEEE transactions on cybernetics, 2023-09, Vol.53 (9), p.6027-6040 |
issn | 2168-2267 2168-2275 |
language | eng |
recordid | cdi_crossref_primary_10_1109_TCYB_2022_3233819 |
source | IEEE Electronic Library (IEL) |
subjects | Context Data mining Electronic mail Embedding Feature extraction Heterogeneity Heterogeneous information network (HIN) Learning network embedding Random walk recommendation system Recommender systems Representation learning Representations Semantics Task analysis |
title | An Approach to Semantic-Aware Heterogeneous Network Embedding for Recommender Systems |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T20%3A41%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20Approach%20to%20Semantic-Aware%20Heterogeneous%20Network%20Embedding%20for%20Recommender%20Systems&rft.jtitle=IEEE%20transactions%20on%20cybernetics&rft.au=Pham,%20Phu&rft.date=2023-09-01&rft.volume=53&rft.issue=9&rft.spage=6027&rft.epage=6040&rft.pages=6027-6040&rft.issn=2168-2267&rft.eissn=2168-2275&rft.coden=ITCEB8&rft_id=info:doi/10.1109/TCYB.2022.3233819&rft_dat=%3Cproquest_RIE%3E2797144894%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2853027725&rft_id=info:pmid/37021984&rft_ieee_id=10025389&rfr_iscdi=true |