Loading…

Overcoming Data Sparsity in Group Recommendation

It has been an important task for recommender systems to suggest satisfying activities to a group of users in people's daily social life. The major challenge in this task is how to aggregate personal preferences of group members to infer the decision of a group. Conventional group recommendatio...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on knowledge and data engineering 2022-07, Vol.34 (7), p.3447-3460
Main Authors: Yin, Hongzhi, Wang, Qinyong, Zheng, Kai, Li, Zhixu, Zhou, Xiaofang
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c293t-4dacdd8e1017539f46ead97c6033ed2e0baafff00f7d47d3e1d464f842630e853
cites cdi_FETCH-LOGICAL-c293t-4dacdd8e1017539f46ead97c6033ed2e0baafff00f7d47d3e1d464f842630e853
container_end_page 3460
container_issue 7
container_start_page 3447
container_title IEEE transactions on knowledge and data engineering
container_volume 34
creator Yin, Hongzhi
Wang, Qinyong
Zheng, Kai
Li, Zhixu
Zhou, Xiaofang
description It has been an important task for recommender systems to suggest satisfying activities to a group of users in people's daily social life. The major challenge in this task is how to aggregate personal preferences of group members to infer the decision of a group. Conventional group recommendation methods applied a predefined strategy for preference aggregation. However, these static strategies are too simple to model the real and complex process of group decision-making, especially for occasional groups which are formed ad-hoc. Moreover, group members should have non-uniform influences or weights in a group, and the weight of a user can be varied in different groups. Therefore, an ideal group recommender system should be able to accurately learn not only users' personal preferences but also the preference aggregation strategy from data. In this paper, we propose a novel end-to-end group recommender system named CAGR (short for " C entrality- A ware G roup R ecommender"), which takes Bipartite Graph Embedding Model (BGEM), the self-attention mechanism and Graph Convolutional Networks (GCNs) as basic building blocks to learn group and user representations in a unified way. Specifically, we first extend BGEM to model group-item interactions, and then in order to overcome the limitation and sparsity of the interaction data generated by occasional groups, we propose a self-attentive mechanism to represent groups based on the group members. In addition, to overcome the sparsity issue of user-item interaction data, we leverage the user social networks to enhance user representation learning, obtaining centrality-aware user representations. To further alleviate the group data sparsity problem, we propose two model optimization approaches to seamlessly integrate the user representations learning process. We create three large-scale benchmark datasets and conduct extensive experiments on them. The experimental results show the superiority of our proposed CAGR by comparing it with state-of-the-art group recommender models.
doi_str_mv 10.1109/TKDE.2020.3023787
format article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_2672805395</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9195784</ieee_id><sourcerecordid>2672805395</sourcerecordid><originalsourceid>FETCH-LOGICAL-c293t-4dacdd8e1017539f46ead97c6033ed2e0baafff00f7d47d3e1d464f842630e853</originalsourceid><addsrcrecordid>eNo9kFFLwzAQx4MoOKcfQHwp-Nx6l6RN-ijbnOJgoPM5xOYiHa6tSSfs29uy4dMd3O__P_gxdouQIUL5sHmdLzIOHDIBXCitztgE81ynHEs8H3aQmEoh1SW7inELAFppnDBY_1Ko2l3dfCVz29vkvbMh1v0hqZtkGdp9l7zRcN9R42xft801u_D2O9LNaU7Zx9NiM3tOV-vly-xxlVa8FH0qna2c04SAKhellwVZV6qqACHIcYJPa733AF45qZwgdLKQXkteCCCdiym7P_Z2of3ZU-zNtt2HZnhpeKG4hqF1pPBIVaGNMZA3Xah3NhwMghnFmFGMGcWYk5ghc3fM1ET0z5dY5kpL8QePol4e</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2672805395</pqid></control><display><type>article</type><title>Overcoming Data Sparsity in Group Recommendation</title><source>IEEE Xplore (Online service)</source><creator>Yin, Hongzhi ; Wang, Qinyong ; Zheng, Kai ; Li, Zhixu ; Zhou, Xiaofang</creator><creatorcontrib>Yin, Hongzhi ; Wang, Qinyong ; Zheng, Kai ; Li, Zhixu ; Zhou, Xiaofang</creatorcontrib><description>It has been an important task for recommender systems to suggest satisfying activities to a group of users in people's daily social life. The major challenge in this task is how to aggregate personal preferences of group members to infer the decision of a group. Conventional group recommendation methods applied a predefined strategy for preference aggregation. However, these static strategies are too simple to model the real and complex process of group decision-making, especially for occasional groups which are formed ad-hoc. Moreover, group members should have non-uniform influences or weights in a group, and the weight of a user can be varied in different groups. Therefore, an ideal group recommender system should be able to accurately learn not only users' personal preferences but also the preference aggregation strategy from data. In this paper, we propose a novel end-to-end group recommender system named CAGR (short for " C entrality- A ware G roup R ecommender"), which takes Bipartite Graph Embedding Model (BGEM), the self-attention mechanism and Graph Convolutional Networks (GCNs) as basic building blocks to learn group and user representations in a unified way. Specifically, we first extend BGEM to model group-item interactions, and then in order to overcome the limitation and sparsity of the interaction data generated by occasional groups, we propose a self-attentive mechanism to represent groups based on the group members. In addition, to overcome the sparsity issue of user-item interaction data, we leverage the user social networks to enhance user representation learning, obtaining centrality-aware user representations. To further alleviate the group data sparsity problem, we propose two model optimization approaches to seamlessly integrate the user representations learning process. We create three large-scale benchmark datasets and conduct extensive experiments on them. The experimental results show the superiority of our proposed CAGR by comparing it with state-of-the-art group recommender models.</description><identifier>ISSN: 1041-4347</identifier><identifier>EISSN: 1558-2191</identifier><identifier>DOI: 10.1109/TKDE.2020.3023787</identifier><identifier>CODEN: ITKEEH</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Agglomeration ; Aggregates ; Bipartite graph ; Data models ; data sparsity ; Decision making ; Graph theory ; group recommendation ; Learning ; network embedding ; Optimization ; Preferences ; Recommender system ; Recommender systems ; Representations ; Social network services ; Social networks ; Sparsity ; Task analysis</subject><ispartof>IEEE transactions on knowledge and data engineering, 2022-07, Vol.34 (7), p.3447-3460</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c293t-4dacdd8e1017539f46ead97c6033ed2e0baafff00f7d47d3e1d464f842630e853</citedby><cites>FETCH-LOGICAL-c293t-4dacdd8e1017539f46ead97c6033ed2e0baafff00f7d47d3e1d464f842630e853</cites><orcidid>0000-0001-6343-1455 ; 0000-0003-1395-261X ; 0000-0002-0217-3998 ; 0000-0003-2355-288X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9195784$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,54796</link.rule.ids></links><search><creatorcontrib>Yin, Hongzhi</creatorcontrib><creatorcontrib>Wang, Qinyong</creatorcontrib><creatorcontrib>Zheng, Kai</creatorcontrib><creatorcontrib>Li, Zhixu</creatorcontrib><creatorcontrib>Zhou, Xiaofang</creatorcontrib><title>Overcoming Data Sparsity in Group Recommendation</title><title>IEEE transactions on knowledge and data engineering</title><addtitle>TKDE</addtitle><description>It has been an important task for recommender systems to suggest satisfying activities to a group of users in people's daily social life. The major challenge in this task is how to aggregate personal preferences of group members to infer the decision of a group. Conventional group recommendation methods applied a predefined strategy for preference aggregation. However, these static strategies are too simple to model the real and complex process of group decision-making, especially for occasional groups which are formed ad-hoc. Moreover, group members should have non-uniform influences or weights in a group, and the weight of a user can be varied in different groups. Therefore, an ideal group recommender system should be able to accurately learn not only users' personal preferences but also the preference aggregation strategy from data. In this paper, we propose a novel end-to-end group recommender system named CAGR (short for " C entrality- A ware G roup R ecommender"), which takes Bipartite Graph Embedding Model (BGEM), the self-attention mechanism and Graph Convolutional Networks (GCNs) as basic building blocks to learn group and user representations in a unified way. Specifically, we first extend BGEM to model group-item interactions, and then in order to overcome the limitation and sparsity of the interaction data generated by occasional groups, we propose a self-attentive mechanism to represent groups based on the group members. In addition, to overcome the sparsity issue of user-item interaction data, we leverage the user social networks to enhance user representation learning, obtaining centrality-aware user representations. To further alleviate the group data sparsity problem, we propose two model optimization approaches to seamlessly integrate the user representations learning process. We create three large-scale benchmark datasets and conduct extensive experiments on them. The experimental results show the superiority of our proposed CAGR by comparing it with state-of-the-art group recommender models.</description><subject>Agglomeration</subject><subject>Aggregates</subject><subject>Bipartite graph</subject><subject>Data models</subject><subject>data sparsity</subject><subject>Decision making</subject><subject>Graph theory</subject><subject>group recommendation</subject><subject>Learning</subject><subject>network embedding</subject><subject>Optimization</subject><subject>Preferences</subject><subject>Recommender system</subject><subject>Recommender systems</subject><subject>Representations</subject><subject>Social network services</subject><subject>Social networks</subject><subject>Sparsity</subject><subject>Task analysis</subject><issn>1041-4347</issn><issn>1558-2191</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNo9kFFLwzAQx4MoOKcfQHwp-Nx6l6RN-ijbnOJgoPM5xOYiHa6tSSfs29uy4dMd3O__P_gxdouQIUL5sHmdLzIOHDIBXCitztgE81ynHEs8H3aQmEoh1SW7inELAFppnDBY_1Ko2l3dfCVz29vkvbMh1v0hqZtkGdp9l7zRcN9R42xft801u_D2O9LNaU7Zx9NiM3tOV-vly-xxlVa8FH0qna2c04SAKhellwVZV6qqACHIcYJPa733AF45qZwgdLKQXkteCCCdiym7P_Z2of3ZU-zNtt2HZnhpeKG4hqF1pPBIVaGNMZA3Xah3NhwMghnFmFGMGcWYk5ghc3fM1ET0z5dY5kpL8QePol4e</recordid><startdate>20220701</startdate><enddate>20220701</enddate><creator>Yin, Hongzhi</creator><creator>Wang, Qinyong</creator><creator>Zheng, Kai</creator><creator>Li, Zhixu</creator><creator>Zhou, Xiaofang</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>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0001-6343-1455</orcidid><orcidid>https://orcid.org/0000-0003-1395-261X</orcidid><orcidid>https://orcid.org/0000-0002-0217-3998</orcidid><orcidid>https://orcid.org/0000-0003-2355-288X</orcidid></search><sort><creationdate>20220701</creationdate><title>Overcoming Data Sparsity in Group Recommendation</title><author>Yin, Hongzhi ; Wang, Qinyong ; Zheng, Kai ; Li, Zhixu ; Zhou, Xiaofang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c293t-4dacdd8e1017539f46ead97c6033ed2e0baafff00f7d47d3e1d464f842630e853</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Agglomeration</topic><topic>Aggregates</topic><topic>Bipartite graph</topic><topic>Data models</topic><topic>data sparsity</topic><topic>Decision making</topic><topic>Graph theory</topic><topic>group recommendation</topic><topic>Learning</topic><topic>network embedding</topic><topic>Optimization</topic><topic>Preferences</topic><topic>Recommender system</topic><topic>Recommender systems</topic><topic>Representations</topic><topic>Social network services</topic><topic>Social networks</topic><topic>Sparsity</topic><topic>Task analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yin, Hongzhi</creatorcontrib><creatorcontrib>Wang, Qinyong</creatorcontrib><creatorcontrib>Zheng, Kai</creatorcontrib><creatorcontrib>Li, Zhixu</creatorcontrib><creatorcontrib>Zhou, Xiaofang</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 Online</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research 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><jtitle>IEEE transactions on knowledge and data engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yin, Hongzhi</au><au>Wang, Qinyong</au><au>Zheng, Kai</au><au>Li, Zhixu</au><au>Zhou, Xiaofang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Overcoming Data Sparsity in Group Recommendation</atitle><jtitle>IEEE transactions on knowledge and data engineering</jtitle><stitle>TKDE</stitle><date>2022-07-01</date><risdate>2022</risdate><volume>34</volume><issue>7</issue><spage>3447</spage><epage>3460</epage><pages>3447-3460</pages><issn>1041-4347</issn><eissn>1558-2191</eissn><coden>ITKEEH</coden><abstract>It has been an important task for recommender systems to suggest satisfying activities to a group of users in people's daily social life. The major challenge in this task is how to aggregate personal preferences of group members to infer the decision of a group. Conventional group recommendation methods applied a predefined strategy for preference aggregation. However, these static strategies are too simple to model the real and complex process of group decision-making, especially for occasional groups which are formed ad-hoc. Moreover, group members should have non-uniform influences or weights in a group, and the weight of a user can be varied in different groups. Therefore, an ideal group recommender system should be able to accurately learn not only users' personal preferences but also the preference aggregation strategy from data. In this paper, we propose a novel end-to-end group recommender system named CAGR (short for " C entrality- A ware G roup R ecommender"), which takes Bipartite Graph Embedding Model (BGEM), the self-attention mechanism and Graph Convolutional Networks (GCNs) as basic building blocks to learn group and user representations in a unified way. Specifically, we first extend BGEM to model group-item interactions, and then in order to overcome the limitation and sparsity of the interaction data generated by occasional groups, we propose a self-attentive mechanism to represent groups based on the group members. In addition, to overcome the sparsity issue of user-item interaction data, we leverage the user social networks to enhance user representation learning, obtaining centrality-aware user representations. To further alleviate the group data sparsity problem, we propose two model optimization approaches to seamlessly integrate the user representations learning process. We create three large-scale benchmark datasets and conduct extensive experiments on them. The experimental results show the superiority of our proposed CAGR by comparing it with state-of-the-art group recommender models.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TKDE.2020.3023787</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0001-6343-1455</orcidid><orcidid>https://orcid.org/0000-0003-1395-261X</orcidid><orcidid>https://orcid.org/0000-0002-0217-3998</orcidid><orcidid>https://orcid.org/0000-0003-2355-288X</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1041-4347
ispartof IEEE transactions on knowledge and data engineering, 2022-07, Vol.34 (7), p.3447-3460
issn 1041-4347
1558-2191
language eng
recordid cdi_proquest_journals_2672805395
source IEEE Xplore (Online service)
subjects Agglomeration
Aggregates
Bipartite graph
Data models
data sparsity
Decision making
Graph theory
group recommendation
Learning
network embedding
Optimization
Preferences
Recommender system
Recommender systems
Representations
Social network services
Social networks
Sparsity
Task analysis
title Overcoming Data Sparsity in Group Recommendation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T18%3A12%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Overcoming%20Data%20Sparsity%20in%20Group%20Recommendation&rft.jtitle=IEEE%20transactions%20on%20knowledge%20and%20data%20engineering&rft.au=Yin,%20Hongzhi&rft.date=2022-07-01&rft.volume=34&rft.issue=7&rft.spage=3447&rft.epage=3460&rft.pages=3447-3460&rft.issn=1041-4347&rft.eissn=1558-2191&rft.coden=ITKEEH&rft_id=info:doi/10.1109/TKDE.2020.3023787&rft_dat=%3Cproquest_ieee_%3E2672805395%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c293t-4dacdd8e1017539f46ead97c6033ed2e0baafff00f7d47d3e1d464f842630e853%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2672805395&rft_id=info:pmid/&rft_ieee_id=9195784&rfr_iscdi=true