{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:49:36Z","timestamp":1777704576304,"version":"3.51.4"},"reference-count":40,"publisher":"SAGE Publications","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2021,4,22]]},"abstract":"<jats:p>How to accurately model user preferences based on historical user behaviour and auxiliary information is of great importance in personalized recommendation tasks. Among all types of auxiliary information, knowledge graphs (KGs) are an emerging type of auxiliary information with nodes and edges that contain rich structural information and semantic information. Many studies prove that incorporating KG into personalized recommendation tasks can effectively improve the performance, rationality and interpretability of recommendations. However, existing methods either explore the independent meta-paths for user-item pairs in KGs or use a graph convolution network on all KGs to obtain embeddings for users and items separately. Although both types of methods have respective effects, the former cannot fully capture the structural information of user-item pairs in KGs, while the latter ignores the mutual effect between the target user and item during the embedding learning process. To alleviate the shortcomings of these methods, we design a graph convolution-based recommendation model called Combining User-end and Item-end Knowledge Graph Learning (CUIKG), which aims to capture the relevance between users\u2019 personalized preferences and items by jointly mining the associated attribute information in their respective KG. Specifically, we describe user embedding from a user KG and then introduce user embedding, which contains the user profile into the item KG, to describe item embedding with the method of Graph Convolution Network. Finally, we predict user preference probability for a given item via multilayer perception. CUIKG describes the connection between user-end KG and item-end KG, and mines the structural and semantic information present in KG. Experimental results with two real-world datasets demonstrate the superiority of the proposed method over existing methods.<\/jats:p>","DOI":"10.3233\/jifs-201635","type":"journal-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T19:36:32Z","timestamp":1613244992000},"page":"9213-9225","source":"Crossref","is-referenced-by-count":3,"title":["Combining user-end and item-end knowledge graph learning for personalized recommendation"],"prefix":"10.1177","volume":"40","author":[{"given":"Tianlong","family":"Gu","sequence":"first","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China"},{"name":"College of Information Science and Technology \/ College of Cyber Security, Jinan University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haohong","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenzhong","family":"Bin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-201635_ref1","doi-asserted-by":"crossref","unstructured":"Lian D. , Zheng V.W. and Xie X. , Collaborative filtering meets next check-in location prediction, WWW (Companion Volume), 2013, 231\u2013232.","DOI":"10.1145\/2487788.2487907"},{"key":"10.3233\/JIFS-201635_ref2","first-page":"635","article-title":"Lars Schmidt-Thieme: Fast context-aware recommendations with factorization machines","volume":"2011","author":"Rendle","journal-title":"SIGIR"},{"key":"10.3233\/JIFS-201635_ref3","first-page":"1721","article-title":"Content-Aware Point of Interest Recommendation on Location-Based Social Networks","volume":"2015","author":"Gao","journal-title":"AAAI"},{"key":"10.3233\/JIFS-201635_ref4","first-page":"505","article-title":"Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks","volume":"2018","author":"Huang","journal-title":"SIGIR"},{"key":"10.3233\/JIFS-201635_ref5","first-page":"1835","article-title":"DKN: Deep Knowledge-Aware Network for News Recommendation","volume":"2018","author":"Wang","journal-title":"WWW"},{"key":"10.3233\/JIFS-201635_ref6","first-page":"4264","article-title":"STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems","volume":"2019","author":"Zhang","journal-title":"IJCAI"},{"key":"10.3233\/JIFS-201635_ref7","first-page":"1721","article-title":"Content-Aware Point of Interest Recommendation on Location-Based Social Networks","volume":"2015","author":"Gao","journal-title":"AAAI"},{"key":"10.3233\/JIFS-201635_ref8","first-page":"283","article-title":"Personalized entity recommendation: a heterogeneous information network approach","volume":"2014","author":"Yu","journal-title":"WSDM"},{"key":"10.3233\/JIFS-201635_ref9","first-page":"635","article-title":"Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks","volume":"2017","author":"Zhao","journal-title":"KDD"},{"key":"10.3233\/JIFS-201635_ref10","first-page":"108","article-title":"Sequential Recommendation with User Memory Networks","volume":"2018","author":"Chen","journal-title":"WSDM"},{"key":"10.3233\/JIFS-201635_ref11","first-page":"355","article-title":"Neural Factorization Machines for Sparse Predictive Analytics","volume":"2017","author":"He","journal-title":"SIGIR"},{"key":"10.3233\/JIFS-201635_ref12","first-page":"355","article-title":"Adversarial Personalized Ranking for Recommendation","volume":"2018","author":"He","journal-title":"SIGIR"},{"key":"10.3233\/JIFS-201635_ref13","first-page":"265","article-title":"Improved Deep Walk Algorithm Based on Preference Random Walk","volume":"2019","author":"Ye","journal-title":"NLPCC"},{"key":"10.3233\/JIFS-201635_ref14","first-page":"153","article-title":"Combining Language and Vision with a Multimodal Skip-gram Model","volume":"2015","author":"Lazaridou","journal-title":"HLT-NAACL"},{"key":"10.3233\/JIFS-201635_ref15","first-page":"1067","article-title":"LINE: Large-scale Information Network Embedding","volume":"2015","author":"Tang","journal-title":"WWW"},{"key":"10.3233\/JIFS-201635_ref16","first-page":"855","article-title":"node2vec: Scalable Feature Learning for Networks","volume":"2016","author":"Grover","journal-title":"KDD"},{"key":"10.3233\/JIFS-201635_ref17","first-page":"1188","article-title":"Distributed Representations of Sentences and Documents","volume":"2014","author":"Le","journal-title":"ICML"},{"key":"10.3233\/JIFS-201635_ref18","first-page":"2787","article-title":"Translating Embeddings for Modeling Multi-relational Data","volume":"2013","author":"Bordes","journal-title":"NIPS"},{"key":"10.3233\/JIFS-201635_ref19","first-page":"2181","article-title":"Learning Entity and Relation Embeddings for Knowledge Graph Completion","volume":"2015","author":"Lin","journal-title":"AAAI"},{"key":"10.3233\/JIFS-201635_ref20","first-page":"4264","article-title":"STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems","volume":"2019","author":"Zhang","journal-title":"IJCAI"},{"key":"10.3233\/JIFS-201635_ref21","first-page":"5329","article-title":"Explainable Reasoning over Knowledge Graphs for Recommendation","volume":"2019","author":"Wang","journal-title":"AAAI"},{"key":"10.3233\/JIFS-201635_ref22","first-page":"974","article-title":"Graph Convolutional Neural Networks for Web-Scale Recommender Systems","volume":"2018","author":"Ying","journal-title":"KDD"},{"key":"10.3233\/JIFS-201635_ref23","first-page":"4869","article-title":"Hyperbolic Graph Convolutional Neural Networks","volume":"2019","author":"Chami","journal-title":"Neur IPS"},{"key":"10.3233\/JIFS-201635_ref24","first-page":"353","article-title":"Collaborative Knowledge Base Embedding for Recommender Systems","volume":"2016","author":"Zhang","journal-title":"KDD"},{"key":"10.3233\/JIFS-201635_ref25","first-page":"84","article-title":"Semantically Smooth Knowledge Graph Embedding","volume":"2015","author":"Guo","journal-title":"ACL"},{"key":"10.3233\/JIFS-201635_ref26","first-page":"417","article-title":"RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems","volume":"2018","author":"Wang","journal-title":"CIKM"},{"key":"10.3233\/JIFS-201635_ref27","first-page":"3307","article-title":"Knowledge Graph Convolutional Networks for Recommender Systems","volume":"2019","author":"Wang","journal-title":"WWW"},{"key":"10.3233\/JIFS-201635_ref28","first-page":"950","article-title":"KGAT: Knowledge Graph Attention Network for Recommendation","volume":"2019","author":"Wang","journal-title":"KDD"},{"issue":"12","key":"10.3233\/JIFS-201635_ref29","doi-asserted-by":"crossref","first-page":"2724","DOI":"10.1109\/TKDE.2017.2754499","article-title":"Knowledge Graph Embedding: A Survey of Approaches and Applications","volume":"29","author":"Wang","year":"2017","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"10.3233\/JIFS-201635_ref31","first-page":"3837","article-title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","volume":"2016","author":"Defferrard","journal-title":"NIPS"},{"key":"10.3233\/JIFS-201635_ref32","first-page":"1024","article-title":"Inductive Representation Learning on Large Graphs","volume":"2017","author":"Hamilton","journal-title":"NIPS"},{"key":"10.3233\/JIFS-201635_ref34","first-page":"426","article-title":"Factorization meets the neighborhood: a multifaceted collaborative filtering model","volume":"2008","author":"Koren","journal-title":"KDD"},{"issue":"3","key":"10.3233\/JIFS-201635_ref35","doi-asserted-by":"crossref","first-page":"57:1","DOI":"10.1145\/2168752.2168771","article-title":"Factorization Machines with libFM","volume":"3","author":"Rendle","year":"2012","journal-title":"ACM Trans Intell Syst Technol"},{"key":"10.3233\/JIFS-201635_ref36","first-page":"353","article-title":"Collaborative Knowledge Base Embedding for Recommender Systems","volume":"2016","author":"Zhang","journal-title":"KDD"},{"key":"10.3233\/JIFS-201635_ref37","first-page":"285","article-title":"Reinforcement Knowledge Graph Reasoning for Explainable Recommendation","volume":"2019","author":"Xian","journal-title":"SIGIR"},{"key":"10.3233\/JIFS-201635_ref38","first-page":"3697","article-title":"Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks","volume":"2017","author":"Monti","journal-title":"NIPS"},{"key":"10.3233\/JIFS-201635_ref39","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.dss.2015.03.008","article-title":"Recommender system application developments: A survey","volume":"74","author":"Lu","year":"2015","journal-title":"Decis Support Syst"},{"key":"10.3233\/JIFS-201635_ref40","first-page":"2347","article-title":"Intent GC: A Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation","volume":"2019","author":"Zhao","journal-title":"KDD"},{"key":"10.3233\/JIFS-201635_ref41","first-page":"639","article-title":"LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation","volume":"2020","author":"He","journal-title":"SIGIR"},{"key":"10.3233\/JIFS-201635_ref43","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.knosys.2013.03.012","article-title":"Recommender systems survey","volume":"46","author":"Bobadilla","year":"2013","journal-title":"Knowl Based Syst"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-201635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:41:31Z","timestamp":1777455691000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-201635"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,22]]},"references-count":40,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/jifs-201635","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,22]]}}}