{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T06:42:29Z","timestamp":1756190549221,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T00:00:00Z","timestamp":1682553600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T00:00:00Z","timestamp":1682553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["2017YFB1400500"],"award-info":[{"award-number":["2017YFB1400500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2023,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Heterogeneous information networks are increasingly used in recommendation algorithms. However, they lack an explicit representation of meta-paths. In using bidirectional neural interaction models for recommendation models, interaction between users and items is often ignored, with an integral impact on the accuracy of the recommendations. To better apply the interaction information, this study proposes a weight-normalized movie recommendation model (SCLW_MCRec) based on a three-way neural interaction network. The model constructs a three-way neural interaction network <jats:inline-formula><jats:alternatives><jats:tex-math>$$\\langle $$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mo>\u27e8<\/mml:mo>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>user, meta-path, item<jats:inline-formula><jats:alternatives><jats:tex-math>$$\\rangle $$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mo>\u27e9<\/mml:mo>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> from meta-path contextual information, introducing meta-paths on top of the user-item representation to represent the user-item interaction information. Introduction of a two-layer, one-dimensional convolutional neural network helps capture higher-order interaction features between the user and the item, making the model more powerful in terms of interaction. Adding a dropout layer to the interaction model and using a two-layer convolutional neural network can prevent overfitting and discard irrelevant information features to improve the recommendation. In addition, an extreme cross-entropy loss (argmaxminloss) that incorporates the properties of the argmin and argmax functions is designed to reduce the model loss. A weight-normalization optimization approach is used to better optimize the model and accelerate convergence of the stochastic gradient descent optimization. Compared to current state-of-the-art recommendation models, the SCLW_MCRec model improves the Prec evaluation index by 2.94\u201335.8%, Recall by 1.15\u201353.51%, and NDCG by 6.7\u201349.37% on the MovieLens dataset. The framework provides a significant improvement in recommendation accuracy and also solves the cold-start problem with application of interaction information.<\/jats:p>","DOI":"10.1007\/s40747-023-01066-8","type":"journal-article","created":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T12:02:51Z","timestamp":1682596971000},"page":"6241-6254","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Weight normalization optimization movie recommendation algorithm based on three-way neural interaction networks"],"prefix":"10.1007","volume":"9","author":[{"given":"Zhenlu","family":"Liang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2458-5114","authenticated-orcid":false,"given":"Zhisheng","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jingyong","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,27]]},"reference":[{"issue":"5","key":"1066_CR1","first-page":"1829","volume":"13","author":"R Sujithra Alias Kanmani","year":"2021","unstructured":"Sujithra Alias Kanmani R, Surendiran B, Ibrahim SP (2021) Recency augmented hybrid collaborative movie recommendation system. Int J Inform Technol 13(5):1829\u20131836","journal-title":"Int J Inform Technol"},{"issue":"1","key":"1066_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13278-021-00785-5","volume":"11","author":"D Roy","year":"2021","unstructured":"Roy D, Ding C (2021) Multi-source based movie recommendation with ratings and the side information. Soc Netw Anal Min 11(1):1\u201320","journal-title":"Soc Netw Anal Min"},{"key":"1066_CR3","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.neucom.2020.06.049","volume":"412","author":"Q Huang","year":"2020","unstructured":"Huang Q, Yin X, Chen S et al (2020) Robust nonnegative matrix factorization with structure regularization. Neurocomputing 412:72\u201390","journal-title":"Neurocomputing"},{"issue":"1","key":"1066_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11257-019-09245-4","volume":"30","author":"C Trattner","year":"2020","unstructured":"Trattner C, Jannach D (2020) Learning to recommend similar items from human judgments. User Model User-Adap Inter 30(1):1\u201349","journal-title":"User Model User-Adap Inter"},{"issue":"1","key":"1066_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1504\/IJES.2020.108275","volume":"13","author":"T Shao","year":"2020","unstructured":"Shao T, Chen X (2020) Hash-based and privacy-aware movie recommendations in a big data environment. Int J Embed Syst 13(1):1\u20138","journal-title":"Int J Embed Syst"},{"key":"1066_CR6","doi-asserted-by":"crossref","unstructured":"Lavanya R, Bharathi B (2021) A novel hybrid feature combination method for enhanced movie recommendations with user resemblance and attitude mining. Pers Ubiquit Comput 9: 1\u20138","DOI":"10.1007\/s00779-021-01628-y"},{"issue":"4","key":"1066_CR7","doi-asserted-by":"publisher","first-page":"104","DOI":"10.4018\/IJERTCS.2020100106","volume":"11","author":"OS Almousa","year":"2020","unstructured":"Almousa OS, Migdady H, Al-Talib M (2020) Conversational frames: improving conversation context in smart personal assistants. Int J Embed Real-Time Commun Syst (IJERTCS) 11(4):104\u2013133","journal-title":"Int J Embed Real-Time Commun Syst (IJERTCS)"},{"issue":"12","key":"1066_CR8","doi-asserted-by":"publisher","first-page":"10939","DOI":"10.1007\/s13369-020-04890-z","volume":"45","author":"N Alghamdi","year":"2020","unstructured":"Alghamdi N, Assiri F (2020) Solving the cold-start problem in recommender systems using contextual information in Arabic from calendars. Arab J Sci Eng 45(12):10939\u201310947","journal-title":"Arab J Sci Eng"},{"issue":"1","key":"1066_CR9","first-page":"1","volume":"15","author":"C Shi","year":"2021","unstructured":"Shi C, Ding J, Cao X et al (2021) Entity set expansion in knowledge graph: a heterogeneous information network perspective. Front Comp Sci 15(1):1\u201312","journal-title":"Front Comp Sci"},{"key":"1066_CR10","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.neucom.2020.08.064","volume":"420","author":"G Du","year":"2021","unstructured":"Du G, Zhang J, Li S et al (2021) Learning from class-imbalance and heterogeneous data for 30-day hospital readmission. Neurocomputing 420:27\u201335","journal-title":"Neurocomputing"},{"issue":"2","key":"1066_CR11","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1016\/j.ejor.2020.01.010","volume":"284","author":"M Gupta","year":"2020","unstructured":"Gupta M, Kumar P (2020) Recommendation generation using personalized weight of meta-paths in heterogeneous information networks. Eur J Oper Res 284(2):660\u2013674","journal-title":"Eur J Oper Res"},{"issue":"6","key":"1066_CR12","first-page":"657","volume":"71","author":"YY Lee","year":"2020","unstructured":"Lee YY, Ke H, Yen TY et al (2020) Combining and learning word embedding with WordNet for semantic relatedness and similarity measurement. J Am Soc Inf Sci 71(6):657\u2013670","journal-title":"J Am Soc Inf Sci"},{"key":"1066_CR13","doi-asserted-by":"crossref","unstructured":"DeLong KA, Kutas M (2020) Comprehending surprising sentences: sensitivity of post-N400 positivities to contextual congruity and semantic relatedness. Lang Cogn Neurosci 35(8) 1044-1063","DOI":"10.1080\/23273798.2019.1708960"},{"issue":"8","key":"1066_CR14","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.1080\/23273798.2019.1708960","volume":"35","author":"KA DeLong","year":"2020","unstructured":"DeLong KA, Kutas M (2020) Comprehending surprising sentences: sensitivity of post-N400 positivities to contextual congruity and semantic relatedness. Lang Cogn Neurosci 35(8):1044\u20131063","journal-title":"Lang Cogn Neurosci"},{"issue":"1","key":"1066_CR15","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1007\/s10489-021-02363-w","volume":"52","author":"B Hui","year":"2022","unstructured":"Hui B, Zhang L, Zhou X et al (2022) Personalized recommendation system based on knowledge embedding and historical behavior. Appl Intell 52(1):954\u2013966","journal-title":"Appl Intell"},{"issue":"1","key":"1066_CR16","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/s40009-021-01051-0","volume":"45","author":"S Airen","year":"2022","unstructured":"Airen S, Agrawal J (2022) Movie recommender system using k-nearest neighbors variants. Natl Acad Sci Lett 45(1):75\u201382","journal-title":"Natl Acad Sci Lett"},{"issue":"6","key":"1066_CR17","doi-asserted-by":"publisher","first-page":"1388","DOI":"10.1587\/transinf.2019EDP7258","volume":"103","author":"R Pan","year":"2020","unstructured":"Pan R, Ge C, Zhang L et al (2020) A new similarity model based on collaborative filtering for new user cold start recommendation. IEICE Trans Inf Syst 103(6):1388\u20131394","journal-title":"IEICE Trans Inf Syst"},{"key":"1066_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2020.125154","volume":"560","author":"Z Su","year":"2020","unstructured":"Su Z, Zheng X, Ai J et al (2020) Link prediction in recommender systems based on vector similarity. Phys A 560:125154","journal-title":"Phys A"},{"issue":"16","key":"1066_CR19","doi-asserted-by":"publisher","first-page":"7418","DOI":"10.3390\/app11167418","volume":"11","author":"J Gong","year":"2021","unstructured":"Gong J, Zhang X, Li Q et al (2021) A top-N movie recommendation framework based on deep neural network with heterogeneous modeling. Appl Sci 11(16):7418","journal-title":"Appl Sci"},{"issue":"12","key":"1066_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-020-2875-7","volume":"63","author":"X Yu","year":"2020","unstructured":"Yu X, Cui Q, Wang Y et al (2020) Stochastic geometry based analysis for heterogeneous networks: a perspective on meta distribution. Sci China Inf Sci 63(12):1\u201321","journal-title":"Sci China Inf Sci"},{"key":"1066_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106434","volume":"209","author":"J Zhao","year":"2020","unstructured":"Zhao J, Wang W, Zhang Z et al (2020) TrustTF: a tensor factorization model using user trust and implicit feedback for context-aware recommender systems. Knowl-Based Syst 209:106434","journal-title":"Knowl-Based Syst"},{"key":"1066_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105468","volume":"193","author":"C Zhang","year":"2020","unstructured":"Zhang C, Wang G, Yu B et al (2020) Proximity-aware heterogeneous information network embedding. Knowl-Based Syst 193:105468","journal-title":"Knowl-Based Syst"},{"issue":"7","key":"1066_CR23","doi-asserted-by":"publisher","first-page":"369","DOI":"10.3390\/info11070369","volume":"11","author":"S Wang","year":"2020","unstructured":"Wang S, Sun G, Li Y (2020) SVD++ recommendation algorithm based on backtracking. Information 11(7):369","journal-title":"Information"},{"key":"1066_CR24","unstructured":"Salimans T, Kingma DP (2016) Weight normalization: a simple reparameterization to accelerate training of deep neural networks. Adv Neural Inf Process Syst 29:1-11"},{"key":"1066_CR25","doi-asserted-by":"crossref","unstructured":"Hu B, Shi C, Zhao WX, et al. (2018) Leveraging meta-path based context for top-n recommendation with a neural co-attention model. In: Proceedings of the 24th ACM SIGKDD International Conference on knowledge discovery & data mining, vol 1. pp 1531\u20131540","DOI":"10.1145\/3219819.3219965"},{"key":"1066_CR26","doi-asserted-by":"crossref","unstructured":"Walker J, Zhou F, Baagyere EY et al (2022) Implicit optimal variational collaborative filtering. Complex Intell Syst, pp 1\u201316","DOI":"10.1007\/s40747-022-00696-8"},{"issue":"1","key":"1066_CR27","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s40747-019-00123-5","volume":"6","author":"J Chen","year":"2020","unstructured":"Chen J, Zhao C, Chen L (2020) Collaborative filtering recommendation algorithm based on user correlation and evolutionary clustering. Complex Intell Syst 6(1):147\u2013156","journal-title":"Complex Intell Syst"},{"issue":"1","key":"1066_CR28","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/s40747-020-00212-w","volume":"7","author":"Q Zhang","year":"2021","unstructured":"Zhang Q, Lu J, Jin Y (2021) Artificial intelligence in recommender systems. Complex Intell Syst 7(1):439\u2013457","journal-title":"Complex Intell Syst"},{"issue":"3","key":"1066_CR29","doi-asserted-by":"publisher","first-page":"2311","DOI":"10.1007\/s40747-022-00645-5","volume":"8","author":"F Yin","year":"2022","unstructured":"Yin F, Ji M, Wang Y et al (2022) Enhanced graph recommendation with heterogeneous auxiliary information. Complex Intell Syst 8(3):2311\u20132324","journal-title":"Complex Intell Syst"},{"key":"1066_CR30","doi-asserted-by":"crossref","unstructured":"Li Y, Xie Z, Wang F (2022) An associative knowledge network model for interpretable semantic representation of noun context. Complex Intell Syst, 8(6):1\u201321","DOI":"10.1007\/s40747-022-00757-y"},{"key":"1066_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116850","volume":"200","author":"ZZ Darban","year":"2022","unstructured":"Darban ZZ, Valipour MH (2022) GHRS: graph-based hybrid recommendation system with application to movie recommendation. Expert Syst Appl 200:116850","journal-title":"Expert Syst Appl"},{"key":"1066_CR32","doi-asserted-by":"crossref","unstructured":"Fu X, Zhang J, Meng Z, et al. (2020) Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding. In: Proceedings of The Web Conference 2020, Vol 1. pp 2331\u20132341","DOI":"10.1145\/3366423.3380297"},{"issue":"7930","key":"1066_CR33","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/s41586-022-05172-4","volume":"610","author":"A Fawzi","year":"2022","unstructured":"Fawzi A, Balog M, Huang A et al (2022) Discovering faster matrix multiplication algorithms with reinforcement learning. Nature 610(7930):47\u201353","journal-title":"Nature"},{"issue":"1","key":"1066_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000086","volume":"16","author":"TM Moerland","year":"2023","unstructured":"Moerland TM, Broekens J, Plaat A et al (2023) Model-based reinforcement learning: a survey. Found Trends\u00ae Mach Learn 16(1):1\u2013118","journal-title":"Found Trends\u00ae Mach Learn"},{"key":"1066_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.120291","volume":"329","author":"R Wang","year":"2023","unstructured":"Wang R, Li Y, Li Y et al (2023) Wind power forecasting considering data privacy protection: a federated deep reinforcement learning approach. Appl Energy 329:120291","journal-title":"Appl Energy"},{"key":"1066_CR36","doi-asserted-by":"crossref","unstructured":"Dey BK, Seok H (2022) Intelligent inventory management with autonomation and service strategy. J Intell Manuf, pp 1-24","DOI":"10.1007\/s10845-022-02046-4"},{"key":"1066_CR37","doi-asserted-by":"crossref","unstructured":"Sarwar B, Karypis G, Konstan J et al (2001) Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th international conference on World Wide Web. pp 285\u2013295","DOI":"10.1145\/371920.372071"},{"key":"1066_CR38","unstructured":"Rendle S, Freudenthaler C, Gantner Z et al (2012) BPR: Bayesian personalized ranking from implicit feedback. Preprint at https:\/\/arxiv.org\/abs\/1205.2618v1"},{"key":"1066_CR39","doi-asserted-by":"crossref","unstructured":"Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. Computer 42(8):30\u201337","DOI":"10.1109\/MC.2009.263"},{"key":"1066_CR40","unstructured":"Chen T, Zhang W, Lu Q et al (2012) SVDFeature: a toolkit for feature-based collaborative filtering. J Mach Learn Res 13(1):3619-3622"},{"key":"1066_CR41","doi-asserted-by":"crossref","unstructured":"Pham TAN, Li X, Cong G et al (2016) A general recommendation model for heterogeneous networks. IEEE Trans on Knowl Data Eng 28(12):3140\u20133153","DOI":"10.1109\/TKDE.2016.2601091"},{"key":"1066_CR42","doi-asserted-by":"crossref","unstructured":"Zhao H, Yao Q, Li J et al (2017) Meta-graph based recommendation fusion over heterogeneous information networks. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, vol 1. pp 635\u2013644","DOI":"10.1145\/3097983.3098063"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01066-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-023-01066-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01066-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T19:14:28Z","timestamp":1698434068000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-023-01066-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,27]]},"references-count":42,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["1066"],"URL":"https:\/\/doi.org\/10.1007\/s40747-023-01066-8","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"type":"print","value":"2199-4536"},{"type":"electronic","value":"2198-6053"}],"subject":[],"published":{"date-parts":[[2023,4,27]]},"assertion":[{"value":"12 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}