{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:24:54Z","timestamp":1780601094695,"version":"3.54.1"},"reference-count":37,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T00:00:00Z","timestamp":1614297600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2016YFB1001000, 2018YFB1402600"],"award-info":[{"award-number":["2016YFB1001000, 2018YFB1402600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61772528"],"award-info":[{"award-number":["61772528"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2021,4,30]]},"abstract":"<jats:p>Item representations in recommendation systems are expected to reveal the properties of items. Collaborative recommender methods usually represent an item as one single latent vector. Nowadays the e-commercial platforms provide various kinds of attribute information for items (e.g., category, price, and style of clothing). Utilizing this attribute information for better item representations is popular in recent years. Some studies use the given attribute information as side information, which is concatenated with the item latent vector to augment representations. However, the mixed item representations fail to fully exploit the rich attribute information or provide explanation in recommender systems. To this end, we propose a fine-grained Disentangled Item Representation (DIR) for recommender systems in this article, where the items are represented as several separated attribute vectors instead of a single latent vector. In this way, the items are represented at the attribute level, which can provide fine-grained information of items in recommendation. We introduce a learning strategy, LearnDIR, which can allocate the corresponding attribute vectors to items. We show how DIR can be applied to two typical models, Matrix Factorization (MF) and Recurrent Neural Network (RNN). Experimental results on two real-world datasets show that the models developed under the framework of DIR are effective and efficient. Even using fewer parameters, the proposed model can outperform the state-of-the-art methods, especially in the cold-start situation. In addition, we make visualizations to show that our proposition can provide explanation for users in real-world applications.<\/jats:p>","DOI":"10.1145\/3445811","type":"journal-article","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T11:13:43Z","timestamp":1614338023000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Disentangled Item Representation for Recommender Systems"],"prefix":"10.1145","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0017-5292","authenticated-orcid":false,"given":"Zeyu","family":"Cui","sequence":"first","affiliation":[{"name":"Institution of Automation Chinese Academy of Sciences (CASIA), University of Chinese Academy of Sciences (UCAS), National Laboratory of Pattern Recognition (NLPR), Center for Research on Intelligent Perception and Computing (CRIPAC), Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Group Institution of Automation Chinese Academy of Sciences (CASIA), University of Chinese Academy of Sciences (UCAS), National Laboratory of Pattern Recognition (NLPR), Center for Research on Intelligent Perception and Computing (CRIPAC)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu","family":"Wu","sequence":"additional","affiliation":[{"name":"Institution of Automation Chinese Academy of Sciences (CASIA), University of Chinese Academy of Sciences (UCAS), National Laboratory of Pattern Recognition (NLPR), Center for Research on Intelligent Perception and Computing (CRIPAC), Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9233-3827","authenticated-orcid":false,"given":"Qiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Institution of Automation Chinese Academy of Sciences (CASIA), University of Chinese Academy of Sciences (UCAS), National Laboratory of Pattern Recognition (NLPR), Center for Research on Intelligent Perception and Computing (CRIPAC), Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Institution of Automation Chinese Academy of Sciences (CASIA), University of Chinese Academy of Sciences (UCAS), National Laboratory of Pattern Recognition (NLPR), Center for Research on Intelligent Perception and Computing (CRIPAC), Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,2,26]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Network Flows: Theory, Algorithms, and Applications. Pearson Education.","author":"Ahuja Ravindra K.","year":"2017"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350915"},{"key":"e_1_2_1_3_1","volume-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In NIPS\u201916. 2172--2180.","author":"Chen Xi","year":"2016"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.04.073"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"e_1_2_1_6_1","volume-title":"Sherlock: Sparse hierarchical embeddings for visually-aware one-class collaborative filtering. In IJCAI\u201916. 3740--3746.","author":"He Ruining","year":"2016"},{"key":"e_1_2_1_7_1","unstructured":"Ruining He and Julian McAuley. 2016. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In WWW\u201916. 507--517.  Ruining He and Julian McAuley. 2016. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In WWW\u201916. 507--517."},{"key":"e_1_2_1_8_1","volume-title":"VBPR: Visual Bayesian personalized ranking from implicit feedback. In AAAI\u201916. 144--150.","author":"He Ruining","year":"2016"},{"key":"e_1_2_1_9_1","volume-title":"Towards a definition of disentangled representations. arXiv preprint arXiv:1812.02230","author":"Higgins Irina","year":"2018"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_1_11_1","volume-title":"Explainable fashion recommendation: A semantic attribute region guided approach. arXiv preprint arXiv:1905.12862","author":"Hou Min","year":"2019"},{"key":"e_1_2_1_12_1","unstructured":"Guangneng Hu Yu Zhang and Qiang Yang. 2019. Transfer meets hybrid: A synthetic approach for cross-domain collaborative filtering with text. In WWW\u201919. 2822--2829.  Guangneng Hu Yu Zhang and Qiang Yang. 2019. Transfer meets hybrid: A synthetic approach for cross-domain collaborative filtering with text. In WWW\u201919. 2822--2829."},{"key":"e_1_2_1_13_1","volume-title":"Disentangled representation learning for text style transfer. arXiv preprint arXiv:1808.04339","author":"John Vineet","year":"2018"},{"key":"e_1_2_1_14_1","volume-title":"Matrix factorization techniques for recommender systems. Computer 42, 8","author":"Koren Yehuda","year":"2009"},{"key":"e_1_2_1_15_1","unstructured":"Xiang Li Tao Qin Jian Yang Xiaolin Hu and Tieyan Liu. 2016. LightRNN: Memory and computation-efficient recurrent neural networks. In NIPS\u201916. 4385--4393.  Xiang Li Tao Qin Jian Yang Xiaolin Hu and Tieyan Liu. 2016. LightRNN: Memory and computation-efficient recurrent neural networks. In NIPS\u201916. 4385--4393."},{"key":"e_1_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Defu Lian Cong Zhao Xing Xie Guangzhong Sun Enhong Chen and Yong Rui. 2014. GeoMF: Joint geographical modeling and matrix factorization for point-of-interest recommendation. In SIGKDD\u201914. 831--840.  Defu Lian Cong Zhao Xing Xie Guangzhong Sun Enhong Chen and Yong Rui. 2014. GeoMF: Joint geographical modeling and matrix factorization for point-of-interest recommendation. In SIGKDD\u201914. 831--840.","DOI":"10.1145\/2623330.2623638"},{"key":"e_1_2_1_17_1","volume-title":"ICDM\u201916","author":"Liu Qiang"},{"key":"e_1_2_1_18_1","unstructured":"Qiang Liu Shu Wu and Liang Wang. 2017. DeepStyle: Learning user preferences for visual recommendation. In SIGIR\u201917. 841--844.  Qiang Liu Shu Wu and Liang Wang. 2017. DeepStyle: Learning user preferences for visual recommendation. In SIGIR\u201917. 841--844."},{"key":"e_1_2_1_19_1","unstructured":"Qiang Liu Shu Wu Liang Wang and Tieniu Tan. 2016. Predicting the next location: A recurrent model with spatial and temporal contexts. In AAAI\u201916. 194--200.  Qiang Liu Shu Wu Liang Wang and Tieniu Tan. 2016. Predicting the next location: A recurrent model with spatial and temporal contexts. In AAAI\u201916. 194--200."},{"key":"e_1_2_1_20_1","volume-title":"Junbo Zhao, Aditya Ramesh, Pablo Sprechmann, and Yann LeCun.","author":"Mathieu Michael F.","year":"2016"},{"key":"e_1_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Julian McAuley Christopher Targett Qinfeng Shi and Anton Van Den Hengel. 2015. Image-based recommendations on styles and substitutes. In SIGIR\u201915. 43--52.  Julian McAuley Christopher Targett Qinfeng Shi and Anton Van Den Hengel. 2015. Image-based recommendations on styles and substitutes. In SIGIR\u201915. 43--52.","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Julian John McAuley and Jure Leskovec. 2013. From amateurs to connoisseurs: Modeling the evolution of user expertise through online reviews. In WWW\u201913. 897--908.  Julian John McAuley and Jure Leskovec. 2013. From amateurs to connoisseurs: Modeling the evolution of user expertise through online reviews. In WWW\u201913. 897--908.","DOI":"10.1145\/2488388.2488466"},{"key":"e_1_2_1_23_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013"},{"key":"e_1_2_1_24_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S. Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In NIPS\u201913. 3111--3119.  Tomas Mikolov Ilya Sutskever Kai Chen Greg S. Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In NIPS\u201913. 3111--3119."},{"key":"e_1_2_1_25_1","volume-title":"ICDM\u201908","author":"Pan Rong"},{"key":"e_1_2_1_26_1","volume-title":"Manning","author":"Pennington Jeffrey","year":"2014"},{"key":"e_1_2_1_27_1","volume-title":"BPR: Bayesian personalized ranking from implicit feedback. In UAI\u201909. 452--461.","author":"Rendle Steffen","year":"2009"},{"key":"e_1_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Steffen Rendle Christoph Freudenthaler and Lars Schmidt-Thieme. 2010. Factorizing personalized Markov chains for next-basket recommendation. In WWW\u201910. 811--820.  Steffen Rendle Christoph Freudenthaler and Lars Schmidt-Thieme. 2010. Factorizing personalized Markov chains for next-basket recommendation. In WWW\u201910. 811--820.","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_2_1_29_1","volume-title":"ICCE\u201919","author":"Shin Yong-Goo"},{"key":"e_1_2_1_30_1","unstructured":"Zhu Sun Jie Yang Jie Zhang and Alessandro Bozzon. 2017. Exploiting both vertical and horizontal dimensions of feature hierarchy for effective recommendation. In AAAI\u201917. 189--195.  Zhu Sun Jie Yang Jie Zhang and Alessandro Bozzon. 2017. Exploiting both vertical and horizontal dimensions of feature hierarchy for effective recommendation. In AAAI\u201917. 189--195."},{"key":"e_1_2_1_31_1","volume-title":"MRLR: Multi-level representation learning for personalized ranking in recommendation. In IJCAI\u201917. 2807--2813.","author":"Sun Zhu","year":"2017"},{"key":"e_1_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Martin Sundermeyer Ralf Schl\u00fcter and Hermann Ney. 2012. LSTM neural networks for language modeling. In INTERSPEECH\u201912. 194--197.  Martin Sundermeyer Ralf Schl\u00fcter and Hermann Ney. 2012. LSTM neural networks for language modeling. In INTERSPEECH\u201912. 194--197.","DOI":"10.21437\/Interspeech.2012-65"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2928848"},{"key":"e_1_2_1_34_1","unstructured":"Xun Yang Xiangnan He Xiang Wang Yunshan Ma Fuli Feng Meng Wang and Tat-Seng Chua. 2019. Interpretable fashion matching with rich attributes. In SIGIR\u201919. 775--784.  Xun Yang Xiangnan He Xiang Wang Yunshan Ma Fuli Feng Meng Wang and Tat-Seng Chua. 2019. Interpretable fashion matching with rich attributes. In SIGIR\u201919. 775--784."},{"key":"e_1_2_1_35_1","unstructured":"Feng Yu Qiang Liu Shu Wu Liang Wang and Tieniu Tan. 2016. A dynamic recurrent model for next basket recommendation. In SIGIR\u201916. 729--732.  Feng Yu Qiang Liu Shu Wu Liang Wang and Tieniu Tan. 2016. A dynamic recurrent model for next basket recommendation. In SIGIR\u201916. 729--732."},{"key":"e_1_2_1_36_1","volume-title":"International World Wide Web Conferences Steering Committee, 649--658","author":"Yu Wenhui","year":"2018"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3285029"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3445811","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3445811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:13Z","timestamp":1750195693000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3445811"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,26]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,4,30]]}},"alternative-id":["10.1145\/3445811"],"URL":"https:\/\/doi.org\/10.1145\/3445811","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,26]]},"assertion":[{"value":"2019-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-12-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}