{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:08:51Z","timestamp":1740103731586,"version":"3.37.3"},"reference-count":55,"publisher":"Wiley","license":[{"start":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T00:00:00Z","timestamp":1603843200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972336"],"award-info":[{"award-number":["61972336"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2020,10,28]]},"abstract":"<jats:p>Nowadays, people have an increasing interest in fresh products such as new shoes and cosmetics. To this end, an E-commerce platform Taobao launched a fresh-item hub page on the recommender system, with which customers can freely and exclusively explore and purchase fresh items, namely, the New Tendency page. In this work, we make a first attempt to tackle the fresh-item recommendation task with two major challenges. First, a fresh-item recommendation scenario usually faces the challenge that the training data are highly deficient due to low page views. In this paper, we propose a deep interest-shifting network (DisNet), which transfers knowledge from a huge number of auxiliary data and then shifts user interests with contextual information. Furthermore, three interpretable interest-shifting operators are introduced. Second, since the items are fresh, many of them have never been exposed to users, leading to a severe cold-start problem. Though this problem can be alleviated by knowledge transfer, we further babysit these fully cold-start items by a relational meta-Id-embedding generator (RM-IdEG). Specifically, it trains the item id embeddings in a learning-to-learn manner and integrates relational information for better embedding performance. We conducted comprehensive experiments on both synthetic datasets as well as a real-world dataset. Both DisNet and RM-IdEG significantly outperform state-of-the-art approaches, respectively. Empirical results clearly verify the effectiveness of the proposed techniques, which are arguably promising and scalable in real-world applications.<\/jats:p>","DOI":"10.1155\/2020\/8828087","type":"journal-article","created":{"date-parts":[[2020,10,29]],"date-time":"2020-10-29T04:50:05Z","timestamp":1603947005000},"page":"1-13","source":"Crossref","is-referenced-by-count":3,"title":["Deep Interest-Shifting Network with Meta-Embeddings for Fresh Item Recommendation"],"prefix":"10.1155","volume":"2020","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5056-0351","authenticated-orcid":true,"given":"Zhao","family":"Li","sequence":"first","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"given":"Haobo","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2898-9386","authenticated-orcid":true,"given":"Donghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"given":"Shichang","family":"Hu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"given":"Zhen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"given":"Weiwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9363-9908","authenticated-orcid":true,"given":"Jianliang","family":"Gao","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}]},{"given":"Zhiqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University of Finance and Economics, Hangzhou, China"}]},{"given":"Ji","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Southern Queensland, Toowoomba, Queensland, Australia"}]}],"member":"311","reference":[{"first-page":"157","article-title":"Poisonrec: an adaptive data poisoning framework for attacking black-box recommender systems","author":"J. Song","key":"1"},{"key":"2","first-page":"366","article-title":"Density matrix based preference evolution networks for e-commerce recommendation","volume-title":"DASFAA","author":"P. Wang","year":"2019"},{"first-page":"2329","article-title":"QPIN: a quantum-inspired preference interactive network for E-commerce recommendation","author":"P. Wang","key":"3"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/5206087"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/6325654"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/6136095"},{"key":"7","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-85820-3_7","volume-title":"Context-Aware Recommender Systems","author":"G. Adomavicius","year":"2011"},{"issue":"2","key":"8","article-title":"Matrix factorization techniques for context-aware collaborative filtering recommender systems: a survey.","volume":"11","author":"M. H. Abdi","year":"2018","journal-title":"Computer and Information Science"},{"first-page":"271","article-title":"Deviation-based contextual SLIM recommenders","author":"Y. Zheng","key":"9"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/9476981"},{"first-page":"1725","article-title":"DeepFM: a factorization-machine based neural network for CTR prediction","author":"H. Guo","key":"11"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/3574194"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1145\/3233770"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/2926749"},{"first-page":"3926","article-title":"CFM: convolutional factorization machines for context-aware recommendation","author":"X. Xin","key":"15"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1145\/3017429"},{"article-title":"Cross-domain recommendation without sharing user-relevant data","year":"2019","author":"C. Gao","key":"17"},{"first-page":"667","article-title":"CoNet: collaborative cross networks for cross-domain recommendation","author":"G. Hu","key":"18"},{"article-title":"Personalized recommendation via cross-domain triadic factorization","year":"2013","author":"L. Hu","key":"19"},{"first-page":"2052","article-title":"Can movies and books collaborate? cross-domain collaborative filtering for sparsity reduction","author":"B. Li","key":"20"},{"author":"W. Pan","key":"21","article-title":"Transfer learning in collaborative filtering for sparsity reduction"},{"first-page":"89","article-title":"Item cold-start recommendations: learning local collective embeddings","author":"S. Martin","key":"22"},{"article-title":"DropoutNet: addressing cold start in recommender systems","year":"2017","author":"M. Volkovs","key":"23"},{"first-page":"99","article-title":"Latent factor representations for cold-start video recommendation","author":"S. Roy","key":"24"},{"key":"25","doi-asserted-by":"crossref","DOI":"10.1145\/1995966.1995976","article-title":"Personalised rating prediction for new users using latent factor models","author":"Y. Seroussi","year":"2011"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013830"},{"key":"27","first-page":"695","article-title":"Warm up cold-start advertisements: improving CTR predictions via learning to learn ID embeddings","volume-title":"","author":"F. Pan","year":"2019"},{"first-page":"301","article-title":"Matrix factorization techniques for context aware recommendation","author":"L. Baltrunas","key":"28"},{"key":"29","doi-asserted-by":"crossref","DOI":"10.1145\/3178876.3186175","article-title":"DKN: deep knowledge-aware network for news recommendation","author":"H. Wang","year":"2018"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015973"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/693"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2327111"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2013.2297923"},{"first-page":"2123","article-title":"ActiveHNE: active heterogeneous network embedding","author":"X. Chen","key":"34"},{"first-page":"2007","article-title":"Deep graph embedding for ranking optimization in e-commerce","author":"C. Chu","key":"35"},{"first-page":"2181","article-title":"Learning entity and relation embeddings for knowledge graph completion","author":"Y. Lin","key":"36"},{"key":"37","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2016.2562621"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"article-title":"Improving recommendation lists through topic diversification","year":"2005","author":"C.-N. Ziegler","key":"39"},{"key":"40","doi-asserted-by":"publisher","DOI":"10.1145\/1055709.1055714"},{"first-page":"265","article-title":"Experimental comparison of pre- vs. post-filtering approaches in context-aware recommender systems","author":"U. Panniello","key":"41"},{"key":"42"},{"key":"43","first-page":"67","volume-title":"Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Implicit Feedback","author":"B. Hidasi","year":"2012"},{"article-title":"TFMAP: optimizing map for top-n context-aware recommendation","year":"2012","author":"Y. Shi","key":"44"},{"first-page":"1132","article-title":"RaFM: rank-aware factorization machines","author":"X. Chen","key":"45"},{"key":"46","doi-asserted-by":"publisher","DOI":"10.1145\/3291756"},{"first-page":"7","article-title":"Wide & deep learning for recommender systems","author":"H.-T. Cheng","key":"47"},{"first-page":"1059","article-title":"Deep interest network for click-through rate prediction","author":"G. Zhou","key":"48"},{"first-page":"291","article-title":"CARS2: learning context-aware representations for context-aware recommendations","author":"Y. Shi","key":"49"},{"author":"I. Fern\u00e1ndez-Tob\u00edas","key":"50","article-title":"Cross-domain recommender systems: a survey of the state of the art"},{"first-page":"801","article-title":"Matching users and items across domains to improve the recommendation quality","author":"C.-Y. Li","key":"51"},{"first-page":"2464","article-title":"Cross-domain recommendation: an embedding and mapping approach","author":"M. Tong","key":"52"},{"first-page":"1073","article-title":"MeLU: meta-learned user preference estimator for cold-start recommendation","author":"H. Lee","key":"53"},{"article-title":"A meta-learning perspective on cold-start recommendations for items","year":"2017","author":"M. Vartak","key":"54"},{"first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"C. Finn","key":"55"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2020\/8828087.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2020\/8828087.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2020\/8828087.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,29]],"date-time":"2020-10-29T04:50:09Z","timestamp":1603947009000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/complexity\/2020\/8828087\/"}},"subtitle":[],"editor":[{"given":"Jia","family":"Wu","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,10,28]]},"references-count":55,"alternative-id":["8828087","8828087"],"URL":"https:\/\/doi.org\/10.1155\/2020\/8828087","relation":{},"ISSN":["1099-0526","1076-2787"],"issn-type":[{"type":"electronic","value":"1099-0526"},{"type":"print","value":"1076-2787"}],"subject":[],"published":{"date-parts":[[2020,10,28]]}}}