Deep Learning based Recommender System: A Survey and New Perspectives

Shuai Zhang, Lina Yao, Aixin Sun

(Submitted on 24 Jul 2017 (v1), last revised 3 Aug 2017 (this version, v5))

With the ever-growing volume, complexity and dynamicity of online information, recommender system has been an effective key solution to overcome such information overload. In recent years, deep learning's revolutionary advances in speech recognition, image analysis and natural language processing have gained significant attention. Meanwhile, recent studies also demonstrate its effectiveness in coping with information retrieval and recommendation tasks. Applying deep learning techniques into recommender system has been gaining momentum due to its state-of-the-art performances and high-quality recommendations. In contrast to traditional recommendation models, deep learning provides a better understanding of user's demands, item's characteristics and historical interactions between them. 
This article aims to provide a comprehensive review of recent research efforts on deep learning based recommender systems towards fostering innovations of recommender system research. A taxonomy of deep learning based recommendation models is presented and used to categorize the surveyed articles. Open problems are identified based on the analytics of the reviewed works and potential solutions discussed.

Comments:35 pages, submitted to journalSubjects:Information Retrieval (cs.IR)Cite as:arXiv:1707.07435 [cs.IR] (or arXiv:1707.07435v5 [cs.IR] for this version)

Submission history

From: Shuai Zhang [view email] 
[v1] Mon, 24 Jul 2017 08:23:26 GMT (1982kb,D)
[v2] Thu, 27 Jul 2017 14:44:59 GMT (1983kb,D)
[v3] Sat, 29 Jul 2017 14:15:51 GMT (1991kb,D)
[v4] Tue, 1 Aug 2017 14:25:09 GMT (2050kb,D)
[v5] Thu, 3 Aug 2017 06:11:24 GMT (2056kb,D)