CASIA OpenIR  > 智能感知与计算研究中心
MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation
Qiang Cui1; Shu Wu1; Qiang Liu1; Wen Zhong2; Liang Wang1
Source PublicationIEEE Transactions on Knowledge and Data Engineering (TKDE)
2018-11
IssuenoPages:no
Abstract

Sequential recommendation is a fundamental task for network applications, and it usually suffers from the item cold start problem due to the insufficiency of user feedbacks. There are currently three kinds of popular approaches which are respectively based on matrix factorization (MF) of collaborative filtering, Markov chain (MC), and recurrent neural network (RNN). Although widely used, they have some limitations. MF based methods could not capture dynamic user’s interest. The strong Markov assumption greatly limits the performance of MC based methods. RNN based methods are still in the early stage of incorporating additional information. Based on these basic models, many methods with additional information only validate incorporating one modality in a separate way. In this work, to make the sequential recommendation and deal with the item cold start problem, we propose a Multi-View Rrecurrent Neural Network (MV-RNN) model. Given the latent feature, MV-RNN can alleviate the item cold start problem by incorporating visual and textual information. First, At the input of MV-RNN, three different combinations of multi-view features are studied, like concatenation, fusion by addition and fusion by reconstructing the original multi-modal data. MV-RNN applies the recurrent structure to dynamically capture the user’s interest. Second, we design a separate structure and a united structure on the hidden state of MV-RNN to explore a more effective way to handle multi-view features. Experiments on two real-world datasets show that MV-RNN can effectively generate the personalized ranking list, tackle the missing modalities problem and significantly alleviate the item cold start problem.

KeywordMulti-view Sequential Recommendation Recurrent Neural Network Cold Start
Indexed BySCI
Language英语
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23690
Collection智能感知与计算研究中心
Corresponding AuthorShu Wu
Affiliation1.Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA) and University of Chinese Academy of Sciences (UCAS)
2.University of Southern California
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Qiang Cui,Shu Wu,Qiang Liu,et al. MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation[J]. IEEE Transactions on Knowledge and Data Engineering (TKDE),2018(no):no.
APA Qiang Cui,Shu Wu,Qiang Liu,Wen Zhong,&Liang Wang.(2018).MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation.IEEE Transactions on Knowledge and Data Engineering (TKDE)(no),no.
MLA Qiang Cui,et al."MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation".IEEE Transactions on Knowledge and Data Engineering (TKDE) .no(2018):no.
Files in This Item: Download All
File Name/Size DocType Version Access License
崔强 正式接收后 TKDE2881260(979KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Qiang Cui]'s Articles
[Shu Wu]'s Articles
[Qiang Liu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qiang Cui]'s Articles
[Shu Wu]'s Articles
[Qiang Liu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qiang Cui]'s Articles
[Shu Wu]'s Articles
[Qiang Liu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 崔强 正式接收后 TKDE2881260.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.