Affiliated with RCfalse
Status已發表Published
Meta-path Based Neighbors for Behavioral Target Generalization in Sequential Recommendation
Chen, Junyang1; Gong, Zhiguo2; Li, Yuanman3; Zhang, Huanjian4; Yu, Hongyong5; Zhu, Junzhang6; Fan, Ge7; Wu, Xiao Ming8; Wu, Kaishun9
2022-06
Source PublicationIEEE Transactions on Network Science and Engineering
Abstract

Click-through rate (CTR) prediction is a crucial task in recommender systems, which aims to model users' dynamic preferences from their historical behaviors. To achieve this goal, most of the previous models adopt sequential neural networks (e.g., GRU) to encode the historical interactions into item representations for recommendations. Though these methods can perform well on recommending highly relevant items to users, we argue that such models are sub-optimal for the long-term user experience due to highly skewed recommendations: Monotonous items with similar subjects get more exposure because of inadequate interest explorations. Thus, some items which are not quite relevant to the users' historical preferences should be considered. To address these limitations, we propose a Heterogeneous Graph Enhanced Sequential Neural Network, HGESNN, to explore the interests of users beyond their historical interactions by explicitly modeling item relations with meta-path constructions. We incorporate a transformer-based network to embed personalized user intents into sequential learning. In the experiments on both public and industrial datasets, HGESNN significantly outperforms the state-of-the-art solutions. Specifically, HGESNN has been deployed in the main traffic of our Image-Text feed recommender system, which obtains 6.28\%, 6.82\%, and 4.77\% CTR gains on news, novels, and entertainment contents, respectively.

KeywordBehavioral Target Generalization Ctr Prediction Predictive Models Recommender Systems Recommender Systems Semantics Sequential Recommendation Task Analysis Training Transformers User Experience
DOI10.1109/TNSE.2022.3149328
URLView the original
Indexed BySCIE
Language英語English
WOS Research AreaEngineering ; Mathematics
WOS SubjectEngineering, Multidisciplinary ; Mathematics, Interdisciplinary Applications
WOS IDWOS:000800200900059
Scopus ID2-s2.0-85124750058
Fulltext Access
Citation statistics
Cited Times [WOS]:0   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorLi, Yuanman
Affiliation1.Shenzhen University, 47890 Shenzhen, Guangdong, China, 518060 (e-mail: yb77403@umac.mo)
2.Department of Computer and Information Science, University of Macau, 59193 Taipa, Macau, Macao, (e-mail: fstzgg@um.edu.mo)
3.Shenzhen University, 47890 Shenzhen, Guangdong, China, 518060 (e-mail: yuanmanli@szu.edu.cn)
4.Tencent, 508929 Shenzhen, Guangdong, China, (e-mail: alexhjzhang@tencent.com)
5.Tencent, 508929 Shenzhen, Guangdong, China, (e-mail: willsyu@tencent.com)
6.Tencent, 508929 Shenzhen, Guangdong, China, (e-mail: johannzhu@tencent.com)
7.Tencent, 508929 Shenzhen, Guangdong, China, (e-mail: gefan@tencent.com)
8.the Department of Computing, The Hong Kong Polytechnic University, 26680 Kowloon, HK, Hong Kong, (e-mail: xiao-ming.wu@polyu.edu.hk)
9.Shenzhen University, 47890 Shenzhen, Guangdong, China, 518060 (e-mail: wu@szu.edu.cn)
Recommended Citation
GB/T 7714
Chen, Junyang,Gong, Zhiguo,Li, Yuanman,et al. Meta-path Based Neighbors for Behavioral Target Generalization in Sequential Recommendation[J]. IEEE Transactions on Network Science and Engineering,2022.
APA Chen, Junyang,Gong, Zhiguo,Li, Yuanman,Zhang, Huanjian,Yu, Hongyong,Zhu, Junzhang,Fan, Ge,Wu, Xiao Ming,&Wu, Kaishun.(2022).Meta-path Based Neighbors for Behavioral Target Generalization in Sequential Recommendation.IEEE Transactions on Network Science and Engineering.
MLA Chen, Junyang,et al."Meta-path Based Neighbors for Behavioral Target Generalization in Sequential Recommendation".IEEE Transactions on Network Science and Engineering (2022).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chen, Junyang]'s Articles
[Gong, Zhiguo]'s Articles
[Li, Yuanman]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen, Junyang]'s Articles
[Gong, Zhiguo]'s Articles
[Li, Yuanman]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen, Junyang]'s Articles
[Gong, Zhiguo]'s Articles
[Li, Yuanman]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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