Multitask-Based Self-Supervised Learning for Recommendation in Social Systems

doi:10.1109/TCSS.2024.3517164

	Multitask-Based Self-Supervised Learning for Recommendation in Social Systems
	Xu, Wenjian 1,2; Zeng, Fanxiang 3; Zhang, Nan 4; Gao, Honghao 5,6; Yin, Yuyu 7; Chen, Zulong 4; Huang, Maolei 8; Wan, Jian 1,2
	2024-12-27
发表期刊	IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
ISSN	2329-924X
页码	12
摘要	In computational social systems, recommendation functionality plays a pivotal role in influencing user behavior, enhancing user experience, and driving engagement. To help recommendation functionality to better suggest relevant content or items, the social platforms usually utilize large-scale knowledge discovery techniques to analyze trends in user interactions and extract patterns from large datasets. Click-through rate (CTR) prediction is crucial in recommendation systems for measuring effectiveness, understanding user behavior, training and optimizing models, impacting business outcomes, enhancing personalization, and identifying issues. It provides actionable insights that assist in continuously refining and improving the recommendation process. Traditional deep learning-based CTR prediction models cannot work well for recommendation in social systems due to the data sparsity and the long-tail data problems since the representation learned from the user behavior is basically dominated by the major part of the data. In this article, we propose a multitask-based self-supervised learning model (MTSSL) that can better deal with sparse and long-tail user interaction data. Specifically, we first transform the CTR prediction task into the multitask joint learning framework with a set of shared subnetworks. Each subnetwork learns a representation of the entire user data, and hence, the sparse and long-tail data would have opportunity to fall into the best matched representation space of historical user behavior. Moreover, two kinds of self-supervision signals are employed to guide the learning of the representations. Extensive experiments over four user interaction datasets demonstrate the superiority of our proposed MTSSL over state-of-art models for recommendations. In terms of online A/B test, our model achieves around 3% better performance than the counterparts.
关键词	Data models Predictive models Heavily-tailed distribution Feature extraction Representation learning Recommender systems Electronic mail Computational modeling Poles and towers Data mining Click-through rate (CTR) prediction large-scale knowledge discovery multitask learning representation learning user behavior modeling
DOI	10.1109/TCSS.2024.3517164
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of Zhejiang Province[LQ24F020040] ; Yangtze River Delta Science and Technology Innovation Community Joint Research Project[2022CSJGG1000/2023ZY1068] ; Zhejiang University of Science and Technology[2024yjskj03]
WOS研究方向	Computer Science
WOS类目	Computer Science, Cybernetics ; Computer Science, Information Systems
WOS记录号	WOS:001385752700001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40797
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Gao, Honghao; Yin, Yuyu; Chen, Zulong
作者单位	1.Zhejiang Key Lab Biomed Intelligent Comp Technol, Hangzhou 310023, Peoples R China 2.Zhejiang Univ Sci & Technol, Sch Informat & Elect Engn, Hangzhou 310023, Peoples R China 3.AutoNavi Software Co Ltd, Beijing 100102, Peoples R China 4.Alibaba Grp, Beijing 100102, Peoples R China 5.Shanghai Univ, Sch Comp Engn & Sci, Shanghai 200444, Peoples R China 6.Gachon Univ, Coll Future Ind, Seongnam 461701, Gyeonggi, South Korea 7.Hangzhou Dianzi Univ, Dept Comp, Hangzhou 310023, Peoples R China 8.Chinese Acad Sci, Inst Comp Technol, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Xu, Wenjian,Zeng, Fanxiang,Zhang, Nan,et al. Multitask-Based Self-Supervised Learning for Recommendation in Social Systems[J]. IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,2024:12.
APA	Xu, Wenjian.,Zeng, Fanxiang.,Zhang, Nan.,Gao, Honghao.,Yin, Yuyu.,...&Wan, Jian.(2024).Multitask-Based Self-Supervised Learning for Recommendation in Social Systems.IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,12.
MLA	Xu, Wenjian,et al."Multitask-Based Self-Supervised Learning for Recommendation in Social Systems".IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS (2024):12.