ID-centric Pre-training for Recommendation

doi:10.1145/3735128

	ID-centric Pre-training for Recommendation
	Wu, Yiqing 1,2; Xie, Ruobing 3; Zhang, Zhao 1; Zhang, Xu 3; Zhuang, Fuzhen 4,5; Lin, Leyu 3; Kang, Zhanhui 6; An, Zhulin 1; Xu, Yongjun 1
	2025-09-01
发表期刊	ACM TRANSACTIONS ON INFORMATION SYSTEMS
ISSN	1046-8188
卷号	43 期号:5 页码:29
摘要	Classical sequential recommendation models generally adopt ID embeddings to store knowledge learned from user historical behaviors and represent items. However, these unique IDs are challenging to be transferred to new domains. With the thriving of pre-trained language model (PLM), some pioneer works adopt PLM for pre-trained recommendation, where modality information is considered universal across domains via PLM. Unfortunately, the behavioral information in ID embeddings is verified to currently dominate in recommendation compared to modality information and thus limits these models' performance. In this work, we propose a novel ID-centric recommendation pre-training paradigm (IDP), which directly transfers informative ID embeddings learned in pre-training domains to item representations in new domains. Specifically, in pre-training stage, besides the ID-based sequential recommendation model, we also build a Cross-domain ID-matcher (CDIM) learned by both behavioral and modality information. In the tuning stage, modality information of new domain items is regarded as a cross-domain bridge built by CDIM. They first adopted to retrieve behaviorally and embeddings are directly adopted to generate downstream new items' embeddings. Through extensive experiments on real-world datasets, we demonstrate that our proposed model significantly outperforms all baselines.
关键词	Pre-trained Recommendation ID-based Recommendation Multi-domain Recommendation
DOI	10.1145/3735128
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2024YFF0729003] ; Young Elite Scientists Sponsorship Program by CAST[2023QNRC001] ; National Natural Science Foundation of China[62206266] ; National Natural Science Foundation of China[62176014] ; Fundamental Research Funds for the Central Universities
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems
WOS记录号	WOS:001552823100001
出版者	ASSOC COMPUTING MACHINERY
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41783
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Zhao
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Tencent, Beijing, Peoples R China 4.Beihang Univ, Inst Artificial Intelligence, Beijing, Peoples R China 5.Zhongguancun Lab, Beijing, Peoples R China 6.Tencent, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Wu, Yiqing,Xie, Ruobing,Zhang, Zhao,et al. ID-centric Pre-training for Recommendation[J]. ACM TRANSACTIONS ON INFORMATION SYSTEMS,2025,43(5):29.
APA	Wu, Yiqing.,Xie, Ruobing.,Zhang, Zhao.,Zhang, Xu.,Zhuang, Fuzhen.,...&Xu, Yongjun.(2025).ID-centric Pre-training for Recommendation.ACM TRANSACTIONS ON INFORMATION SYSTEMS,43(5),29.
MLA	Wu, Yiqing,et al."ID-centric Pre-training for Recommendation".ACM TRANSACTIONS ON INFORMATION SYSTEMS 43.5(2025):29.