ID-centric Pre-training for Recommendation
Open Access
- 10 July 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (5) , 1-29
Abstract
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 semantically similar items from pre-training domains using CDIM. Next, these retrieved items’ pre-trained ID 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.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2024YFF0729003)
- Young Elite Scientists Sponsorship Program by CAST (2023QNRC001)
- National Natural Science Foundation of China (62206266 and 62176014)
- Fundamental Research Funds for the Central Universities
This publication has 39 references indexed in Scilit:
- Personalized Prompt for Sequential RecommendationIEEE Transactions on Knowledge and Data Engineering, 2024
- BMLP: behavior-aware MLP for heterogeneous sequential recommendationFrontiers of Computer Science, 2024
- A general tail item representation enhancement framework for sequential recommendationFrontiers of Computer Science, 2023
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- Cross-domain Recommendation with Probabilistic Knowledge Transfer2018
- Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks2017
- Translation-based Recommendation2017
- Neural Collaborative Filtering2017
- Deep Neural Networks for YouTube Recommendations2016
- Factorizing personalized Markov chains for next-basket recommendation2010