A Unified Framework for Multi-Domain CTR Prediction via Large Language Models
ACM Transactions on Information Systems · 30.09.2025 · 43 (5) · 1-33
DOI: 10.1145/3698878 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 10.07.2025. Verfasst von Zichuan Fu und 8 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: (Huawei Innovation Research Program), Research Impact Fund, APRC - CityU New Research Initiatives, CityU - HKIDS Early Career Research Grant.
Abstract (Originalsprache)
Multi-Domain Click-Through Rate (MDCTR) prediction is crucial for online recommendation platforms, which involves providing personalized recommendation services to users in different domains. However, current MDCTR models are confronted with the following limitations. Firstly, due to varying data sparsity in different domains, models can easily be dominated by some specific domains, which leads to significant performance degradation in other domains (i.e., the “seesaw phenomenon”). Secondly, when new domain emerges, the scalability of existing methods is limited, making it difficult to adapt to the dynamic growth of the domain. Traditional MDCTR models usually use one-hot encoding for semantic information such as product titles, thus losing rich semantic information and leading to insufficient generalization of the model. In this article, we propose a novel solution Uni-CTR to address these challenges. Uni-CTR leverages Large Language Model (LLM) to extract layer-wise semantic representations that capture domain commonalities, mitigating the seesaw phenomenon and enhancing generalization. Besides, it incorporates a pluggable domain-specific network to capture domain characteristics, ensuring scalability to dynamic domain growth. Experimental results on public datasets and industrial scenarios show that Uni-CTR significantly outperforms state-of-the-art (SOTA) models. In addition, Uni-CTR shows significant results in zero shot prediction. Code is available at Applied Machine Learning Lab (Pytorch), GitHub (Pytorch) and Gitee (MindSpore).
Förderung
- (Huawei Innovation Research Program), Research Impact Fund
- APRC - CityU New Research Initiatives
- CityU - HKIDS Early Career Research Grant
- Hong Kong ITC Innovation and Technology Fund Midstream Research Programme for Universities Project
- Hong Kong Environmental and Conservation Fund
- SIRG - CityU Strategic Interdisciplinary Research Grant
Zitieren
APA
Fu, Z., Li, X., Wu, C., Wang, Y., Dong, K., Zhao, X., Zhao, M., Guo, H., & Tang, R. (2025). A Unified Framework for Multi-Domain CTR Prediction via Large Language Models. ACM Transactions on Information Systems, 43(5), 1-33. https://doi.org/10.1145/3698878
Vancouver
Fu Z, Li X, Wu C, Wang Y, Dong K, Zhao X, et al. A Unified Framework for Multi-Domain CTR Prediction via Large Language Models. ACM Transactions on Information Systems. 2025;43(5):1-33. doi:10.1145/3698878
BibTeX
@article{Fu2025,
author = {Fu, Zichuan and Li, Xiangyang and Wu, Chuhan and Wang, Yichao and Dong, Kuicai and Zhao, Xiangyu and Zhao, Mengchen and Guo, Huifeng and Tang, Ruiming},
title = {A Unified Framework for Multi-Domain CTR Prediction via Large Language Models},
journal = {ACM Transactions on Information Systems},
year = {2025},
volume = {43},
number = {5},
pages = {1--33},
doi = {10.1145/3698878}
}
EUVIMED