Dual Test-Time Training for Out-of-Distribution Recommender System
IEEE Transactions on Knowledge and Data Engineering · 2025-06 · 37 (6) · 3312-3326
DOI: 10.1109/tkde.2025.3548160 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2025-06. Verfasst von Xihong Yang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 55-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: National Science and Technology Innovation 2030 Major Project, National Natural Science Foundation of China, China Scholarship Council.
Abstract (Originalsprache)
Deep learning has been widely applied in recommender systems, which has recently achieved revolutionary progress. However, most existing learning-based methods assume that the user and item distributions remain unchanged between the training phase and the test phase. However, the distribution of user and item features can naturally shift in real-world scenarios, potentially resulting in a substantial decrease in recommendation performance. This phenomenon can be formulated as an Out-Of-Distribution (OOD) recommendation problem. To address this challenge, we propose a novel Dual Test-Time-Training framework for OOD Recommendation, termed DT3OR. In DT3OR, we incorporate a model adaptation mechanism during the test-time phase to carefully update the recommendation model, allowing the model to adapt specially to the shifting user and item features. To be specific, we propose a self-distillation task and a contrastive task to assist the model learning both the user’s invariant interest preferences and the variant user/item characteristics during the test-time phase, thus facilitating a smooth adaptation to the shifting features. Furthermore, we provide theoretical analysis to support the rationale behind our dual test-time training framework. To the best of our knowledge, this paper is the first work to address OOD recommendation via a test-time-training strategy. We conduct experiments on five datasets with various backbones. Comprehensive experimental results have demonstrated the effectiveness of DT3OR compared to other state-of-the-art baselines.
Förderung
- National Science and Technology Innovation 2030 Major Project
- National Natural Science Foundation of China
- China Scholarship Council
Zitieren
APA
Yang, X., Wang, Y., Chen, J., Fan, W., Zhao, X., Zhu, E., Liu, X., & Lian, D. (2025). Dual Test-Time Training for Out-of-Distribution Recommender System. IEEE Transactions on Knowledge and Data Engineering, 37(6), 3312-3326. https://doi.org/10.1109/tkde.2025.3548160
Vancouver
Yang X, Wang Y, Chen J, Fan W, Zhao X, Zhu E, et al. Dual Test-Time Training for Out-of-Distribution Recommender System. IEEE Transactions on Knowledge and Data Engineering. 2025;37(6):3312-3326. doi:10.1109/tkde.2025.3548160
BibTeX
@article{Yang2025,
author = {Yang, Xihong and Wang, Yiqi and Chen, Jin and Fan, Wenqi and Zhao, Xiangyu and Zhu, En and Liu, Xinwang and Lian, Defu},
title = {Dual Test-Time Training for Out-of-Distribution Recommender System},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2025},
volume = {37},
number = {6},
pages = {3312--3326},
doi = {10.1109/tkde.2025.3548160}
}
EUVIMED