Dual Test-time Training for Out-of-distribution Recommender System

IEEE TRANSACTIONS ON KNOWLEDGE AND DA T A ENGINEERING 1 Dual Test-time Training for Out-of-distribution Recommender System Xihong Y ang, Yiqi Wang, Jin Chen, Wenqi Fan, Xiangyu Zhao, En Zhu, Xinwang Liu, Senior Member, IEEE, Defu Lian Abstract --Deep learning has been widely applied in rec-ommender 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. T o 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. T o 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. T o 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. I NTRODUCTION R ECOMMENDER systems play a crucial role in alleviating the information overload on social media platforms by providing personalized information filtering. In recent years, a plethora of recommendation algorithms have been proposed, including collaborative filtering [1], [2], [3], [4], [5], [6], [7], [8], [9], graph-based recommendation [10], [11], [12], [13], [14], cross-domain recommendation [15], [16], [17], [18] and etc. X. Y ang, Y . Wang, X. Liu and E. Zhu are with School of Computer, National University of Defense Technology, Changsha, 410073, China. J. Chen is with School of Business and Management of the Hong Kong University of Science and Technology. W . Fan is with the Department of Computing (COMP) and Department of Management and Markering (MM), The Hong Kong Polytechnic University.