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

2024-07-22

arXiv.org

AI Summary

Recommender systems suffer significant performance degradation when user and item feature distributions shift over time—a challenge known as out-of-distribution (OOD) recommendation. To address this, we propose DT3OR, a test-time dual-task adaptation framework that pioneers the application of test-time training to OOD recommendation. DT3OR dynamically adapts to evolving data distributions during inference via two complementary mechanisms: self-distillation to model invariant user interests, and contrastive learning to capture distribution-specific, mutable features. A rigorous theoretical analysis ensures interpretability and provides convergence guarantees. Extensive experiments across three public benchmarks and multiple backbone architectures demonstrate that DT3OR consistently outperforms state-of-the-art methods under diverse distribution shifts, validating its robustness and generalization capability in real-world OOD scenarios.

Technology Category

• Machine Learning: Online Learning & Bandits
• Search and Optimization: Distributed Search
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Deep learning has been widely applied in recommender systems, which has achieved revolutionary progress recently. 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 specially adapt 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 three datasets with various backbones. Comprehensive experimental results have demonstrated the effectiveness of DT3OR compared to other state-of-the-art baselines.

Problem

• Addresses Out-Of-Distribution (OOD) recommendation challenges
• Proposes Dual Test-Time-Training (DT3OR) framework for model adaptation
• Enhances recommendation performance under shifting user/item features

Innovation

• Dual Test-Time-Training for OOD recommendation
• Self-distillation and contrastive tasks adaptation
• Model updates during test-time for shifting features