Recommender System as Slow and Fast Thinkers

2026-09-02

AI Summary

为解决推荐系统在不同用户环境下的效果差异，提出DS-Frame框架，结合快速预测和慢速优化，并通过学习选择器来平衡效率与准确性。

Abstract

Sequential recommendation models are foundational to modern personalized services, yet their effectiveness varies substantially across heterogeneous user environments. In particular, static one-pass recommenders often perform well on common behavior patterns but degrade on operationally challenging user groups, such as users with longer histories or less mainstream item profiles. To address this limitation, we propose \textsc{DS-Frame}, an adaptive fast--slow inference framework for sequential recommendation. \textsc{DS-Frame} combines a Fast System for efficient routine prediction, a Slow System for iterative latent refinement, and a learned selector that routes each sample under a controllable computation budget. Experiments on five real-world datasets show that \textsc{DS-Frame} consistently improves representative sequential recommendation backbones, with larger gains on challenging groups and effective accuracy--efficiency trade-offs. This highlights the potential of adaptive inference for more efficient and robust recommendation. Code is available at \href{https://github.com/ZichenYuan233/Recommender-System-as-Slow-and-Fast-Thinkers}{this link}.

Problem

• Sequential Recommendation
• Heterogeneous User Environments
• Operationally Challenging User Groups

Innovation

• adaptive fast-slow inference
• sequential recommendation
• DS-Frame
• computation budget