AI 中文总结
针对序列推荐模型在挑战性用户群体上性能不足的问题，提出自适应快慢推理框架\textsc{DS-Frame}，结合快系统、慢系统与学习选择器，在五组真实数据集上提升了推荐效果并实现了准确率与效率的权衡。
AI 中文摘要
序列推荐模型是现代个性化服务的基础，但其效果在不同用户环境中差异显著。静态单通推荐器通常在常见行为模式上表现良好，但在操作难度大的用户群体（如历史更长或物品画像非主流的用户）上性能下降。为解决这一局限，我们提出\textsc{DS-Frame}，一种用于序列推荐的自适应快慢推理框架。\textsc{DS-Frame}结合了用于高效常规预测的快系统、用于迭代潜在细化的慢系统，以及在可控计算预算下对每个样本进行路由的学习选择器。在五个真实世界数据集上的实验表明，\textsc{DS-Frame}持续提升了代表性序列推荐骨干模型，在挑战性用户群体上获得更大增益，且实现了有效的准确率-效率权衡。这凸显了自适应推理在构建更高效、更鲁棒的推荐系统方面的潜力。代码可在该链接获取。
英文摘要
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}.
Comments12 pages, 4 figures
