A survey on sequential recommendation

作者：Liwei Pan, Weike Pan, Mei‐Yan Wei, Heng Yin, Zhong Ming · 发表于：Frontiers of Computer Science · 年份：2025 · DOI：10.1007/s11704-025-41329-w · 被引用次数：28 · 研究领域：Recommender Systems and Techniques、Advanced Bandit Algorithms Research、Mobile Crowdsensing and Crowdsourcing

Abstract Different from most conventional recommendation problems, sequential recommendation (SR) focuses on learning users’ preferences by exploiting the internal order and dependency among the interacted items, which has received significant attention from both researchers and practitioners. In recent years, we have witnessed great progress and achievements in this field, necessitating a new survey. In this survey, we study the SR problem from a new perspective (i.e., the construction of an item’s properties), and summarize the most recent techniques used in sequential recommendation such as multi-modal SR, generative SR, LLM-powered SR, ultra-long SR, and data-augmented SR. Moreover, we introduce some frontier research topics in SR, e.g., open-domain SR, data-centric SR, cloud-edge collaborative SR, continuous SR, SR for good, and explainable SR. We believe that our survey could be served as a valuable roadmap for readers in this field.