系统梳理序列推荐最新方法与前沿方向，助你快速掌握领域全貌。
A Survey on Sequential Recommendation
- 从物品属性构建视角重新审视序列推荐问题
- 涵盖纯ID、多模态、生成式、大模型等主流技术路线
- 覆盖长序列、可解释性、数据驱动等前沿研究方向
与传统推荐不同，序列推荐通过挖掘用户交互物品间的顺序和依赖关系来学习偏好，近年来受到广泛关注。本文从物品属性构建的新视角出发，系统总结了序列推荐领域的最新技术，包括基于纯ID的推荐、融合辅助信息的推荐、多模态推荐、生成式推荐、大语言模型驱动的推荐、超长序列推荐以及数据增强推荐。此外，还介绍了开放域推荐、数据导向推荐、边缘协同推荐、连续推荐、向善推荐和可解释推荐等前沿课题。本综述可为该领域的研究者提供有价值的参考路径。
原文摘要 · Abstract (English)
Different from most conventional recommendation problems, sequential recommendation 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 pure ID-based SR, SR with side information, multi-modal SR, generative SR, LLM-powered SR, ultra-long SR and data-augmented SR. Moreover, we introduce some frontier research topics in sequential recommendation, e.g., open-domain SR, data-centric SR, could-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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。