用大模型压缩用户行为，更准预测长期与短期兴趣。
CHIME: A Compressive Framework for Holistic Interest Modeling
- 用大模型整合多样行为数据，保留完整上下文信息。
- 多粒度对比学习捕捉持久与瞬时兴趣模式。
- 残差向量量化生成紧凑嵌入，适合大规模推荐系统。
全面建模用户兴趣对提升推荐系统性能至关重要，但面临计算成本高和难以处理多样化信息的挑战。现有基于搜索的方法在行为选择过程中可能丢失关键信号。为此，我们提出CHIME：一种用于全面兴趣建模的压缩框架。该框架利用适配的大语言模型对异构输入的完整用户行为进行编码，引入多粒度对比学习目标以捕捉持久性与瞬时性兴趣模式，并采用残差向量量化生成紧凑嵌入。CHIME在多个数据集上表现出卓越的排序性能，为推荐系统中的可扩展全面兴趣建模提供了稳健解决方案。
原文摘要 · Abstract (English)
Modeling holistic user interests is important for improving recommendation systems but is challenged by high computational cost and difficulty in handling diverse information with full behavior context. Existing search-based methods might lose critical signals during behavior selection. To overcome these limitations, we propose CHIME: A Compressive Framework for Holistic Interest Modeling. It uses adapted large language models to encode complete user behaviors with heterogeneous inputs. We introduce multi-granular contrastive learning objectives to capture both persistent and transient interest patterns and apply residual vector quantization to generate compact embeddings. CHIME demonstrates superior ranking performance across diverse datasets, establishing a robust solution for scalable holistic interest modeling in recommendation systems.
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。