返回
Robust prototype-aware representation refinement for LLM-based sequential recommendation
DOI:10.1016/j.patcog.2026.113550.png)
摘要
En 中文
• PRLSR具有三个模块:LLM Augmentation、LAFF和PGRC。
• PRLSR从用户-物品交互序列中提炼细粒度的行为模式。
• LLM augmentation模块利用提示(prompts)生成物品表示并对齐序列编码器。
• LAFF通过抑制低振幅频率分量来消除冗余。
• PGRC通过簇内注意力(intra-cluster attention)和原型引导对比学习(prototype-guided contrastive learning)提升聚类效果。
Keyword:
LLM augmentation
LAFF
PGRC
sequential recommendation
prototype-aware refinement
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
A unified framework of data augmentation using large language models for text-based cross-modal retrieval基于大语言模型的数据增强统一框架,用于文本基础的跨模态检索
PATTERN RECOGNITION
IF7.6
Multi-dimensional Graph Neural Network for Sequential Recommendation面向序贯推荐的多维图神经网络
PATTERN RECOGNITION
IF7.6
Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations用于顺序推荐的深度学习: 算法、影响因素和评估
Towards consistent representations with bidirectional view alignment in graph contrastive learning for recommendation通过双向视图对齐实现图对比学习推荐任务中的表示一致性
Neurocomputing
IF6.5
J. Jia, Y. Wang, Y. Li, H. Chen, X. Bai, Z. Liu, J. Liang, Q. Chen, H. Li, P. Jiang, K. Gai, LEARN: knowledge adaptation from large language model to recommendation for practical industrial application, in: AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia, PA, USA, AAAI Press, 2025, pp. 11861–11869. doi:10.1609/AAAI.V39I11.33291.J. Jia, Y. Wang, Y. Li, H. Chen, X. Bai, Z. Liu, J. Liang, Q. Chen, H. Li, P. Jiang, K. Gai, LEARN: 从大型语言模型到推荐的工业实践应用知识适应,刊于:AAAI-25,由人工智能促进协会赞助,2025年2月25日-3月4日,美国宾夕法尼亚州费城,AAAI Press出版,2025年,第11861-11869页。doi:10.1609/AAAI.V39I11.33291.

