电子学报2025，Vol.53Issue(8)：2805-2817,13.DOI:10.12263/DZXB.20250144
基于邻域与超图协作的会话推荐
Neighborhood and Hypergraph Collaboration for Session-Based Recommendation
摘要
Abstract
Current session recommendation models excel at extracting users'immediate preferences but struggle to capture the dynamic evolution of user interests over time and context,making it challenging to extract latent relationships between items from short-term interaction sequences.This paper proposes a neighborhood and hypergraph collaboration for session-based recommendation model(NHG-Rec),which first comprehensively utilizes adaptive multi-hop hypergraph con-volution and neighborhood convolution to simultaneously capture explicit and implicit relationships between items;then employs a context-aware dynamic positional attention mechanism to explore the importance of items within a session,there-by capturing users'real-time interests;further adopts multi-view session embeddings through a local-global contrastive learning strategy to capture multi-dimensional item features and distinguish semantic differences.Experimental results dem-onstrate that for Tmall,Diginetica,and Nowplaying benchmark datasets,compared to mainstream baseline models such as SR-GNN,GCE-GNN,and DHCN,this model improves P@10,P@20,MRR@10,and MRR@20 performance metrics by an average of 12.38%,5.47%,6.53%,and 6.39%,respectively.The NHG-Rec model effectively captures the dynamic changes of user interests and multi-dimensional relationships between items.关键词
会话推荐/超图学习/邻域卷积/对比学习/注意力机制Key words
session-based recommendation/hypergraph learning/domain convolution/contrastive learning/atten-tion mechanism分类
信息技术与安全科学引用本文复制引用
陈荣元,文杰彬,黄少年,何晔宇..基于邻域与超图协作的会话推荐[J].电子学报,2025,53(8):2805-2817,13.基金项目
国家自然科学基金(No.41101425) （No.41101425）
长沙市自然科学基金(No.kq2402096,No.kq2208056) National Natural Science Foundation of China(No.41101425) （No.kq2402096,No.kq2208056）
Changsha Natural Science Foun-dation(No.kq2402096,No.kq2208056) （No.kq2402096,No.kq2208056）
