计算机应用研究2024，Vol.41Issue(1)：45-50,58,7.DOI:10.19734/j.issn.1001-3695.2023.05.0283
基于多层次视图对比学习的知识感知推荐算法
Knowledge-aware recommendation algorithm based on multi-level view contrastive learning
摘要
Abstract
The existing graph neural network(GNN)-based recommendation models have a natural limitation,namely the sparse supervision signal problem and coarse-grained relation modeling.These models can't identify user-item interaction rela-tionships at a finer granularity,potentially leading to a decrease in their actual performance.Inspired by the successful appli-cation of contrastive learning in mining supervision signals,this paper proposed a KRMVC algorithm.The KRMVC framework constructed four graph views,including a global structural view,a local intention view,a coordination view,and a collabora-tion view.Additionally,the algorithm designed a new GNN information aggregation scheme to extract useful information about user intents and encoded it into the representations of users and items.KRMVC performed contrastive learning across the four views at both global and local levels,used a multi-task strategy to jointly optimize the recommendation supervision task and contrastive learning task for performance improvement.Experimental results demonstrate that the model achieves improvements in AUC values by 1.1％and 0.7％,F1 scores by 1.4％and 1.0％,and recall@K scores surpass state-of-the-art baselines on the MovieLens and Yelp2018 datasets.关键词
推荐系统/知识图谱/对比学习/图神经网络Key words
recommender system/knowledge graph/contrastive learning/graph neural network分类
信息技术与安全科学引用本文复制引用
王正东,王靖,杨晓君,林浩申..基于多层次视图对比学习的知识感知推荐算法[J].计算机应用研究,2024,41(1):45-50,58,7.基金项目
广东省面上自然基金资助项目 （）
国防重点实验室开放基金资助项目 （）
国家自然基金青年项目 （）
