基于虚拟关系知识图可自适应聚合的推荐算法

李源1; 杨谋均2

基于虚拟关系知识图可自适应聚合的推荐算法

引用本文：李源1，杨谋均2.基于虚拟关系知识图可自适应聚合的推荐算法[J].计算技术与自动化,2024,(4):73-78

摘要点击次数: 214

全文下载次数: 0

作者	单位
李源1，杨谋均2	（1.湖南省电子信息产业研究院，湖南长沙 410001；2.中车株洲电力机车研究所有限公司，湖南株洲 412001）

中文摘要:在信息爆炸的时代，推荐算法成为应对信息过载的有效手段。近年来，图神经网络（GNN）以其强大的建模能力和应对冷启动的优势被广泛应用于推荐算法。本文提出了一种基于深度强化学习与GNN-R的联合训练框架，解决GNN-R中固定层数和聚合策略的问题，通过间隔经验回放和延后奖励机制，优化了推荐模型的学习过程。在此基础上，提出了自适应优化GNN-R聚合层数和虚拟关系数量的两个优化算法，改进了VRKG4Rec模型的性能。实验结果表明，两个优化算法对比VRKG4Rec模型都有较好的性能提升。

中文关键词:推荐算法图神经网络深度强化学习知识图谱

Recommendation Algorithm Based on Adaptive Aggregation of Virtual Relationship Knowledge Graph

Abstract:In the era of information explosion, recommendation algorithms have become an effective means to cope with information overload. In recent years, graph neural networks (GNN) have been widely applied in recommendation algorithms due to their powerful modeling capabilities and advantages in addressing cold start issues. A joint training framework based on deep reinforcement learning and GNN-R is proposed in this paper to address the fixed-layer and aggregation strategy issues in GNN-R. By employing interval experience replay and delayed reward mechanisms, the learning process of the recommendation model is optimized. Building upon this, two optimization algorithms for adaptively optimizing the aggregation layers and virtual relation quantities in GNN-R are proposed, enhancing the performance of the VRKG4Rec model. Experimental results demonstrate significant performance improvements of the two optimization algorithms compared to the VRKG4Rec model.

keywords:recommendation algorithm graph neural network deep reinforcement learning knowledge graph

查看全文 查看/发表评论 下载pdf阅读器