摘要
跨项目社会推荐是一种将社交关系整合到推荐系统中的方法。社会化推荐中包含用户-项目交互图和社交网络图,用户是连接这两个图的桥梁,其表示学习对提升社会化推荐的性能至关重要。然而,现有方法主要使用用户或项目的静态属性和社交网络中的显式朋友关系来进行表示学习,用户和项目交互的时序信息及隐式朋友关系未得到充分利用。因此,在社会化推荐中,如何有效利用时序信息和社交信息成为重要的研究课题之一。文中通过建模用户的隐式朋友和项目的社交属性,提出了一种新颖的基于高阶和时序特征的图神经网络社会化推荐算法(Graph Neural Networks Social Recommendation Based on High-order and Temporal Features)模型,简称HTGSR。HTGSR首先利用门控递归单元对基于项目的用户表征进行建模,以反映用户的近期动态偏好,并定义一个高阶建模单元来提取用户的高阶连通特征,挖掘用户的隐式朋友信息;其次利用注意力机制获取基于社交关系的用户表征;然后提出不同的项目社交网络的构建方式,并利用注意力机制来获取项目表征;最后将用户和项目的潜在表征输入到多层感知机,完成用户对项目的评分预测。在两个数据集上进行详细的实验,并将实验结果与多种类型的推荐算法进行比较,结果表明HTGSR模型在两个数据集上的效果均较优。
Cross-item social recommendation is a method of integrating social relationships into the recommendation system.In social recommendation, user is the bridge connecting user-item interaction graph and user-user social graph.So user representation learning is essential to improve the performance of social recommendation.However, existing methods mainly use static attributes of users or items and explicit friend information in social networks for representations learning, and the temporal information of the interaction between users and items and their implicit friend information are not fully utilized.Therefore, in social recommendation, effective use of temporal information and social information has become one of the important research topics.This paper focuses on the temporal information of the interaction between users and items, and gives full play to the advantages of social network, modeling the user’s implicit friends and item’s social attributes.This paper proposes a novel graph neural networks social recommendation based on high-order and temporal features, referred to as HTGSR.Firstly, the framework uses gated recurrent unit to model item-based user representations to reflect the user’s recent preferences, and defines a high-order mo-deling unit to extract the user’s high-order connected features and obtain the user’s implicit friend information.Secondly, HTGSR uses attention mechanism to obtain social-based user representation.Thirdly, the paper proposes different ways to construct item’s social networks, and uses the attention mechanism to obtain item representations.Finally, the user’s and item’s representations are input to the MLP to complete the user’s rating prediction for the item.The paper conducts specific experiments on two public and real-world datasets, and compares the experimental results with different recommendation algorithms.The results show that the HTGSR has achieved good results on the two datasets.
作者
于健
赵满坤
高洁
王聪源
李亚蓉
张文彬
YU Jian;ZHAO Mankun;GAO Jie;WANG Congyuan;LI Yarong;ZHANG Wenbin(College of Intelligence and Computing,Tianjin University,Tianjin 300354,China;Tianjin International Engineering Institute,Tianjin University,Tianjin 300354,China;Information and Network Center,Tianjin University,Tianjin 300354,China;Tianjin Key Laboratory of Advanced Networks and Applications,Tianjin 300354,China;Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin 300354,China)
出处
《计算机科学》
CSCD
北大核心
2023年第3期49-64,共16页
Computer Science
基金
国家自然科学基金(61877043,61877044)。
关键词
社会化推荐
时序特征
图神经网络
高阶特征
Social recommendation
Temporal features
Graph neural networks
High-order features
作者简介
于健,born in 1974,senior engineer.His main research interests include data mining,database,and computer network research.(yujian@tju.edu.cn);通讯作者: 张文彬,born in 1983,engineer.His main research interests include data mining and education informatization research.(zhangwenbin@tju.edu.cn)。
