Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (1): 176-184.DOI: 10.3778/j.issn.1673-9418.2103072

• Artificial Intelligence • Previous Articles     Next Articles

Double End Knowledge Graph Convolutional Networks for Recommender Systems

LI Xiang, YANG Xingyao+(), YU Jiong, QIAN Yurong, ZHENG Jie   

  1. School of Software, Xinjiang University, Urumqi 830008, China
  • Received:2021-03-22 Revised:2021-06-15 Online:2022-01-01 Published:2021-06-17
  • About author:LI Xiang, born in 1996, M.S. candidate, member of CCF. His research interest is recommender system.
    YANG Xingyao, born in 1984, Ph.D., associate professor, member of CCF. His research interests include recommender system, big data and trust computation.
    YU Jiong, born in 1964, Ph.D., professor, Ph.D. supervisor, member of CCF. His research interests include grid computing and parallel computing.
    QIAN Yurong, born in 1980, Ph.D., professor, Ph.D. supervisor, member of CCF. Her research interests include image processing, artificial intelligence and network computing.
    ZHENG Jie, born in 1989, M.S. candidate. His research interest is recommender system.
  • Supported by:
    National Natural Science Foundation of China(61862060);National Natural Science Foundation of China(61966035);National Natural Science Foundation of China(61562086);Education Department Project of Xinjiang Uygur Autonomous Region(XJEDU2016S035);Doctoral Research Start-up Foundation of Xinjiang University(BS150257)

基于知识图谱卷积网络的双端推荐算法

李想, 杨兴耀+(), 于炯, 钱育蓉, 郑捷   

  1. 新疆大学 软件学院,乌鲁木齐 830008
  • 通讯作者: + E-mail: yangxy@xju.edu.cn
  • 作者简介:李想(1996—), 男, 湖北随州人, 硕士研究生, CCF会员,主要研究方向为推荐系统。
    杨兴耀(1984—),男,湖北襄阳人,博士,副教授,CCF会员,主要研究方向为推荐系统、大数据、信任计算。
    于炯(1964—),男,北京人,博士,教授,博士生导师,CCF会员,主要研究方向为网格计算、并行计算。
    钱育蓉(1980—),女,山东德州人,博士,教授,博士生导师,CCF会员,主要研究方向为图像处理、人工智能、网络计算。
    郑捷(1989—),男,四川南充人,硕士研究生,主要研究方向为推荐系统。
  • 基金资助:
    国家自然科学基金(61862060);国家自然科学基金(61966035);国家自然科学基金(61562086);新疆维吾尔自治区教育厅项目(XJEDU2016S035);新疆大学博士科研启动基金(BS150257)

Abstract:

Knowledge graph (KG) provides a data structure to generate hybrid recommendations based on content and collaborative filtering. However, the existing recommendation methods based on knowledge graph take much less account of the user attribute information than the item attribute. To solve this problem, double end knowledge graph convolutional networks (DEKGCN) for recommender systems is proposed. In this algorithm, certain amount of sample of each entity’s neighborhood in the knowledge graph is taken as its high-order acceptance domain, and the related attributes of users in the dataset are taken as its first-order receptive field. Then, when calculating the representation of a given entity and a user, the neighborhood information is combined respectively, and finally the probability of user’s preference for items is obtained. It is an end-to-end framework that integrates multiple information of both user and item sides to learn the vector representation of users and items, which effectively solves the problem of data sparsity and cold start. Experimental results on real datasets show that DEKGCN has better recommendation quality than other baselines.

Key words: recommender system, knowledge graph (KG), graph convolutional networks, knowledge representation learning

摘要:

知识图谱(KG)提供了一种数据结构来生成基于内容和协同过滤的混合推荐,但现有的基于知识图谱推荐方法对用户属性信息的考虑少于对物品属性的考虑,针对这一问题,提出了基于知识图谱卷积网络的双端推荐算法(DEKGCN)。该算法用知识图谱中每一个实体邻域的抽取样本作为其高阶接受域,用数据集中用户的相关属性作为其一阶接受域,在计算给定实体和用户的表示时分别结合各自的邻域信息,最后得到用户对物品的偏好概率。用户端和物品端的多种信息被用来学习用户和物品的向量表示,有效解决了数据稀疏和冷启动问题。在真实数据集上的实验结果表明,DEKGCN与其他基准模型相比推荐质量有较大提升。

关键词: 推荐系统, 知识图谱(KG), 图卷积网络, 知识表示学习

CLC Number: