计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (6): 1343-1353.DOI: 10.3778/j.issn.1673-9418.2110057

• 人工智能 • 上一篇    下一篇

融合知识图谱与图卷积网络的混合推荐模型

郭晓旺1, 夏鸿斌1,2,+(), 刘渊1,2   

  1. 1. 江南大学 人工智能与计算机学院,江苏 无锡 214122
    2. 江苏省媒体设计与软件技术重点实验室,江苏 无锡 214122
  • 收稿日期:2021-10-22 修回日期:2022-01-25 出版日期:2022-06-01 发布日期:2022-06-20
  • 通讯作者: + E-mail: hbxia@163.com
  • 作者简介:郭晓旺(1996—),女,河南安阳人,硕士研究生,主要研究方向为机器学习、推荐系统。
    夏鸿斌(1972—),男,安徽庐江人,博士,副教授,CCF会员,主要研究方向为个性化推荐、自然语言处理、网络优化。
    刘渊(1967—),男,江苏无锡人,教授,CCF高级会员,主要研究方向为网络安全、社交网络。
  • 基金资助:
    国家自然科学基金(61972182)

Hybrid Recommendation Model of Knowledge Graph and Graph Convolutional Network

GUO Xiaowang1, XIA Hongbin1,2,+(), LIU Yuan1,2   

  1. 1. School of Artificial Intelligence and Computer, Jiangnan University, Wuxi, Jiangsu 214122, China
    2. Jiangsu Key Laboratory of Media Design and Software Technology, Wuxi, Jiangsu 214122, China
  • Received:2021-10-22 Revised:2022-01-25 Online:2022-06-01 Published:2022-06-20
  • About author:GUO Xiaowang, born in 1996, M.S. candidate.Her research interests include machine learning and recommendation system.
    XIA Hongbin, born in 1972, Ph.D., associate professor, member of CCF. His research interests include personalized recommendation, natural language processing and network optimization.
    LIU Yuan, born in 1967, professor, senior mem-ber of CCF. His research interests include network security and social network.
  • Supported by:
    National Natural Science Foundation of China(61972182)

摘要:

针对当前多数基于知识图谱的推荐模型未能充分对用户特征建模,且未考虑知识图谱中实体间的邻域关系的问题,提出了一种融合知识图谱与图卷积网络的混合推荐模型(HKC)。首先,利用KGCN算法捕捉项目间的相关性,通过邻域聚合计算得到项目的特征向量;然后,通过协作传播提取知识图谱中与用户相联系的实体,使用交替学习的方式同时优化模型预测单元和知识图谱嵌入单元,通过交互单元计算得到用户的特征向量;最后,将用户特征向量和项目特征向量送入预测环节,通过向量的内积运算以及归一化操作计算用户与项目的交互概率。在三种公开数据集上与七个基线模型进行了对比实验,在MovieLens-1M数据集上,AUC提升了0.25%~37.41%,ACC提升了0.78%~49.44%;在Book-Crossing数据集上,AUC提升了0.04%~19.38%,ACC提升了6.49%~18.60%;在Last.FM数据集上,AUC提升了1.33%~33.50%,ACC提升了0.36%~30.66%。实验结果表明,提出的混合推荐模型与其他具有代表性的推荐模型相比具有良好的推荐性能。

关键词: 推荐系统, 知识图谱, 交替学习, 邻域聚合

Abstract:

Concerning the failure of most current recommendation models based on knowledge graph to adequately model users’ characteristics, the neighborhood relationship between entities in the knowledge graph is not considered. This paper proposes a hybrid recommendation model that combines knowledge graph and graph convolutional network (HKC). Firstly, the KGCN (knowledge graph convolutional networks for recommender systems) algorithm is used to capture the correlation between items, and obtain the feature vector of the item through neighborhood aggregation unit. The entities associated with the user in the knowledge graph are extracted through collaborative propagation. Then the model uses the alternate learning method to optimize the model prediction unit and the knowledge graph embedding unit at the same time, and calculate the user’s feature vector through the interaction unit. Finally, the user feature vector and the item feature vector are sent to the prediction link and the interaction probability between the user and the item is calculated through the inner product operation and normalization of the vector. Comparative experiments are conducted on three public datasets with seven baseline models. On the MovieLens-1M dataset, AUC is increased by 0.25% to 37.41%, and ACC is increased by 0.78% to 49.44%; on the Book-Crossing dataset, AUC is increased by 0.04% to 19.38%, and ACC is increased by 6.49% to 18.60%; on the Last.FM dataset, AUC is increased by 1.33% to 33.50%, and ACC is increased by 0.36% to 30.66%. Experimental results show that the model proposed has improved performance compared with other benchmark models.

Key words: recommender system, knowledge graph, alternate learning, neighborhood aggregation

中图分类号: