Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (7): 1865-1870.DOI: 10.11772/j.issn.1001-9081.2020081254

Special Issue: 人工智能

• Artificial intelligence • Previous Articles     Next Articles

Knowledge graph driven recommendation model of graph neural network

LIU Huan1,2, LI Xiaoge1,2, HU Likun3, HU Feixiong3, WANG Penghua1,2   

  1. 1. School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an Shaanxi 710121, China;
    2. Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing(Xi'an University of Posts and Telecommunications), Xi'an Shaanxi 710121, China;
    3. Department of Intelligent Operation and Maintenance, Shenzhen Tencent Computer Systems Company Limited, Shenzhen Guangdong 518000, China
  • Received:2020-08-17 Revised:2020-12-24 Online:2021-07-10 Published:2021-01-22
  • Supported by:
    This work is partially supported by the Innovation Capacity Support Project of Shaanxi Province (2019PT-12), the National Key Research and Development Program of China (2018YFB1403004).

基于知识图谱驱动的图神经网络推荐模型

刘欢1,2, 李晓戈1,2, 胡立坤3, 胡飞雄3, 王鹏华1,2   

  1. 1. 西安邮电大学 计算机学院, 西安 710121;
    2. 陕西省网络数据分析与智能处理重点实验室(西安邮电大学), 西安 710121;
    3. 深圳腾讯计算机系统有限公司 智能化运维部, 广东 深圳 518000
  • 通讯作者: 李晓戈
  • 作者简介:刘欢(1995-),男,陕西咸阳人,硕士研究生,主要研究方向:自然语言处理、推荐系统;李晓戈(1962-),男,安徽合肥人,教授,博士,主要研究方向:自然语言处理、机器学习;胡立坤(1991-),男,湖北黄冈人,硕士,主要研究方向:智能化运维、数据挖掘;胡飞雄(1990-),男,江西九江人,主要研究方向:智能化运维、数据挖掘;王鹏华(1991-),男,陕西咸阳人,硕士,主要研究方向:自然语言处理、数据挖掘。
  • 基金资助:
    国家重点研发计划项目(2018YFB1403004);陕西省创新能力支撑计划项目(2019PT-12)。

Abstract: The abundant structure and association information contained in Knowledge Graph (KG) can not only alleviate the data sparseness and cold-start in the recommender systems, but also make personalized recommendation more accurately. Therefore, a knowledge graph driven end-to-end recommendation model of graph neural network, named KGLN, was proposed. First, a signal-layer neural network framework was used to fuse the features of individual nodes in the graph, then the aggregation weights of different neighbor entities were changed by adding influence factors. Second, the single-layer was extended to multi-layer by iteration, so that the entities were able to obtain abundant multi-order associated entity information. Finally, the obtained features of entities and users were integrated to generate the prediction score for recommendation. The effects of different aggregation methods and influence factors on the recommendation results were analyzed. Experimental results show that on the datasets MovieLen-1M and Book-Crossing, compared with the benchmark methods such as Factorization Machine Library (LibFM), Deep Factorization Machine (DeepFM), Wide&Deep and RippleNet, KGLN obtains an AUC (Area Under ROC (Receiver Operating Characteristic) curve) improvement of 0.3%-5.9% and 1.1%-8.2%, respectively.

Key words: recommender system, Knowledge Graph (KG), graph neural network, network feature learning, personalized recommendation, interest mining

摘要: 知识图谱(KG)蕴含丰富的结构与关联信息,不仅可以缓解推荐系统中数据稀疏、冷启动等问题,还可以更准确地进行个性化推荐,因此提出一种基于知识图谱驱动的端到端图神经网络推荐模型KGLN。首先使用单层神经网络框架对图中单个节点进行特征融合,并加入影响因子来改变不同邻居实体的聚合权重;然后通过迭代的方式将单层扩展到多层,使实体可以获得丰富的多阶关联实体信息;最后结合实体特征与用户特征产生预测评分进行推荐。分析并研究了不同聚合方法及影响因子对推荐效果的影响。实验结果表明,在数据集MovieLens-1M以及Book-Crossing上与基准方法因子分解库(LibFM)、深度分解机(DeepFM)、Wide&Deep、RippleNet的对比中,KGLN的曲线下面积(AUC)分别提升了0.3%~5.9%和1.1%~8.2%。

关键词: 推荐系统, 知识图谱, 图神经网络, 网络特征学习, 个性化推荐, 兴趣挖掘

CLC Number: