《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (4): 1087-1092.DOI: 10.11772/j.issn.1001-9081.2021071269

• CCF第36届中国计算机应用大会 (CCF NCCA 2021) • 上一篇    

融合协同过滤信息的知识图注意力网络

顾军华1,2, 王锐1, 李宁宁1, 张素琪3()   

  1. 1.河北工业大学 人工智能与数据科学学院,天津 300401
    2.河北省大数据计算重点实验室(河北工业大学),天津 300401
    3.天津商业大学 信息工程学院,天津 300134
  • 收稿日期:2021-07-16 修回日期:2021-08-17 接受日期:2021-08-23 发布日期:2021-08-17 出版日期:2022-04-10
  • 通讯作者: 张素琪
  • 作者简介:顾军华(1966—),男,天津人,教授,博士,CCF会员,主要研究方向:智能信息处理、数据挖掘
    王锐(1995—),男,江苏泰州人,硕士研究生,主要研究方向:推荐系统
    李宁宁(1994—),女,河南周口人,硕士研究生,主要研究方向:推荐系统
  • 基金资助:
    国家自然科学基金资助项目(61802282);天津市科技计划项目技术创新引导专项(20YDTPJC00670)

Knowledge graph attention network fusing collaborative filtering information

Junhua GU1,2, Rui WANG1, Ningning LI1, Suqi ZHANG3()   

  1. 1.School of Artificial Intelligence and Data Science,Hebei University of Technology,Tianjin 300401,China
    2.Hebei Province Key Laboratory of Big Data Computing (Hebei University of Technology),Tianjin 300401,China
    3.School of Information Engineering,Tianjin University of Commerce,Tianjin 300134,China
  • Received:2021-07-16 Revised:2021-08-17 Accepted:2021-08-23 Online:2021-08-17 Published:2022-04-10
  • Contact: Suqi ZHANG
  • About author:GU Junhua, born in 1966, Ph. D., professor. His research interests include intelligent information processing, data mining.
    WANG Rui, born in 1995, M. S. candidate. His research interests include recommendation system.
    LI Ningning, born in 1994, M. S. candidate. Her research interests include recommendation system.
  • Supported by:
    National Natural Science Foundation of China(61802282);Technology Innovation Guidance Special Project of Tianjin Science and Technology Plan(20YDTPJC00670)

摘要:

知识图谱(KG)能够缓解协同过滤算法存在的数据稀疏和冷启动问题,在推荐领域被广泛地研究和应用。现有的很多基于KG的推荐模型混淆了用户物品二部图中的协同过滤信息和KG中实体间的关联信息,导致学习到的用户向量和物品向量无法准确表达其特征,甚至引入与用户、物品无关的信息从而干扰推荐。针对上述问题提出一种融合协同信息的知识图注意力网络(KGANCF)。首先,为了避免KG实体信息的干扰,网络的协同过滤层从用户物品二部图中挖掘出用户和物品的协同过滤信息;然后,在知识图注意力嵌入层中应用图注意力机制,从KG中继续提取与用户和物品密切相关的属性信息;最后,在预测层将用户物品的协同过滤信息和KG中的属性信息融合,得到用户和物品最终向量表示,进而预测用户对物品的评分。在MovieLens-20M和Last.FM数据集上进行了实验,与协同知识感知注意力网络(CKAN)相比,KGANCF在MovieLens-20M数据集上的F1分数提升了1.1个百分点,曲线下面积(AUC)提升了0.6个百分点;而在KG相对稀疏的Last.FM数据集上,模型的F1分数提升了3.3个百分点,AUC提升了8.5个百分点。实验结果表明,KGANCF能够有效提高推荐结果的准确度,在KG稀疏的数据集上显著优于协同知识嵌入(CKE)、知识图谱卷积网络(KGCN)、知识图注意网络(KGAT)和CKAN模型。

关键词: 推荐系统, 知识图谱, 协同过滤, 注意力机制, 图神经网络

Abstract:

Since Knowledge Graph(KG) can alleviate the problems of data sparsity and cold start in collaborative filtering algorithm, it has been widely studied and applied in the recommendation field. Many existing recommendation models based on KG confuse the collaborative filtering information in user-item bipartite graph and the association information between entities in KG, resulting in the learned user vector and item vector cannot accurately express the characteristics of users and items, and even introducing wrong information to interfere with recommendation. Regarding the issues above, a model called KG Attention Network fusing Collaborative Filtering information (KGANCF) was proposed. Firstly, the collaborative filtering information of users and items was dug out by the collaborative filtering layer of the network from the user-item bipartite graph, avoiding the interference of the entity information of KG. Then, the graph attention mechanism was applied in the KG attention embedding layer, the attribute information closely related to users and items was extracted from KG. Finally, the collaborative filtering information and the attribute information in KG were merged at the prediction layer to obtain the final vector representations of users and items, and then the scores of users to items were predicted. The experiments were carried out on MovieLens-20M and Last.FM datasets. Compared with the results of Collaborative Knowledge-aware Attentive Network (CKAN), on Movielens-20M, F1-score of KGANCF improves by 1.1 percentage points while Area Under Curve (AUC) improves by 0.6 percentage points; on Last.FM, F1-score improves by 3.3 percentage points and AUC improves by 8.5 percentage points. Experimental results show that KGANCF can effectively improve the accuracy of recommendation results, and is significantly better than CKE (Collaborative Knowledge base Embedding),KGCN (Knowledge Graph Convolutional Network),KGAT (Knowledge Graph Attention Network) and CKAN models on datasets with sparse KG.

Key words: recommender system, Knowledge Graph (KG), collaborative filtering, attention mechanism, graph neural network

中图分类号: