计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (8): 1681-1705.DOI: 10.3778/j.issn.1673-9418.2112070

• 综述·探索 • 上一篇    下一篇

推荐任务中知识图谱嵌入应用研究综述

田萱1,+(), 陈杭雪1,2   

  1. 1. 北京林业大学 信息学院,北京 100083
    2. 国家林业草原林业智能信息处理工程技术研究中心,北京 100083
  • 收稿日期:2021-12-17 修回日期:2022-02-24 出版日期:2022-08-01 发布日期:2022-08-19
  • 通讯作者: +E-mail: tianxuan@bjfu.edu.cn
  • 作者简介:田萱(1976—),女,山东济宁人,博士,副教授,主要研究方向为智能信息处理、文本挖掘等。
    陈杭雪(1997—),女,浙江衢州人,硕士研究生,主要研究方向为智能信息处理、个性化推荐等。
  • 基金资助:
    国家重点研发计划(2018YFC1603305)

Survey on Applications of Knowledge Graph Embedding in Recommendation Tasks

TIAN Xuan1,+(), CHEN Hangxue1,2   

  1. 1. School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China
    2. Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration, Beijing 100083, China
  • Received:2021-12-17 Revised:2022-02-24 Online:2022-08-01 Published:2022-08-19
  • About author:TIAN Xuan, born in 1976, Ph.D., associate professor. Her research interests include intelligent information processing, text mining, etc.
    CHEN Hangxue, born in 1997, M.S. candidate. Her research interests include intelligent information processing, personalized recommendation, etc.
  • Supported by:
    the National Key Research and Development Program of China(2018YFC1603305)

摘要:

推荐系统旨在为用户推荐个性化内容以提升用户体验,但目前仍面临着诸如可解释性差、冷启动问题和序列化推荐建模等挑战。近年来,蕴含大量结构化知识和语义信息的知识图谱(KG)被广泛应用于各种推荐任务中以期缓解上述问题。对不同推荐任务中知识图谱嵌入(KGE)的创新应用进行系统性综述。首先梳理出采用知识图谱嵌入的三类常见推荐任务以及知识图谱嵌入应用的四种目的;然后根据技术不同归纳总结出四类知识图谱嵌入方法,包括传统嵌入方法、嵌入传播方法、异质图嵌入方法和基于图神经网络的方法;进一步详细阐述了每类方法在不同推荐任务中的使用特点及应用策略,评价其优点和局限性等,并从多个方面对方法间的联系与区别进行定性和定量分析;最后,针对面向不同推荐任务中知识图谱嵌入应用的发展趋势提出一些看法,从多个角度展望了该领域未来值得关注的几个发展方向。

关键词: 知识图谱嵌入(KGE), 推荐任务, 可解释推荐, 冷启动, 序列化推荐, 知识图谱嵌入应用

Abstract:

Recommendation systems are designed to recommend personalized content to improve user experience. At present, the recommendation systems still face some challenges such as poor interpretability, cold start problem and serialized recommendation modeling. Recently, the knowledge graph (KG) containing a large amount of semantic and structural information has been widely used in a variety of different recommendation tasks to alleviate the above problems. This paper systematically reviews the innovative applications of knowledge graph embedding (KGE) in different recommendation tasks. It first summarizes three common recommendation tasks and four applying goals of knowledge graph embedding. Then, it generalizes four types of knowledge graph embedding methods according to specific technologies, including traditional embedding method, embedding propagation method, heterogeneous graph embedding method and graph neural network based method. It further elaborates on the applying characteristics and strategies of the above four methods in different recommendation tasks, and evaluates advantages and limitations of each method. Also, it conducts qualitative and quantitative analysis of the associations and differences of four methods from multiple aspects. Finally, it puts forward some views on the development trend of applying knowledge graph embedding for recommendation systems, and proposes several noteworthy development directions in the future from multiple perspectives.

Key words: knowledge graph embedding (KGE), recommendation tasks, explainable recommendation, cold start, serialization recommendation, application of knowledge graph embedding

中图分类号: