Journal of Frontiers of Computer Science and Technology ›› 2021, Vol. 15 ›› Issue (6): 1103-1113.DOI: 10.3778/j.issn.1673-9418.2006066

• Artificial Intelligence • Previous Articles     Next Articles

Citation Recommendation via Hierarchical Attributed Network Representation Learning

CHEN Jie, LIU Yang, ZHAO Shu, ZHANG Yanping   

  1. 1.Key Laboratory of Intelligent Computing & Signal Processing, Ministry of Education, Anhui University, Hefei 230601, China
    2.School of Computer Science and Technology, Anhui University, Hefei 230601, China
    3.Sinosteel Maanshan General Institute of Mining Research Co., Ltd., Maanshan, Anhui 243000, China
  • Online:2021-06-01 Published:2021-06-03

利用多粒度属性网络表示学习进行引文推荐

陈洁刘洋赵姝张燕平   

  1. 1.安徽大学 计算智能与信号处理教育部重点实验室,合肥 230601
    2.安徽大学 计算机科学与技术学院,合肥 230601
    3.中钢集团马鞍山矿山研究总院股份有限公司,安徽 马鞍山 243000

Abstract:

Citation recommendation (CR) is able to intelligently generate a paper list related to a query paper, which is of great value to researches. CR problem is related to papers?? semantic and structural information. Recently, network representation learning (NRL) based CR problem has gained extensive attention. However, existing studies all use single granularity networks to model CR, which have the disadvantages of high computational complexity and large memory consumption. For overcoming this challenge, this paper proposes a citation recommendation algorithm based on hierarchical attributed network representation learning (CR-HANRSL), which can greatly improve the efficiency of NRL while taking into account semantic and structural features of papers. First, the network is coarsened into a series of smaller networks based on papers?? attributes and author relationship repeatedly, and the super-nodes are made to contain child-nodes?? attributes after coarsening for further constructing semantic links. Second, this paper uses the single granularity NRL to learn the roughened network and graph convolutional network to refine the learned network representations. Finally, a multi-modal feature representation similarity between papers is generated to get a paper recommendation list. A mass of experimental results on AAN and DBLP two datasets show that the proposed method can improve NRL??s efficiency while learning high-quality network feature representations.

Key words: citation recommendation (CR), hierarchical attributed network, semantic links, representation learning

摘要:

引文推荐(CR)聚焦于智能化地产生与查询文章相关的文献列表,对科学研究具有重要价值。引文推荐有关于文章的语义信息和结构信息,近年来,基于网络表示学习(NRL)的引文推荐获得广泛关注。但现有研究使用单粒度网络来建模引文推荐问题,存在计算复杂度高、内存消耗大的弊端。为克服这个挑战,提出一种基于多粒度属性网络表示学习的引文推荐算法(CR-HANRSL),可以大大提升网络表示学习效率并同时兼顾文章的语义和结构特征。首先,根据文章结点属性的语义关联度和作者关系反复将网络粗化成更小的网络,并在每次粗化后都让超结点融合子结点的文本属性为粗化后的网络计算语义连边。随后,利用单粒度网络表示学习方法学习粗化后的网络特征表示并通过学习图卷积神经网络,对原网络的表示进行细化。最后,融合文章间多模态特征表示相似度产生推荐列表。在AAN和DBLP两个数据集上的实验结果表明提出的方法可以在学习高质量网络特征表示的前提下大大提升网络表示学习效率。

关键词: 引文推荐, 多粒度属性网络, 语言连边, 表示学习