Relational Topic Factorization for Link Prediction in Document Networks

被引:0
|
作者
Zhang, Wei [1 ,2 ]
Li, Jiankou [1 ,2 ]
Yong, Xi [1 ,2 ]
机构
[1] Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China
[2] Univ Chinese Acad Sci, Sch Informat Sci & Engn, Beijing, Peoples R China
关键词
Link prediction; Matrix factorization; Latent Dirichlet allocation;
D O I
10.1007/978-3-319-13123-8_8
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Link prediction is one of the fundamental problems in complex networks. In this paper, we focus on link prediction in document networks, in which nodes are text documents. We propose the relational topic factorization model (RTF), a model that combines topic models and matrix factorization. We also develop an efficient Monte Carlo EM algorithm for learning the parameters. Empirical results show that our model outperforms other state-of-the-art ones, and can give better understanding of the documents.
引用
收藏
页码:96 / 107
页数:12
相关论文
共 50 条
  • [41] Link prediction in bipartite networks via deep autoencoder-like nonnegative matrix factorization
    Yu, Wei
    Fu, Jiale
    Zhao, Yanxia
    Shi, Hongjin
    Chen, Xue
    Shen, Shigen
    Gao, Xiao-Zhi
    APPLIED SOFT COMPUTING, 2025, 169
  • [42] Deep non-negative matrix factorization with edge generator for link prediction in complex networks
    Yao, Yabing
    He, Yangyang
    Huang, Zhentian
    Xu, Zhipeng
    Yang, Fan
    Tang, Jianxin
    Gao, Kai
    APPLIED INTELLIGENCE, 2024, 54 (01) : 592 - 613
  • [43] Semi-supervised collective matrix factorization for topic detection and document clustering
    Wang, Ye
    Zhang, Yanchun
    Zhou, Bin
    Jia, Yan
    2017 IEEE SECOND INTERNATIONAL CONFERENCE ON DATA SCIENCE IN CYBERSPACE (DSC), 2017, : 88 - 97
  • [44] Collaborative QoS Prediction via Matrix Factorization and Topic Model
    Liang, Tingting
    Ji, Lichuan
    Chen, Liang
    Wu, Jian
    Wu, Zhaohui
    2013 IEEE SIXTH INTERNATIONAL CONFERENCE ON SERVICE-ORIENTED COMPUTING AND APPLICATIONS (SOCA), 2013, : 282 - 289
  • [45] Using Relational Topic Model and Factorization Machines to Recommend Web APIs for Mashup Creation
    Cao, Buqing
    Shi, Min
    Liu, Xiaoqing
    Liu, Jianxun
    Tang, Mingdong
    ADVANCES IN SERVICES COMPUTING, 2016, 10065 : 391 - 407
  • [46] Topic Modeling on Document Networks with Adjacent-Encoder
    Zhang, Ce
    Lauw, Hady W.
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 6737 - 6745
  • [47] Granular concept-enhanced relational graph convolution networks for link prediction in knowledge graph
    Dai, Yuhao
    Yan, Mengyu
    Li, Jinhai
    INFORMATION SCIENCES, 2025, 694
  • [48] Adversarial nonnegative matrix factorization for temporal link prediction
    Zhang, Ting
    Lv, Laishui
    Bardou, Dalal
    PHYSICS LETTERS A, 2024, 527
  • [49] Generalized Coupled Symmetric Tensor Factorization for Link Prediction
    Ermis, Beyza
    Cemgil, A. Taylan
    Acar, Evrim
    2013 21ST SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2013,
  • [50] A fusion probability matrix factorization framework for link prediction
    Wang, Zhiqiang
    Liang, Jiye
    Li, Ru
    KNOWLEDGE-BASED SYSTEMS, 2018, 159 : 72 - 85