Robust and fast representation learning for heterogeneous information networks

被引:1
|
作者
Lei, Yong [1 ,2 ]
Chen, Lei [3 ]
Li, Yuan [3 ]
Xiao, Ruifeng [4 ]
Liu, Zhaohua [3 ]
机构
[1] Hunan Univ Sci & Technol, Sch Comp Sci & Engn, Xiangtan, Peoples R China
[2] Hunan Key Lab Serv Comp & Novel Software Technol, Xiangtan, Peoples R China
[3] Hunan Univ Sci & Technol, Sch Informat & Elect Engn, Xiangtan, Peoples R China
[4] Hunan Tech Coll Railway Highspeed, Sch Comp Sci & Railway Engn, Hengyang, Peoples R China
基金
中国国家自然科学基金;
关键词
heterogeneous information network (HIN); robust representation learning; adversarial learning; intra-type feature; inter-type feature;
D O I
10.3389/fphy.2023.1196294
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Network representation learning is an important tool that can be used to optimize the speed and performance of downstream analysis tasks by extracting latent features of heterogeneous networks. However, in the face of new challenges of increasing network size, diverse latent features, and unseen network noise, existing representation models need to be further optimized. In this paper, a robust and fast representation learning model is proposed for heterogeneous networks, called RFRL. First, the global features of a heterogeneous network are divided into multiple intra-type local features and inter-type local features, and a type-aware biased sampling is designed to generate training samples for each local feature. Second, a node-type-aware and a link-type-aware shallow representation strategy are used to learn intra-type features and inter-type features respectively. This enables the model to achieve good performance while having high speed through the divide-and-conquer learning process and shallow learning model, thus coping with increasing network size and latent feature diversity. Finally, adversarial learning is used to integrate the above two representation strategies to address unseen network noise and enhance the robustness of representation learning. Extensive experiments on three network analysis tasks and three public datasets demonstrate the good performance of our RFRL model.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] Robust and Fast Measure of Information via Low-Rank Representation
    Dong, Yuxin
    Gong, Tieliang
    Yu, Shujian
    Chen, Hong
    Li, Chen
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 6, 2023, : 7450 - 7458
  • [32] A FAST AND ROBUST LEARNING ALGORITHM FOR FEEDFORWARD NEURAL NETWORKS
    WEYMAERE, N
    MARTENS, JP
    NEURAL NETWORKS, 1991, 4 (03) : 361 - 369
  • [33] HybridGNN: Learning Hybrid Representation for Recommendation in Multiplex Heterogeneous Networks
    Gu, Tiankai
    Wang, Chaokun
    Wu, Cheng
    Lou, Yunkai
    Xu, Jingcao
    Wang, Changping
    Xu, Kai
    Ye, Can
    Song, Yang
    2022 IEEE 38TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2022), 2022, : 1355 - 1367
  • [34] Representation Learning for Classification in Heterogeneous Graphs with Application to Social Networks
    Dos Santos, Ludovic
    Piwowarski, Benjamin
    Denoyer, Ludovic
    Gallinari, Patrick
    ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2018, 12 (05)
  • [35] SHNE: Representation Learning for Semantic-Associated Heterogeneous Networks
    Zhang, Chuxu
    Swami, Ananthram
    Chawla, Nitesh, V
    PROCEEDINGS OF THE TWELFTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING (WSDM'19), 2019, : 690 - 698
  • [36] DHNE: Network Representation Learning Method for Dynamic Heterogeneous Networks
    Yin, Ying
    Ji, Li-Xin
    Zhang, Jian-Peng
    Pei, Yu-Long
    IEEE ACCESS, 2019, 7 : 134782 - 134792
  • [37] MBRep: Motif-based representation learning in heterogeneous networks
    Hu, Qian
    Lin, Fan
    Wang, Beizhan
    Li, Chunyan
    EXPERT SYSTEMS WITH APPLICATIONS, 2022, 190
  • [38] Quintuple-based Representation Learning for Bipartite Heterogeneous Networks
    Zhou, Cangqi
    Chen, Hui
    Zhang, Jing
    Li, Qianmu
    Hu, Dianming
    ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2024, 15 (03)
  • [39] AngHNE: Representation Learning for Bipartite Heterogeneous Networks with Angular Loss
    Zhou, Cangqi
    Chen, Hui
    Zhang, Jing
    Li, Qianmu
    Hu, Dianming
    WSDM'22: PROCEEDINGS OF THE FIFTEENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2022, : 1470 - 1478
  • [40] Online User Representation Learning Across Heterogeneous Social Networks
    Wang, Weiqing
    Yin, Hongzhi
    Du, Xingzhong
    Hua, Wen
    Li, Yongjun
    Quoc Viet Hung Nguyen
    PROCEEDINGS OF THE 42ND INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '19), 2019, : 545 - 554