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
  • [1] Robust representation learning for heterogeneous attributed networks
    Fu, Yue
    Yu, Xinyi
    Wu, Yongliang
    Ding, Xueyi
    Zhao, Shuliang
    INFORMATION SCIENCES, 2023, 628 : 22 - 49
  • [2] Collective Representation Learning on Spatiotemporal Heterogeneous Information Networks
    Chandra, Dakshak Keerthi
    Wang, Pengyang
    Leopold, Jennifer
    Fu, Yanjie
    27TH ACM SIGSPATIAL INTERNATIONAL CONFERENCE ON ADVANCES IN GEOGRAPHIC INFORMATION SYSTEMS (ACM SIGSPATIAL GIS 2019), 2019, : 319 - 328
  • [3] Representation Learning for Heterogeneous Information Networks via Embedding Events
    Fu, Guoji
    Yuan, Bo
    Duan, Qiqi
    Yao, Xin
    NEURAL INFORMATION PROCESSING (ICONIP 2019), PT I, 2019, 11953 : 327 - 339
  • [4] Representation Learning in Heterogeneous Information Networks Based on Hyper Adjacency Matrix
    Yang, Bin
    Wang, Yitong
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT I, 2022, : 747 - 755
  • [5] TransPath: Representation Learning for Heterogeneous Information Networks via Translation Mechanism
    Fang, Yang
    Zhao, Xiang
    Tan, Zhen
    Xiao, Weidong
    IEEE ACCESS, 2018, 6 : 20712 - 20721
  • [6] RL4HIN: Representation Learning for Heterogeneous Information Networks
    Liu, Chunfeng
    Liu, Ying
    Yu, Mei
    Yu, Ruiguo
    Li, Xuewei
    Zhao, Mankun
    Xu, Tianyi
    Liu, Hongwei
    Xu, Linying
    Yu, Jian
    2019 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2019,
  • [7] An effective representation learning model for link prediction in heterogeneous information networks
    Kumar, Vishnu
    Krishna, P. Radha
    COMPUTING, 2024, 106 (07) : 2185 - 2210
  • [8] Scalable Representation Learning for Dynamic Heterogeneous Information Networks via Metagraphs
    Fang, Yang
    Zhao, Xiang
    Huang, Peixin
    Xiao, Weidong
    de Rijke, Maarten
    ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2022, 40 (04)
  • [9] Sparse representation for heterogeneous information networks
    Zhai, Xuemeng
    Tang, Zhiwei
    Liu, Zhiwei
    Zhou, Wanlei
    Hu, Hangyu
    Fei, Gaolei
    Hu, Guangmin
    NEUROCOMPUTING, 2023, 525 : 111 - 122
  • [10] AGHINT: Attribute-guided representation learning on heterogeneous information networks with transformer
    Yuan, Jinhui
    Lu, Shan
    Duan, Peibo
    He, Jieyue
    KNOWLEDGE-BASED SYSTEMS, 2025, 310