DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction

被引:38
|
作者
Yuan, Chunyuan [1 ,2 ]
Li, Jiacheng [1 ,2 ]
Zhou, Wei [1 ]
Lu, Yijun [3 ]
Zhang, Xiaodan [1 ]
Hu, Songlin [1 ,2 ]
机构
[1] Chinese Acad Sci, Inst Informat Engn, Beijing, Peoples R China
[2] Univ Chinese Acad Sci, Sch Cyber Secur, Beijing, Peoples R China
[3] Alibaba Cloud Comp Co Ltd, Hangzhou, Peoples R China
来源
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2020, PT III | 2021年 / 12459卷
关键词
Data mining; Information diffusion prediction; Dynamic diffusion graph; Graph convolutional network;
D O I
10.1007/978-3-030-67664-3_21
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Information diffusion prediction is a fundamental task for understanding the information propagation process. It has wide applications in such as misinformation spreading prediction and malicious account detection. Previous works either concentrate on utilizing the context of a single diffusion sequence or using the social network among users for information diffusion prediction. However, the diffusion paths of different messages naturally constitute a dynamic diffusion graph. For one thing, previous works cannot jointly utilize both the social network and diffusion graph for prediction, which is insufficient to model the complexity of the diffusion process and results in unsatisfactory prediction performance. For another, they cannot learn users' dynamic preferences. Intuitively, users' preferences are changing as time goes on and users' personal preference determines whether the user will repost the information. Thus, it is beneficial to consider users' dynamic preferences in information diffusion prediction. In this paper, we propose a novel dynamic heterogeneous graph convolutional network (DyHGCN) to jointly learn the structural characteristics of the social graph and dynamic diffusion graph. Then, we encode the temporal information into the heterogeneous graph to learn the users' dynamic preferences. Finally, we apply multi-head attention to capture the context-dependency of the current diffusion path to facilitate the information diffusion prediction task. Experimental results show that DyHGCN significantly outperforms the state-of-the-art models on three public datasets, which shows the effectiveness of the proposed model.
引用
收藏
页码:347 / 363
页数:17
相关论文
共 50 条
  • [1] Interactive dynamic diffusion graph convolutional network for traffic flow prediction
    Zhang, Shuai
    Yu, Wangzhi
    Zhang, Wenyu
    INFORMATION SCIENCES, 2024, 677
  • [2] Dynamic Spatial-Temporal Heterogeneous Graph Convolutional Network for Traffic Prediction
    Jin, Hengqing
    Pu, Lipeng
    Lecture Notes in Electrical Engineering, 2024, 1253 LNEE : 60 - 68
  • [3] Drug-Target Prediction Based on Dynamic Heterogeneous Graph Convolutional Network
    Xu, Peng
    Wei, Zhitao
    Li, Chuchu
    Yuan, Jiaqi
    Liu, Zaiyi
    Liu, Wenbin
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2024, 28 (11) : 6997 - 7005
  • [4] RD-GCN: A Role-Based Dynamic Graph Convolutional Network for Information Diffusion Prediction
    Ye, Jingkai
    Bao, Qing
    Xu, Ming
    Xu, Jian
    Qiu, Hongjun
    Jiao, Pengfei
    IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, 2024, 11 (05): : 4923 - 4937
  • [5] A Dynamic Heterogeneous Graph Perception Network with Time-Based Mini-Batch for Information Diffusion Prediction
    Fan, Wei
    Liu, Meng
    Liu, Yong
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT I, 2022, : 604 - 612
  • [6] Multimodal dynamic graph convolutional network for crowdfunding success prediction
    Cai, Zihui
    Ding, Hongwei
    Xu, Mohan
    Cui, Xiaohui
    APPLIED SOFT COMPUTING, 2024, 154
  • [7] Dynamic Graph Convolutional Recurrent Network With Spatiotemporal Category Information Embedding for Traffic Flow Prediction
    Zhu, Guodong
    Niu, Yunyun
    Du, Songzhi
    Wang, Pengcheng
    IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (24): : 39473 - 39486
  • [8] Cascade-Enhanced Graph Convolutional Network for Information Diffusion Prediction
    Wang, Ding
    Wei, Lingwei
    Yuan, Chunyuan
    Bao, Yinan
    Zhou, Wei
    Zhu, Xian
    Hu, Songlin
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT I, 2022, : 615 - 631
  • [9] Dynamic meta-graph convolutional recurrent network for heterogeneous spatiotemporal graph forecasting
    Guo, Xianwei
    Yu, Zhiyong
    Huang, Fangwan
    Chen, Xing
    Yang, Dingqi
    Wang, Jiangtao
    NEURAL NETWORKS, 2025, 181
  • [10] A Dynamic Heterogeneous Graph Convolution Network For Traffic Flow Prediction
    Li, He
    Jin, Duo
    Li, XueJiao
    Qiao, Shaojie
    COMPUTER JOURNAL, 2024, 67 (01): : 31 - 44