Traffic prediction methods on a single-source data have achieved excellent results in recent years, especially the Graph Convolutional Networks (GCN) based models with spatio-temporal dependency. In reality, various modes of urban transportation operate simultaneously. They influence and complement each other in common space-time occasions, constituting the transportation system dynamically. Thus, traffic data from multiple sources is ostensibly heterogeneous, but internally correlated. The typical single data driven models are, however, not universally applicable for heterogeneous traffic data. To address this issue, we propose a Multi-task Hypergraph Convolutional Neural Network (MT-HGCN) for the multi-source traffic prediction problem. The framework consists of a main task and a related task. Both tasks are based on Hypergraph Convolutional Neural Networks (HGCN) and are devoted to two prediction problems. Furthermore, the tasks are bridged by a feature compress unit, which models the correlation and shares the latent feature to improve the performance of the main task. The node-level forecasting has been evaluated on historical datasets of Beijing to verify the effectiveness of the proposed method. Compared with the state-of-the-arts, the superior performance of the proposed method can be obtained.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multitask Hypergraph Convolutional Networks: A Heterogeneous Traffic Prediction Framework


    Beteiligte:
    Wang, Jingcheng (Autor:in) / Zhang, Yong (Autor:in) / Wang, Lixun (Autor:in) / Hu, Yongli (Autor:in) / Piao, Xinglin (Autor:in) / Yin, Baocai (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.10.2022


    Format / Umfang :

    3302613 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Dynamic Spatio-Temporal Residual Hypergraph Convolutional Networks for Traffic Flow Forecasting

    Su, Jun / Wang, Hairu / Przystupa, Krzysztof et al. | Transportation Research Record | 2025


    Traffic flow prediction method and device based on adaptive hypergraph convolutional neural network

    LIANG JUN / LOU SHUNJIE / WANG WENHAI | Europäisches Patentamt | 2023

    Freier Zugriff

    Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning

    Huang, Wenhao / Song, Guojie / Hong, Haikun et al. | IEEE | 2014


    Equivalent hypergraph construction method for traffic flow prediction

    WANG FENG / CAO YUHANG / ZHANG JIEYIN et al. | Europäisches Patentamt | 2025

    Freier Zugriff

    Traffic prediction method and system based on adaptive hypergraph

    ZHU CHAO / ZHU RUI / LI TONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff