Spatio-temporal forecasting, a prominent research focus for understanding the dynamics of data flow in various domains, has recently extended its significance to traffic prediction as a notable application. Considering topology of data flow, existing methods mainly utilize Graph Convolutional Networks (GCNs), where graph construction is the basic concern and generally determines how data features are propagated. However, through extensive investigations and theoretical evidence, it is revealed that graph construction strategy, which is usually regarded as the key step to success, has actually provided very little benefit, while the presence of feature propagation itself on spatiotemporal domain is more significant, i.e., feature propagation carry more weights than how they do. Thus, by making slight refinements of a feature normalization method, we propose a Spatio-Temporal Propagation (STP) module, which does not require intervention of a specific graph structure, yet simple and effective. Various experiments on public datasets verify that the proposed STP module is an on-the-shelf tool that can be accessed to the end of current models or even replace GCNs as an alternative for capturing spatiotemporal features, while achieving better predictions. All the source codes are open accessed on GitHub.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Revisiting Spatio-Temporal Forecasting: Feature Propagation Carry More Weights Than How They Do


    Contributors:
    Fang, Shen (author) / Liu, Hongyan (author) / Yu, Chengcheng (author) / Xie, Tian (author) / Hua, Wei (author)


    Publication date :

    2024-09-24


    Size :

    717937 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    MLP for Spatio-Temporal Traffic Volume Forecasting

    Dimara, Asimina / Triantafyllidis, Dimitrios / Krinidis, Stelios et al. | IEEE | 2021


    Auxiliary tool for forklift to carry balancing weights

    SUN NENGKE / ZHOU JUNKE / JIANG JIWEI et al. | European Patent Office | 2024

    Free access


    STGT: FORECASTING PEDESTRIAN MOTION USING SPATIO-TEMPORAL GRAPH TRANSFORMER

    Syed, Arsal / Morris, Brendan | British Library Conference Proceedings | 2021