Traffic flow forecasting is challenging due to the intricate spatio-temporal correlations in traffic patterns. Previous works captured spatial dependencies based on graph neural networks and used fixed graph construction methods to characterize spatial relationships, which limits the ability of models to capture dynamic and long-range spatial dependencies. Meanwhile, prior studies did not consider the issue of a large number of redundant parameters in traffic prediction models, which not only increases the storage cost of the model but also reduces its generalization ability. To address the above challenges, we propose a Dynamic Spatial Transformer for Traffic Forecasting with Low-Rank Tensor Compression (DSFormer-LRTC). Specifically, we constructed a global spatial Transformer to capture remote spatial dependencies, and a distance-based mask matrix is used in local spatial Transformer to enhance the adjacent spatial influence. To reduce the complexity of the model, the model adopts a design that separates temporal and spatial. Meanwhile, we introduce low-rank tensor decomposition to reconstruct the parameter matrix in Transformer module to compress the proposed model. Experimental results show that DSFormer-LRTC achieves state-of-the-art performance on four real-world datasets. The experimental analysis of attention matrix also proves that the model can learn dynamic and distant spatial features. Finally, the compressed model parameters reduce the original parameter size by two-thirds, while significantly outperforming the baseline model in terms of computational efficiency.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    DSFormer-LRTC: Dynamic Spatial Transformer for Traffic Forecasting With Low-Rank Tensor Compression


    Beteiligte:
    Zhao, Jianli (Autor:in) / Zhuo, Futong (Autor:in) / Sun, Qiuxia (Autor:in) / Li, Qing (Autor:in) / Hua, Yiran (Autor:in) / Zhao, Jianye (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.11.2024


    Format / Umfang :

    2783473 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Traffic forecasting with missing data via low rank dynamic mode decomposition of tensor

    Xinyu Zhang / Yong Zhang / Xiulan Wei et al. | DOAJ | 2022

    Freier Zugriff

    Traffic forecasting with missing data via low rank dynamic mode decomposition of tensor

    Zhang, Xinyu / Zhang, Yong / Wei, Xiulan et al. | Wiley | 2022

    Freier Zugriff

    Research on Traffic Flow Forecasting Based on Dynamic Spatial-Temporal Transformer

    Zhang, Hong / Wang, Hongyan / Zhang, Xijun et al. | Transportation Research Record | 2023


    Spatial-Temporal Graph-Based Transformer Model for Traffic Flow Forecasting

    Wang, Qichao / He, Guojun / Lu, Peiyu et al. | IEEE | 2022