Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting

TL;DR

This paper introduces STFGNN, a novel graph neural network that fuses multiple spatial-temporal graphs to improve traffic flow forecasting by capturing hidden dependencies and handling long sequences effectively.

Contribution

The paper proposes a data-driven fusion operation for spatial-temporal graphs and integrates it with gated convolution to enhance traffic forecasting accuracy.

Findings

Achieves state-of-the-art performance on public traffic datasets.

Effectively models hidden spatial-temporal dependencies.

Handles long sequences better than existing methods.

Abstract

Spatial-temporal data forecasting of traffic flow is a challenging task because of complicated spatial dependencies and dynamical trends of temporal pattern between different roads. Existing frameworks typically utilize given spatial adjacency graph and sophisticated mechanisms for modeling spatial and temporal correlations. However, limited representations of given spatial graph structure with incomplete adjacent connections may restrict effective spatial-temporal dependencies learning of those models. To overcome those limitations, our paper proposes Spatial-Temporal Fusion Graph Neural Networks (STFGNN) for traffic flow forecasting. SFTGNN could effectively learn hidden spatial-temporal dependencies by a novel fusion operation of various spatial and temporal graphs, which is generated by a data-driven method. Meanwhile, by integrating this fusion graph module and a novel gated convolution module into a unified layer, SFTGNN could handle long sequences. Experimental results on several public traffic datasets demonstrate that our method achieves state-of-the-art performance consistently than other baselines.