Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting

By Mengzhang Li, Zhanxing Zhu. AAAI Conference on Artificial Intelligence, 2020

1,081 citations recorded by the source corpus.

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 usually 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. Furthermore, existing methods were out at elbows when solving complicated spatial-temporal data: they usually utilize separate modules for spatial and temporal correlations, or they only use independent components capturing localized or global heterogeneous dependencies. To overcome those limitations, our paper proposes a novel Spatial-Temporal Fusion Graph Neural Networks (STFGNN) for traffic flow forecasting. First, a data-driven method of generating “temporal graph” is proposed to compensate several genuine correlations that spatial graph may not reflect. STFGNN could effectively learn hidden spatial-temporal dependencies by a novel fusion operation of various spatial and temporal graphs, treated for different time periods in parallel. Meanwhile, by integrating this fusion graph module and a novel gated convolution module into a unified layer parallelly, STFGNN could handle long sequences by learning more spatial-temporal dependencies with layers stacked. Experimental results on several public traffic datasets demonstrate that our method achieves state-of-the-art performance consistently than other baselines.

Subfields: Building and Construction, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/24cff2aafcd66e1b7be4f647e478e8e73cf410a5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

In Environmental Engineering

Citations in the corpus

Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction (2022, methodology): “Nevertheless, the parameter space differentiation strategy adopted in (Song et al. 2020; Li and Zhu 2021) assumes that the temporal heterogeneity is static across the entire time periods, which is not always held, e.g., evening traffic patterns can be significantly different for workdays and…”
SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction (2021, methodology): “Most recent approaches: DCRNN [22], STGCN [41], ASTGCN [11], GraphWaveNet [39], STSGCN [35], AGCRN [3], LSGCN [15] and STFGNN [20] use graph neural networks to capture spatial relations while modeling temporal dependencies via conventional TCN or RNN/LSTM architectures.”
DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting (2022, methodology): “On the basis of (Song et al., 2020), STFGCN (Li & Zhu, 2021) constructed a spatial-temporal fusion graph for tra ffi c prediction, in which the static adjacent graph was supplemented by the information derived from historic sequences, similar to DTW (Berndt & Cli ff ord, 1994).”
PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction (2023, background): “…structure of traffic data (Li et al. 2018; Yu, Yin, and Zhu 2018), and thus GNN-based methods have been widely explored in traffic prediction (Wu et al. 2019; Song et al. 2020; Wu et al. 2020; Bai et al. 2020; Chen et al. 2020; Ye et al. 2021; Li and Zhu 2021; Fang et al. 2021; Choi et al. 2022).”
Graph Neural Controlled Differential Equations for Traffic Forecasting (2021, background): “…Cheng et al. 2018a,b; Hossain et al. 2015; Ren et al. 2021; Tekin et al. 2021; Li et al. 2018; Yu, Yin, and Zhu 2018; Wu et al. 2019; Guo et al. 2019; Bai et al. 2019; Song et al. 2020; Huang et al. 2020; Bai et al. 2020; Li and Zhu 2021; Chen, Segovia-Dominguez, and Gel 2021; Fang et al. 2021).”
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection (2023, background): “There are also several variants for creating similarity-based graphs, such as Pearson correlation coefﬁcient (PCC) [43] and dynamic time warping (DTW) [44].”
Graph Neural Networks for Intelligent Transportation Systems: A Survey (2023, methodology): “This dataset is collected in North Central Area in California and the subset has been used in [216], [217], and [218].”
Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey (2023, background): “For example, STFGNN [52] proposes to construct the spatio-temporal synchronous graph using not only topology-based but also similarity-based graphs, thereby making the spatio-temporal synchronous graph more informative.”