Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting
By Shengna Guo, Youfang Lin, Ning Feng, Chao Song, Huaiyu Wan. AAAI Conference on Artificial Intelligence, 2019
3,235 citations recorded by the source corpus.
Forecasting the traffic flows is a critical issue for researchers and practitioners in the field of transportation. However, it is very challenging since the traffic flows usually show high nonlinearities and complex patterns. Most existing traffic flow prediction methods, lacking abilities of modeling the dynamic spatial-temporal correlations of traffic data, thus cannot yield satisfactory prediction results. In this paper, we propose a novel attention based spatial-temporal graph convolutional network (ASTGCN) model to solve traffic flow forecasting problem. ASTGCN mainly consists of three independent components to respectively model three temporal properties of traffic flows, i.e., recent, daily-periodic and weekly-periodic dependencies. More specifically, each component contains two major parts: 1) the spatial-temporal attention mechanism to effectively capture the dynamic spatialtemporal correlations in traffic data; 2) the spatial-temporal convolution which simultaneously employs graph convolutions to capture the spatial patterns and common standard convolutions to describe the temporal features. The output of the three components are weighted fused to generate the final prediction results. Experiments on two real-world datasets from the Caltrans Performance Measurement System (PeMS) demonstrate that the proposed ASTGCN model outperforms the state-of-the-art baselines.
Subfields: Building and Construction, Civil and Structural Engineering, Transportation
View Paper: https://www.semanticscholar.org/paper/36cf500079b82e3adf4a3afe3356c1c03426bdcd
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
- Zezhi Shao
- Fei Wang
- Zhao Zhang
- Yongjun Xu
- Nizar Bouguila
- Saeed Rahmani
- Asiye Baghbani
- Zachary Patterson
In Civil and Structural Engineering
In Transportation
Citations in the corpus
- Spatio-Temporal Meta-Graph Learning for Traffic Forecasting (2022, neutral): “Although the heterogeneity issue can be alleviated to some extent by applying attentions over the space and time (Guo et al. 2019; Zheng et al. 2020), sensor signals of different natures are still left entangled, not to mention that incidents are simply untreated.”
- Graph Neural Controlled Differential Equations for Traffic Forecasting (2021, methodology): “…et al. 2018; 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…”
- Traffic transformer: Capturing the continuity and periodicity of time series for traffic forecasting (2020, background): “This is an important shortcoming as time series usually convey periodic patterns, such as hourly, daily, weekly, and seasonally (Guo, Lin, Feng, Song, & Wan, 2019; Yao et al., 2019).”
- Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting (2021, methodology): “ASTGCN in our preliminary work is the only baseline in which the parameters capturing the dynamics in traffic data are dependent on the input data while the parameters in all the other baseline methods are invariant to the input after being learned.”
- A Comprehensive Survey on Graph Neural Networks (2019, background): “ASTGCN [77] further includes a spatial attention function and a temporal attention function to learn latent dynamic spatial dependencies and temporal dependencies through a CNN-based approach.”
- Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution (2021, methodology): “CNN [1]–[4], GNN [5]–[8], [12]–[23] and attention mechanism [7]–[11], [17], [19], [23], [25] have been widely used to capture spatial dependency.”
- Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting (2022, methodology): “Moreover, attention mechanism is widely used in many methods, such as GMAN [41] and ASTGCN [11].”
- A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection (2023, background): “For example, AST-GCN [86] and DSTAGNN [88] concurrently employ temporal attention and convolution in learning temporal correlations.”
- Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting (2022, neutral): “Specifically, PEMS08 contains data of 170 sensors in the District08 over a period of 2 months from July 1st 2018 to Aug 31th 2018 [11].”
- Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting (2020, background): “Only recent components of modeling periodicity is taken to keep fair comparison(Guo et al. 2019).”
- Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey (2023, background): “Overview of ASTGCN [172]. jointly utilizes TCNs and Transformers for long-short range temporal learning.”
- PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction (2023, background): “Recently, the attention mechanism has become increasingly popular due to its effectiveness in modeling the dynamic dependencies in traffic data (Guo et al. 2019; Wang et al. 2020; Lin et al. 2020b; Yan and Ma 2021; Ye et al. 2022).”
- Spatial-Temporal Transformer Networks for Traffic Flow Forecasting (2020, methodology): “Most recently, [19] also proposed to generate dynamical spatial dependencies but their spatial dependencies are not evolving time but the depth of spatial and temporal blocks.”