Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction

Xuanmian He; Can Li; Wanjing Ma

cs.LGAug 14, 2026

Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction

Authors: Xuanmian He, Can Li, Wanjing Ma

Organizations: Department of Civil and Environmental Engineering, University of California, Berkeley, United States · Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 201804, China

Abstract

Deep spatiotemporal models integrating graph convolutions and attention mechanisms have demonstrated excellent performance in network-level traffic flow prediction, owing to their exceptional ability to capture complex spatiotemporal dependencies. Despite their predictive success, deployment of such models in safety-critical urban systems remains constrained by their inherent lack of transparency. Existing post-hoc diagnostic methods often struggle with spurious correlations and fail to unveil the intrinsic decision-making mechanisms governing traffic dynamics, resulting in suboptimal interpretability and limited operational trustworthiness. To address these challenges, this paper proposes the Structure-Guided Spatiotemporal Attention Graph Neural Network (SGSAN). Departing from traditional architectures that rely on unconstrained adaptive graphs, SGSAN explicitly learns a static Directed Dependency Graph (DDG) to identify the invariant macroscopic propagation paths of traffic states. We further introduce an InfoNCE-based soft-coupling mechanism that anchors the model's dynamic spatiotemporal attention to this structural prior, offering a mechanistic account of the model's decision-making process while ensuring robust forecasting by aligning attention-based reasoning with identified macroscopic dependencies and preventing over-reliance on ephemeral local noise. Furthermore, a decoupled two-stage optimization framework is developed to resolve the fundamental conflict between structural discovery and predictive error minimization. Extensive experiments on multiple real-world datasets demonstrate that SGSAN achieves state-of-the-art predictive accuracy while providing built-in interpretability that organically aligns with the physical logic of traffic networks.

Figures & tables

Notation	Definition
$V$	Number of detector nodes in the network
$T$	Length of the historical input sequence
$H$	Length of the prediction horizon
$d$	Dimension of the hidden representation layers
$N$	Number of samples in a training batch
$\mathbf{X}_{t}$	Traffic states of all nodes at time step $t$

TABLE I: Summary of Key Notations

Fig. 1: Framework of Structure-Guided Spatiotemporal Attention Graph Neural Network (SGSAN)

Dataset	PeMS03	PeMS07	PeMS08	PeMS-Bay
Timesteps	26,208	28,224	17,856	52,116
Number of nodes	358	883	170	325
Number of edges	549	865	276	2,369
Predicted state	Volume	Volume	Volume	Mean Speed

TABLE II: Descriptive Analysis of Datasets

Dataset	Model	Horizon=15min			Horizon=30min			Horizon=60min			Average
Dataset	Model	MAE	MAPE	RMSE	MAE	MAPE	RMSE	MAE	MAPE	RMSE	MAE	MAPE	RMSE
PeMS03	T-GCN	20.18	19.13	27.82	29.02	26.65	43.36	36.42	33.86	53.03	28.54	26.55	41.40
	STGCN	17.05	14.41	26.76	26.96	25.99	39.58	31.72	29.73	46.78	25.24	23.38	37.71
	GMAN	14.87	13.37	23.15	23.65	20.35	36.70	32.00	28.79	47.63	23.51	20.83	35.83
	ASTGCN	14.40	12.26	25.17	23.98	20.68	37.71	24.07	20.25	37.65	20.81	17.73	33.51
	STTN	16.43	17.38	24.20	22.40	19.12	34.14	27.38	31.77	42.68	22.07	22.75	33.67

TABLE III: Performance Comparison: Prediction Accuracy

Dataset	Model	Horizon=15min			Horizon=30min			Horizon=60min
Dataset	Model	MAE	MAPE	RMSE	MAE	MAPE	RMSE	MAE	MAPE	RMSE
PeMS03	STA-GNN	17.70	14.42	28.88	21.30	17.02	34.54	28.36	23.07	44.46
	SGSAN (DAG-Relaxed)	16.30	18.36	30.40	20.74	22.95	33.52	24.15	22.71	37.60
	SGSAN (Random-DDG)	16.45	17.76	26.30	23.28	26.86	33.10	25.47	26.42	39.07
	SGSAN (Joint)	14.05	11.20	22.95	25.59	23.59	38.60	31.72	32.36	44.87
	SGSAN (Ours) - KL	15.80	13.35	24.85	20.23	16.12	32.02	24.26	20.90	37.08

TABLE IV: Prediction Results in the Ablation Studies

Model	PeMS03	PeMS07	PeMS08	PeMS-Bay
SGSAN (Joint)	11.35s	52.21s	4.63s	21.20s
SGSAN (Ours)	8.35s	31.73s	3.25s	14.57s
Reduction	-26.4%	-39.2%	-29.8%	-31.3%

TABLE V: Average Training Time Per Epoch

Model	Avg Time per Sample (ms)
T-GCN	0.044 $\pm$ 0.003
ASTGCN	0.078 $\pm$ 0.001
CCHMM	0.079 $\pm$ 0.004
SGSAN (Ours)	0.096 $\pm$ 0.003
DCST	0.125 $\pm$ 0.001
STCGCN	0.136 $\pm$ 0.002

TABLE VI: Inference Efficiency Comparison

Fig. 2: Sensitivity Analysis of Interpretability Metrics (ASC, SPC, and APC) across varying sparsity levels (Top- $K\%$ )

Panel of Figure 9 — Fig. 3: Example Nodes in the Subgraphs illustrating consistency between the DDG and the Attention Map.

Traffic Flow Estimation

Traffic flow estimation infers and predicts vehicle volumes, speeds, densities, and origin–destination demand from incomplete transportation data.

See all 51 papers

Jul 27, 2026

Eliminating Propagation Delay: Attention-Based Spatial-Temporal Fusion Graph Convolution Network for Traffic Flow Prediction

Predicting traffic flow is crucial to optimizing transportation systems and improving urban mobility. Many graph convolution-based models have been proposed to extract spatial-temporal features and predict traffic flow. However, most focus on spatial-temporal and semantic correlation in topological relationships. There are two primary problems to address. Firstly, the convolutional structure in the model focuses on utilizing static spatial dependencies and spatial-temporal relationships in topological structures, while neglecting the different information propagation delays between adjacent nodes in the convolution. Secondly, these methods often stack a large number of complex structures, resulting in a substantial increase in computational time during the model training phase, thereby disregarding the model's requirements for timeliness. In this paper, we propose a novel network called the Attention-Based Spatial-Temporal Fusion Graph Convolution Network (A-STFGCN). We design a spatial-temporal fusion block to extract the spatial-temporal feature correlations with propagation delay errors removed and to capture both long-term and short-term temporal characteristics of the data within a multi-head self-attention mechanism based on a mask matrix. Extensive experiments on five real-world datasets demonstrate that our method achieves the best overall performance while having good computation and data utilization efficiency compared with the eight baseline methods.

Jinpeng Chen, Ziyu Yu, Tao Wang +5

School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, China · Key Laboratory of Trustworthy Distributed Computing and Service (Beijing University of Posts and Telecommunications), Ministry of Education, Beijing, China · Department of Automation, School of Information Science and Technology, University of Science and Technology of China, Hefei, China +3

Intelligent Transportation Systems Traffic Flow Estimation Spatiotemporal GNNs

Ask PDF

May 16, 2026

A Global-Local Graph Attention Network for Traffic Forecasting

Traffic forecasting is a significant part of intelligent transportation systems. One of the critical challenges of traffic forecasting is to find spatio-temporal correlations. In recent years, graph convolutional networks and graph attention networks have replaced traditional statistical models to predict future traffic. However, it is complicated for both of them to allow vertices to have far different characters. To address this, we propose the Global-Local Graph Attention Network (GLGAT) with pairwise encoding and the event-based adjacency matrix. The GLGAT allows vertices to have a global attention matrix set for the whole graph and assigns local attention matrix sets to each vertex. Experiments on two real-world traffic datasets show that GLGAT can effectively capture spatio-temporal correlations and has competitive performance against other state-of-the-art baselines.

Tianchi Zhang

Intelligent Transportation Systems Spatiotemporal Forecasting Traffic Forecasting Spatiotemporal GNNs

Ask PDF

Apr 18, 2026

GAMMA-Net: Adaptive Long-Horizon Traffic Spatio-Temporal Forecasting Model based on Interleaved Graph Attention and Multi-Axis Mamba

Accurate traffic forecasting is crucial for intelligent transportation systems, supporting effective traffic management, congestion reduction, and informed urban planning. However, traditional models often fail to adequately capture the intricate spatio-temporal dependencies present in traffic data. To overcome these limitations, we introduce GAMMA-Net, a novel approach that integrates Graph Attention Networks (GAT) with multi-axis Selective State Space Models (Mamba). The GAT component uses a self-attention mechanism to dynamically adjust the influence of nodes within the traffic network, enabling adaptive spatial dependency modeling based on real-time conditions. Simultaneously, the Mamba module efficiently models long-term temporal and spatial dynamics without the heavy computational cost of conventional recurrent architectures. Extensive experiments on several benchmark traffic datasets, including METR-LA, PEMS-BAY, PEMS03, PEMS04, PEMS07, and PEMS08, show that GAMMA-Net consistently outperforms existing state-of-the-art models across different prediction horizons, achieving up to a 16.25% reduction in Mean Absolute Error (MAE) compared to baseline models. Ablation studies highlight the critical contributions of both the spatial and temporal components, emphasizing their complementary role in improving prediction accuracy. In conclusion, the GAMMA-Net model sets a new standard in traffic forecasting, offering a powerful tool for next-generation traffic management and urban planning. The code for this study is available at https://github.com/hdy6438/GAMMA-Net

Dongyi He, Yuanquan Gao, Bin Jiang +1

School of Artificial Intelligence, Chongqing University of Technology, Chongqing, 400054, China

Long-Term Time Series Forecasting Intelligent Transportation Systems Traffic Forecasting Spatiotemporal GNNs

Ask PDF

Abstract

Traffic Flow Estimation

Explore similar work

Eliminating Propagation Delay: Attention-Based Spatial-Temporal Fusion Graph Convolution Network for Traffic Flow Prediction

A Global-Local Graph Attention Network for Traffic Forecasting

GAMMA-Net: Adaptive Long-Horizon Traffic Spatio-Temporal Forecasting Model based on Interleaved Graph Attention and Multi-Axis Mamba