Self-Attention Graph Convolution Residual Network for Traffic Data Completion

• Published in: IEEE transactions on big data Vol. 9; no. 2; pp. 528 - 541
• Main Authors: Zhang, Yong, Wei, Xiulan, Zhang, Xinyu, Hu, Yongli, Yin, Baocai
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.04.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Communications traffic; Convolution; Correlation; Data models; Feature extraction; Graph convolution; Graph neural networks; Machine learning; Mathematical analysis; Roads; self-attention mechanism; Structured data; Task analysis; Tensors; Topology; traffic data completion; Traffic management; Traffic models; Traffic planning
• ISSN: 2332-7790; 2332-7790; 2372-2096
• DOI: 10.1109/TBDATA.2022.3181068

Complete and accurate traffic data is critical in urban traffic management, planning and operation. In fact, real-world traffic data contains missing values due to multiple factors, such as device outages and communication errors. For traffic data completion task, most of the existing methods are matrix/tensor completion methods, which usually enforce low rank constraint on traffic data matrix/tensor. But they neglect the graph structure of traffic data, resulting in low completion performance. Recently, graph convolutional networks have achieved remarkable results in traffic data forecasting due to their abilities of feature extraction and nonlinear fitting on arbitrarily graph-structured data. However, there are few studies based on graph neural networks for traffic data completion task. In this paper, we propose a traffic data completion model based on graph convolutional network model to impute missing values from the perspective of deep learning. This model utilizes graph convolution to model the local spatial dependency. As for global spatial dependency and temporal dependency, this model incorporates self-attention mechanism, which is applied in the spatial and temporal dimensions respectively. The experimental results on the two real-time datasets demonstrate that the proposed model outperforms the baseline methods significantly under arbitrarily missing scenarios.