TEA-GCN: Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Forecasting

• 出版年: Sensors
• 主要な著者: Xiaxia He, Wenhui Zhang, Xiaoyu Li, Xiaodan Zhang
• フォーマット: 論文
• 言語: 英語
• 出版事項: MDPI AG 2024-11-01
• 主題: graph convolutional networks; traffic flow forecasting; adaptive graph learning
• オンライン･アクセス: https://www.mdpi.com/1424-8220/24/21/7086

Traffic flow forecasting is crucial for improving urban traffic management and reducing resource consumption. Accurate traffic conditions prediction requires capturing the complex spatial-temporal dependencies inherent in traffic data. Traditional spatial-temporal graph modeling methods often rely on fixed road network structures, failing to account for the dynamic spatial correlations that vary over time. To address this, we propose a Transformer-Enhanced Adaptive Graph Convolutional Network (TEA-GCN) that alternately learns temporal and spatial correlations in traffic data layer-by-layer. Specifically, we design an adaptive graph convolutional module to dynamically capture implicit road dependencies at different time levels and a local-global temporal attention module to simultaneously capture long-term and short-term temporal dependencies. Experimental results on two public traffic datasets demonstrate the effectiveness of the proposed model compared to other state-of-the-art traffic flow prediction methods.