Huang, E ORCID: https://orcid.org/0009-0008-2646-5128, Zhao, Zhanshan Z ORCID: https://orcid.org/0000-0002-2177-3980, Yin, Jiao ORCID: https://orcid.org/0000-0002-0269-2624, Cao, J ORCID: https://orcid.org/0000-0002-0221-6361 and Wang, Hua H ORCID: https://orcid.org/0000-0002-8465-0996 (2026) Transformer-Enhanced Adaptive Graph Convolutional Network for Traffic Flow Prediction. ACM Transactions on Intelligent Systems and Technology, 17 (3). pp. 1-24. ISSN 2157-6904

Abstract

Traffic flow prediction is vital in urban traffic management, planning, and development. With the continuous advancement of urbanization, there is an increasing demand for traffic flow prediction models to achieve higher accuracy and long-range forecasting capabilities. Against this backdrop, traditional methods that rely on local feature extraction and static spatial graph construction often fall short of expectations. This highlights the urgent need for advanced approaches to dynamically model spatio-temporal features while capturing global dependencies, effectively meeting the demands of complex traffic flow prediction tasks. To achieve this, we propose the Transformer-Enhanced Adaptive Graph Convolutional Network (T-AGCN), a novel model designed to capture global temporal relationships and dynamically extract rich spatial information. T-AGCN incorporates an Adaptive Graph Learner module to model dynamic relationships among traffic nodes and a Transformer-Based Spatio-Temporal graph convolutional module to capture long-range temporal dependencies in historical traffic data effectively. These innovations enable T-AGCN to jointly learn dynamic spatial interactions and complex temporal patterns, offering a comprehensive representation of traffic network dynamics. We evaluate T-AGCN on three real-world datasets, PeMSD7(M), PeMS08, and METR-LA. The experimental results demonstrate that T-AGCN, inspired by the baseline model Spatial-Temporal Graph Convolutional Network (STGCN), significantly enhances its design. Moreover, T-AGCN consistently outperforms state-of-the-art models, including the Transformer-Based Interactive Temporal and Adaptive Network (TITAN) and the Spatial-Temporal Decoupled Masked Autoencoder (STD-MAE). The implementation is available on GitHub at https://github.com/time1722/T-AGCN.

Search Google Scholar

Repository staff login