TY  - EJOU
AU  - Zhao, Zitong 
AU  - Zhang, Zixuan 
AU  - Niu, Zhenxing 

TI  - Interactive Dynamic Graph Convolution with Temporal Attention for Traffic Flow Forecasting
T2  - Computers, Materials \& Continua

PY  - 2026
VL  - 86
IS  - 1
SN  - 1546-2226

AB  - Reliable traffic flow prediction is crucial for mitigating urban congestion. This paper proposes Attention-based spatiotemporal Interactive Dynamic Graph Convolutional Network (AIDGCN), a novel architecture integrating Interactive Dynamic Graph Convolution Network (IDGCN) with Temporal Multi-Head Trend-Aware Attention. Its core innovation lies in IDGCN, which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs, and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data. For 15- and 60-min forecasting on METR-LA, AIDGCN achieves MAEs of 0.75% and 0.39%, and RMSEs of 1.32% and 0.14%, respectively. In the 60-min long-term forecasting of the PEMS-BAY dataset, the AIDGCN out-performs the MRA-BGCN method by 6.28%, 4.93%, and 7.17% in terms of MAE, RMSE, and MAPE, respectively. Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.
KW  - Traffic flow prediction; interactive dynamic graph convolution; graph convolution; temporal multi-head trend-aware attention; self-attention mechanism

DO  - 10.32604/cmc.2025.069752