GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series

Abstract

Traffic forecasting is an integral part of intelligent transportation systems (ITS). Achieving a high prediction accuracy is a challenging task due to a high level of dynamics and complex spatial-temporal dependency of road networks. For this task, we propose Graph Attention-Convolution-Attention Networks (GACAN). The model uses a novel Att-Conv-Att (ACA) block which contains two graph attention layers and one spectralbased GCN layer sandwiched in between. The graph attention layers are meant to capture temporal features while the spectralbased GCN layer is meant to capture spatial features. The main novelty of the model is the integration of time series of four different time granularities: the original time series, together with hourly, daily, and weekly time series. Unlike previous work that used multi-granularity time series by handling every time series separately, GACAN combines the outcome of processing all time series after each graph attention layer. Thus, the effects of different time granularities are integrated throughout the model. We perform a series of experiments on three real-world datasets. The experimental results verify the advantage of using multigranularity time series and that the proposed GACAN model outperforms the state-of-the-art baselines.

Long-term traffic flow prediction based on multi-scale perceptual change

“…Local governments are also actively encouraging the development of intelligent transportation systems and striving to achieve the goal of establishing low-carbon, green and environmental protection. As a key component of intelligent transportation system, traffic flow prediction has attracted extensive research interest in academia and industry [2] .…”