A Decomposition Dynamic graph convolutional recurrent network for traffic forecasting

Our daily lives are greatly impacted by traffic conditions, making it essential to have accurate predictions of traffic flow within a road network. Traffic signals used for forecasting are usually generated by sensors along roads, which can be represented as nodes on a graph. These sensors typically produce normal signals representing normal traffic flows and abnormal signals indicating unknown traffic disruptions. Graph convolution networks are widely used for traffic prediction due to their ability to capture correlations between network nodes. However, existing approaches use a predefined or adaptive adjacency matrix that does not accurately reflect real-world relationships between signals. To address this issue, we propose a decomposition dynamic graph convolutional recurrent network (DDGCRN) for traffic forecasting. DDGCRN combines a dynamic graph convolution recurrent network with an RNN-based model that generates dynamic graphs based on time-varying traffic signals, allowing for the extraction of both spatial and temporal features. Additionally, DDGCRN separates abnormal signals from normal traffic signals and models them using a data-driven approach to further improve predictions. Results from our analysis of six real-world datasets demonstrate the superiority of DDGCRN compared to the current state-of-the-art. The source codes are available at: https://github.com/wengwenchao123/DDGCRN.

PDF

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Traffic Prediction PeMS04 DDGCRN 12 Steps MAE 18.45 # 5
Traffic Prediction PeMS07 DDGCRN MAE@1h 19.79 # 8
Traffic Prediction PeMS08 DDGCRN MAE@1h 14.40 # 9
Traffic Prediction PeMSD3 DDGCRN 12 steps MAE 14.63 # 2
12 steps RMSE 25.07 # 2
12 steps MAPE 14.22 # 2
Traffic Prediction PeMSD4 DDGCRN 12 steps MAE 18.45 # 6
Traffic Prediction PeMSD7 DDGCRN 12 steps MAE 19.79 # 5
Traffic Prediction PeMSD7(L) DDGCRN 12 steps MAE 2.79 # 2
12 steps RMSE 5.68 # 5
12 steps MAPE 7.06 # 4
Traffic Prediction PeMSD7(M) DDGCRN 12 steps MAE 2.59 # 2
12 steps RMSE 5.21 # 6
12 steps MAPE 6.48 # 6
Traffic Prediction PeMSD8 DDGCRN 12 steps MAE 14.40 # 6

Methods