Multicomponent Spatial-Temporal Graph Attention Convolution Networks for Traffic Prediction with Spatially Sparse Data

<div>The performance of various existing methods. (a) Performance on sparse PeMS-BAY with different node amounts. (b) Performance of different methods in different forecasting duration.</div>

Computational Intelligence and Neuroscience

fig5

Figure 5

Figure 5: Multicomponent Spatial-Temporal Graph Attention Convolution Networks for Traffic Prediction with Spatially Sparse Data 