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

<div>Input an hour data, the spatial attention matrix coefficients calculated by different GAT layers. (a) The first GAT calculation. (b) The second GAT calculation. (c) The penultimate GAT calculation. (d) The last GAT calculation.</div>

Computational Intelligence and Neuroscience

fig6

Figure 6

Figure 6: Multicomponent Spatial-Temporal Graph Attention Convolution Networks for Traffic Prediction with Spatially Sparse Data 