<ul><li>Spatio-temporal traffic prediction is important in intelligent transportation systems.</li><li>Traditional Graph Convolutional Networks (GCNs) face challenges with static adjacency matrices and learnable matrices.</li><li>The study introduces a novel Multi-Task Learning (MTL) framework called DG-STMTL.</li><li>DG-STMTL combines static and dynamic adjacency matrices and includes a group-wise GCN module.</li></ul>

DG-STMTL: A Novel Graph Convolutional Network for Multi-Task Spatio-Temporal Traffic Forecasting

Discover more