Jing Gan

Cold-Start Traffic State Forecasting at Unseen Sensor Locations via Support-Conditioned Meta-Graph Learning

Support-conditioned sensor-adaptive meta-graph learning (SC-SAMG) is proposed, which derives target-node representations and spatial dependencies from a short support period and consistently outperforms fine-tuned gated recurrent unit (GRU), adaptive graph convolutional recurrent network (AGCRN), and diffusion convolut...