traffic-flow-prediction

This paper introduces RiskTraf, a residual learning plug-in for multi-variate traffic flow prediction, and presents a new benchmark PEMSB-3V to enhance forecasting accuracy by extrapolating risk from speed and occupancy data.

This paper proposes the Structure-Guided Spatiotemporal Attention Graph Neural Network (SGSAN) to improve traffic flow prediction by explicitly modeling structural dependencies for better interpretability and state-of-the-art accuracy.