Implementation of the paper "SCANNER+: Neighborhood-based self-enrichment approach for traffic speed prediction"
Abstract
In this repository, you can find the code to train and evaluate SCANNER+, a novel neighborhood-based self-enrichment approach for traffic speed prediction. SCANNER+ learns effective node representations in dynamic road traffic settings. This work extends SCANNER, which utilizes correlation-based pattern detection and a self-enrichment mechanism.
Publication details
- Journal / source
- bonndata
- Publication date
- 6 January 2026
- Document type
- Dataset