FedeRICo: Federated Region-Influenced Coupling for Traffic Flow Prediction
FedeRICo, a federated traffic forecasting framework that combines gradient-level collaboration with boundary-aware residual communication, is proposed that consistently outperforms state-of-the-art federated spatial-temporal baselines while maintaining competitive training runtime.
Fermin Orozco, Man Luo, Johan Wahlström
· 0 citations