MoE Enhanced Federated Learning for Spatiotemporal Prediction
Researchers have developed MoE-FedTP, a new framework for spatiotemporal prediction that uses a Mixture-of-Experts (MoE) approach within a federated learning system. This method aims to improve traffic prediction accuracy, especially in cities with limited data, by enabling knowledge transfer from data-rich cities without compromising privacy. Experiments show MoE-FedTP outperforms existing cross-city and federated learning techniques. AI
IMPACT This framework could improve traffic management and urban planning in data-scarce regions by enabling more accurate predictions.