MoE Enhanced Federated Learning for Spatiotemporal Prediction

2026-06-09

AI Summary

This work addresses the challenges of cross-city traffic forecasting—namely data scarcity, strong spatiotemporal heterogeneity, and privacy constraints—by proposing MoE-FedTP, a novel framework that introduces the Mixture-of-Experts (MoE) architecture into federated spatiotemporal prediction for the first time. Integrating lightweight spatiotemporal neural networks with a dynamic gating mechanism, MoE-FedTP enables partial parameter sharing under the federated learning paradigm, effectively capturing inter-city heterogeneity while personalizing the fusion of multi-city expert knowledge. Experimental results on four real-world traffic datasets demonstrate that MoE-FedTP significantly outperforms existing cross-city and federated learning approaches, particularly enhancing prediction accuracy in data-scarce cities.

Abstract

Traffic prediction is fundamental to intelligent transportation systems and urban computing, yet many cities continue to suffer from traffic data scarcity due to limited sensor deployment and uneven urban development. Cross-city knowledge transfer has thus attracted increasing attention, enabling data-rich cities to assist data-scarce ones. However, centralized approaches raise privacy concerns, while existing federated methods struggle with pronounced spatiotemporal heterogeneity across cities. To address these challenges, we propose MoE-FedTP, a personalized federated cross-city spatiotemporal prediction framework based on lightweight Mixture-of-Experts (MoE) networks. MoE-FedTP first employs spatiotemporal neural networks to extract features from both source and target cities, then introduces a set of expert networks derived from different source cities through partial parameter sharing. A gating mechanism dynamically fuses the experts to capture diverse traffic dynamics, achieving fine-grained modeling of urban heterogeneity while preserving privacy. Experiments on four real-world traffic datasets show that MoE-FedTP consistently outperforms state-of-the-art cross-city and federated learning baselines, demonstrating its effectiveness in enhancing prediction accuracy for data-scarce cities.

Problem

• federated learning
• spatiotemporal prediction
• cross-city transfer
• traffic data scarcity
• urban heterogeneity

Innovation

• Mixture-of-Experts
• Federated Learning
• Spatiotemporal Prediction
• Cross-city Transfer
• Privacy Preservation