MoE-FedTP applies lightweight MoE networks within a personalized federated setup to improve cross-city spatiotemporal traffic prediction by dynamically fusing experts from source cities.
arXiv preprint arXiv:2411.09251 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MoE Enhanced Federated Learning for Spatiotemporal Prediction
MoE-FedTP applies lightweight MoE networks within a personalized federated setup to improve cross-city spatiotemporal traffic prediction by dynamically fusing experts from source cities.