Search Results for author:
Found 3 papers, 1 papers with code
Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach
From spatial perspective, we design lightweight-but-efficient prototypes as client-level semantic representations, based on which the server evaluates spatial similarity and yields client-customized global prototypes for the supplemented inter-client contrastive task.
Online Spatio-Temporal Correlation-Based Federated Learning for Traffic Flow Forecasting
In this paper, we perform the first study of forecasting traffic flow adopting Online Learning (OL) manner in FL framework and then propose a novel prediction method named Online Spatio-Temporal Correlation-based Federated Learning (FedOSTC), aiming to guarantee performance gains regardless of traffic fluctuation.
Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation
Federated distillation (FD) is proposed to simultaneously address the above two problems, which exchanges knowledge between the server and clients, supporting heterogeneous local models while significantly reducing communication overhead.
