3 papers
cs.LG2025
A Unified Convergence Analysis for Semi-Decentralized Learning: Sampled-to-Sampled vs. Sampled-to-All Communication
Angelo Rodio, Giovanni Neglia, Zheng Chen +1
In semi-decentralized federated learning, devices primarily rely on device-to-device communication but occasionally interact with a central server. Periodically, a sampled subset o…
cs.LG2025
Green Federated Learning via Carbon-Aware Client and Time Slot Scheduling
Daniel Richards Arputharaj, Charlotte Rodriguez, Angelo Rodio +1
Training large-scale machine learning models incurs substantial carbon emissions. Federated Learning (FL), by distributing computation across geographically dispersed clients, offe…
cs.LG2025
Optimizing Privacy-Utility Trade-off in Decentralized Learning with Generalized Correlated Noise
Angelo Rodio, Zheng Chen, Erik G. Larsson
Decentralized learning enables distributed agents to collaboratively train a shared machine learning model without a central server, through local computation and peer-to-peer comm…