2 papers
cs.DC2025
Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
Chengjie Ma, Seungeun Oh, Jihong Park +1
Federated learning (FL) enables distributed model training, yet in heterogeneous deployments, Bandwidth-Constrained Clients (BCCs) often contribute inefficiently due to limited upl…
cs.LG2024
Federated Learning based on Pruning and Recovery
Chengjie Ma
A novel federated learning training framework for heterogeneous environments is presented, taking into account the diverse network speeds of clients in realistic settings. This fra…