What type of study is this?

This is a Experimental Study study.

October 11, 2025Open Access

Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models

View Full Paper

Ask AI

Bookmark

Authors

Proposed FedOL reduces communication overhead and improves model reliability in mobile networks, highlighting federated learning's effectiveness.

FedOL improves learning reliability by refining pseudo-labels and server models to overcome data distribution bias.
Simulation results show that FedOL significantly outperforms existing baselines, achieving better resource efficiency.
This approach enables cooperative model training without direct data sharing, adhering to privacy constraints.
FedOL supports heterogeneous client models by allowing customized architectures, enhancing application flexibility.

Ye et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

October 11, 2025Open Access

View Full Paper

Ask AI

Bookmark

Authors

Proposed FedOL reduces communication overhead and improves model reliability in mobile networks, highlighting federated learning's effectiveness.

FedOL improves learning reliability by refining pseudo-labels and server models to overcome data distribution bias.
Simulation results show that FedOL significantly outperforms existing baselines, achieving better resource efficiency.
This approach enables cooperative model training without direct data sharing, adhering to privacy constraints.
FedOL supports heterogeneous client models by allowing customized architectures, enhancing application flexibility.

Ye et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark