Semi-Federated Learning
This work addresses efficiency and data distribution issues in federated learning for mobile communication networks, representing an incremental improvement.
The paper tackles the challenges of practicality, communication expense, and non-IID data in federated learning by proposing Semi-Federated Learning, which involves local client clustering and in-cluster training to reduce uplink bandwidth and improve robustness, as validated by numerical experiments.
Federated learning (FL) enables massive distributed Information and Communication Technology (ICT) devices to learn a global consensus model without any participants revealing their own data to the central server. However, the practicality, communication expense and non-independent and identical distribution (Non-IID) data challenges in FL still need to be concerned. In this work, we propose the Semi-Federated Learning (Semi-FL) which differs from the FL in two aspects, local clients clustering and in-cluster training. A sequential training manner is designed for our in-cluster training in this paper which enables the neighboring clients to share their learning models. The proposed Semi-FL can be easily applied to future mobile communication networks and require less up-link transmission bandwidth. Numerical experiments validate the feasibility, learning performance and the robustness to Non-IID data of the proposed Semi-FL. The Semi-FL extends the existing potentials of FL.