Semi-Federated Learning for Collaborative Intelligence in Massive IoT Networks

Implementing existing federated learning in massive Internet of Things (IoT) networks faces critical challenges, such as imbalanced and statistically heterogeneous data and device diversity. To this end, we propose a semi-federated learning (SemiFL) framework to provide a potential solution for the realization of intelligent IoT. By seamlessly integrating the centralized and federated paradigms, our SemiFL framework shows high scalability in terms of the number of IoT devices even in the presence of computing-limited sensors. Furthermore, compared to traditional learning approaches, the proposed SemiFL can make better use of distributed data and computing resources, due to the collaborative model training between the edge server and local devices. Simulation results show the effectiveness of our SemiFL framework for massive IoT networks. The code can be found at https://github.com/niwanli/SemiFL_IoT.

Automated summary

We propose a semi-federated learning (SemiFL) framework to address the challenges faced by existing federated learning in massive IoT networks. This framework seamlessly integrates centralized and federated paradigms and shows high scalability even with computing-limited sensors. Compared to traditional learning methods, SemiFL utilizes distributed data and computing resources more effectively through collaborative model training between edge servers and local devices. Simulation results demonstrate the effectiveness of our SemiFL framework for massive IoT networks.