A PRACTICAL CROSS-DEVICE FEDERATED LEARNING FRAMEWORK OVER 5G NETWORKS

The concept of federated learning (FL) was first proposed by Google in 2016. Since then, FL has been widely studied for the feasibility of application in various fields due to its potential to make full use of data without compromising privacy. However, limited by the capacity of wireless data transmission, the employment of FL on mobile devices has been making slow progress in practice. The development and commercialization of the 5th generation (5G) mobile networks has shed some light on this. In this article, we analyze the challenges of existing FL schemes for mobile devices and propose a novel cross-device FL framework that utilizes the anonymous communication technology and ring signature to protect the privacy of participants while reducing the computation overhead of mobile devices participating in FL. In addition, our scheme implements a contribution-based incentive mechanism to encourage mobile users to participate in FL. We also give a case study of autonomous driving. Finally, we present the performance evaluation of the proposed scheme and discuss some open issues in FL.

Automated summary

This article introduces the concept and current applications of federated learning (FL), highlighting the challenges of applying FL on mobile devices and potential solutions through the use of 5G networks. A novel cross-device FL framework is proposed to protect privacy and reduce computation overhead on mobile devices, along with a contribution-based incentive mechanism to encourage user participation in FL. The article also includes a case study on autonomous driving, performance evaluation of the proposed scheme, and discussion of open issues in FL.