On Differential Privacy for Federated Learning in Wireless Systems with Multiple Base Stations
This work addresses privacy and efficiency challenges in federated learning for wireless networks, but it is incremental as it builds on existing differential privacy and scheduling methods.
The authors tackled the problem of federated learning in wireless systems with multiple base stations by applying differential privacy to protect user data during transmission, showing that their proposed scheduler improves average prediction accuracy and reduces privacy leakage.
In this work, we consider a federated learning model in a wireless system with multiple base stations and inter-cell interference. We apply a differential private scheme to transmit information from users to their corresponding base station during the learning phase. We show the convergence behavior of the learning process by deriving an upper bound on its optimality gap. Furthermore, we define an optimization problem to reduce this upper bound and the total privacy leakage. To find the locally optimal solutions of this problem, we first propose an algorithm that schedules the resource blocks and users. We then extend this scheme to reduce the total privacy leakage by optimizing the differential privacy artificial noise. We apply the solutions of these two procedures as parameters of a federated learning system. In this setting, we assume that each user is equipped with a classifier. Moreover, the communication cells are assumed to have mostly fewer resource blocks than numbers of users. The simulation results show that our proposed scheduler improves the average accuracy of the predictions compared with a random scheduler. Furthermore, its extended version with noise optimizer significantly reduces the amount of privacy leakage.