Utility Fairness for the Differentially Private Federated-Learning-Based Wireless IoT Networks

Federated learning (FL) allows predictive model training on the sensed data in a wireless Internet of Things (IoT) network evading data collection cost in terms of energy, time, and privacy. In this article, for an FL setting, we model the learning gain achieved by an IoT device against its participation cost as its utility. The local model quality and the associated cost differ from device to device due to the device heterogeneity, which could be time varying. We identify that this results in utility unfairness because the same global model is shared among the devices. In the vanilla FL setting, the master is unaware of devices' local model computation and transmission costs, thus, it is unable to address the utility unfairness problem. In addition, a device may exploit this lack of knowledge at the master to intentionally reduce its expenditure and thereby boost its utility. We propose to control the quality of the global model shared with the devices, in each round, based on their contribution and expenditure. This is achieved by employing differential privacy (DP) to curtail global model divulgence based on the learning contribution. Furthermore, we devise adaptive computation and transmission policies for each device to control its expenditure in order to mitigate utility unfairness. Our results show that the proposed scheme reduces the standard deviation of the energy cost of devices by 99% in comparison to the benchmark scheme, while the standard deviation of the training loss of devices varies around 0.103.

Automated summary

This article discusses the application of federated learning in the Internet of Things and proposes a solution based on differential privacy to address privacy concerns and utility unfairness. By controlling the quality of the global model and the expenditure of devices, the proposed scheme significantly reduces the variability of energy costs.