Privacy is What We Care About: Experimental Investigation of Federated Learning on Edge Devices
This work addresses privacy concerns in digital health by demonstrating federated learning on edge devices, but it is incremental as it applies existing methods to new hardware and data scenarios.
The study investigated training deep neural networks on Raspberry Pi4 edge devices using federated learning on MNIST data, achieving up to 85% test accuracy with non-IID samples in 2 minutes while exchanging less than 10 MB per device.
Federated Learning enables training of a general model through edge devices without sending raw data to the cloud. Hence, this approach is attractive for digital health applications, where data is sourced through edge devices and users care about privacy. Here, we report on the feasibility to train deep neural networks on the Raspberry Pi4s as edge devices. A CNN, a LSTM and a MLP were successfully trained on the MNIST data-set. Further, federated learning is demonstrated experimentally on IID and non-IID samples in a parametric study, to benchmark the model convergence. The weight updates from the workers are shared with the cloud to train the general model through federated learning. With the CNN and the non-IID samples a test-accuracy of up to 85% could be achieved within a training time of 2 minutes, while exchanging less than $10$ MB data per device. In addition, we discuss federated learning from an use-case standpoint, elaborating on privacy risks and labeling requirements for the application of emotion detection from sound. Based on the experimental findings, we discuss possible research directions to improve model and system performance. Finally, we provide best practices for a practitioner, considering the implementation of federated learning.