On-Demand Client Deployment And Selection In Federated Learning

Abstract

Traditional machine learning models are used to train their models on centralized data sets. Lately, data privacy becomes a real aspect to take into consideration while collecting data. For that, Federated learning plays nowadays a great role in addressing privacy and technology together by maintaining the ability to learn over decentralized data sets. The training is limited to the user devices only while sharing the locally computed parameter with the server that aggregates those updated weights to optimize a global model. This scenario is repeated multiple rounds for better results and convergence. Most of the literature proposed client selection methods to converge faster and increase accuracy. However, none of them has targeted the ability to deploy and select clients on the fly wherever and whenever needed. In fact, some devices are not available to serve as clients in the federated learning due to the highly dynamic environments and/or do not have the capabilities to accomplish this task. In this paper, we address the aforementioned limitations by introducing an on-demand client deployment in federated learning offering more volume and heterogeneity of data in the learning process. We make use of containerization technology such as Docker to build efficient environments using IoT and mobile devices serving as volunteering devices, and Kubernetes utility called Kubeadm to monitor the devices. The performed experiments illustrate the relevance of the proposed approach and the efficiency of the on-the-fly deployment of clients whenever and wherever needed.