1 Introduction
Traditional machine learning adopts a centralized approach, which requires training data from different sources to be aggregated on a single machine or in a data center. This centralized training approach can be privacy-intrusive, requiring users to upload their data to train a better machine learning model. As an alternative decentralized training approach, federated learning (FL) enables users to collaboratively learn a machine learning model while keeping all the data that may contain private information on their local devices [1]. In this case, users can benefit from a well-trained machine learning model, utilizing sufficient data from different sources without sharing sensitive personal data.