Abstract
Smart devices, such as smartphones, wearables, robots, and others, can collect vast amounts of data from their environment. This data is suitable for training machine learning models, which can significantly improve their behavior, and therefore, the user experience. Federated learning is a young and popular framework that allows multiple distributed devices to train deep learning models collaboratively while preserving data privacy. Nevertheless, this approach may not be optimal for scenarios where data distribution is non-identical among the participants or changes over time, causing what is known as concept drift. Little research has yet been done in this field, but this kind of situation is quite frequent in real life and poses new challenges to both continual and federated learning. Therefore, in this work, we present a new method, called Concept-Drift-Aware Federated Averaging (CDA-FedAvg). Our proposal is an extension of the most popular federated algorithm, Federated Averaging (FedAvg), enhancing it for continual adaptation under concept drift. We empirically demonstrate the weaknesses of regular FedAvg and prove that CDA-FedAvg outperforms it in this type of scenario.
Highlights
Over the last few decades, our society has experienced a technological explosion which, among other things, has gradually surrounded us with smart devices that are part of our daily lives
In this article we describe the performance of our method when it has been tested for the task of human activity recognition (HAR) using smartphones
We have shown the shortcomings of regular federated algorithms, such as Federated Averaging (FedAvg), when data is nonstationary over time, which is a common real-world situation
Summary
Over the last few decades, our society has experienced a technological explosion which, among other things, has gradually surrounded us with smart devices that are part of our daily lives. We are talking about smartphones, and wearables, “things” from the Internet of Things (IoT), service robots, etc. Multifunctional devices with cutting-edge technology that allows a great number of applications from all human domains: health, sport, education, banking, etc. The growing amount of data that these devices can collect, together with a good intercommunication between them, enables the possibility of integrating machine learning models that evolve and adapt to improve their behaviour. Extended author information available on the last page of the article
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
