Parameterizing Federated Continual Learning for Reproducible Research

Conference Paper (2025)
Author(s)

Bart Cox (TU Delft - Data-Intensive Systems)

Jeroen Galjaard (TU Delft - Data-Intensive Systems)

Aditya Shankar (TU Delft - Data-Intensive Systems)

J.E.A.P. Decouchant (TU Delft - Data-Intensive Systems)

Lydia Chen (TU Delft - Data-Intensive Systems)

Research Group
Data-Intensive Systems
DOI related publication
https://doi.org/10.1007/978-3-031-74643-7_35
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Data-Intensive Systems
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.@en
Pages (from-to)
478-486
ISBN (print)
978-3-031-74642-0
ISBN (electronic)
978-3-031-74643-7
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Federated Learning (FL) systems evolve in heterogeneous and ever-evolving environments that challenge their performance. Under real deployments, the learning tasks of clients can also evolve with time, which calls for the integration of methodologies such as Continual Learning (CL). To enable research reproducibility, we propose a set of experimental best practices that precisely capture and emulate complex learning scenarios. To the best of our knowledge, our framework, Freddie, is the first entirely configurable framework for Federated Continual Learning (FCL), and it can be seamlessly deployed on a large number of machines leveraging containerization and Kubernetes. We demonstrate the effectiveness of Freddie on two use cases, (i) large-scale concurrent FL on CIFAR100 and (ii) heterogeneous task sequence on FCL, which highlight unaddressed performance challenges in FCL scenarios.

Files

978-3-031-74643-7-1.pdf
(pdf | 0.847 Mb)
- Embargo expired in 01-07-2025
License info not available