Parameterizing Federated Continual Learning for Reproducible Research

TL;DR

This paper introduces Freddie, a configurable framework for Federated Continual Learning that supports reproducible research and addresses performance challenges in complex, evolving FL environments.

Contribution

The paper presents Freddie, the first fully configurable framework for Federated Continual Learning, enabling reproducible experiments in heterogeneous and evolving scenarios.

Findings

Freddie effectively models complex FL and FCL scenarios.

It reveals performance challenges in large-scale and heterogeneous FCL.

Demonstrates deployment on Kubernetes for scalability.

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. To enable research reproducibility, we propose a set of experimental best practices that precisely capture and emulate complex learning scenarios. 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 thanks to the use of Kubernetes and containerization. We demonstrate the effectiveness of Freddie on two use cases, (i) large-scale FL on CIFAR100 and (ii) heterogeneous task sequence on FCL, which highlight unaddressed performance challenges in FCL scenarios.