Parameterizing Federated Continual Learning for Reproducible Research
This work addresses the problem of research reproducibility in FCL for researchers, but it is incremental as it focuses on experimental best practices rather than new learning methods.
The authors tackled the challenge of enabling reproducible research in Federated Continual Learning (FCL) by proposing a configurable framework called Freddie, which captures and emulates complex learning scenarios, and demonstrated its effectiveness on large-scale FL and heterogeneous task sequence use cases.
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.