RT Journal Article
T1 Concept drift detection and adaptation for federated and continual learning
A1 Estévez Casado, Fernando
A1 Lema Pais, Dylan
A1 Fernández Criado, Marcos
A1 Iglesias Rodríguez, Roberto
A1 Vázquez Regueiro, Carlos
A1 Barro Ameneiro, Senén
K1 Federated learning
K1 Continual learning
K1 Nonstationarity
K1 Concept drift
K1 Federated Averaging
K1 Catastrophic forgetting
K1 Rehearsal
AB 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
PB Springer
SN 1380-7501
YR 2021
FD 2021
LK http://hdl.handle.net/10347/26638
UL http://hdl.handle.net/10347/26638
LA eng
NO Casado, F.E., Lema, D., Criado, M.F. et al. Concept drift detection and adaptation for federated and continual learning. Multimed Tools Appl (2021). https://doi.org/10.1007/s11042-021-11219-x
NO This research has received financial support from AEI/FEDER (EU) grant number TIN2017-90135-R, as well as the Consellería de Cultura, Educación e Ordenación Universitaria of Galicia (accreditation 2016–2019, ED431G/01 and ED431G/08, reference competitive group ED431C2018/29, and grant ED431F2018/02), and the European Regional Development Fund (ERDF). It has also been supported by the Ministerio de Universidades of Spain in the FPU 2017 program (FPU17/04154)
DS Minerva
RD 2 may 2026