RT Journal Article
T1 Non-IID data and Continual Learning processes in Federated Learning: a long road ahead
A1 Fernández Criado, Marcos
A1 Estévez Casado, Fernando
A1 Iglesias Rodríguez, Roberto
A1 Vázquez Regueiro, Carlos
A1 Barro Ameneiro, Senén
K1 Federated learning
K1 Data heterogeneity
K1 Non-IID data
K1 Concept drift
K1 Distributed learning
K1 Continual learning
AB Federated Learning is a novel framework that allows multiple devices or institutions to train a machine learning model collaboratively while preserving their data private. This decentralized approach is prone to suffer the consequences of data statistical heterogeneity, both across the different entities and over time, which may lead to a lack of convergence. To avoid such issues, different methods have been proposed in the past few years. However, data may be heterogeneous in lots of different ways, and current proposals do not always determine the kind of heterogeneity they are considering. In this work, we formally classify data statistical heterogeneity and review the most remarkable learning Federated Learning strategies that are able to face it. At the same time, we introduce approaches from other machine learning frameworks. In particular, Continual Learning strategies are worthy of special attention, since they are able to handle habitual kinds of data heterogeneity. Throughout this paper, we present many methods that could be easily adapted to the Federated Learning settings to improve its performance. Apart from theoretically discussing the negative impact of data heterogeneity, we examine it and show some empirical results using different types of non-IID data
PB Elsevier
YR 2022
FD 2022
LK http://hdl.handle.net/10347/29177
UL http://hdl.handle.net/10347/29177
LA eng
NO Information Fusion 88 (2022) 263-280
NO This work has received financial support from AEI/FEDER (EU) grant number PID2020-119367RB-I00. It has also been supported by the Xunta de Galicia - Consellería de Cultura, Educación e Universidade (Centros de investigación de Galicia accreditation 2019–2022 ED431G-2019/04 and ED431G2019/01, and Reference Competitive Groups accreditation 2021–2024, ED431C 2018/29, ED431F2018/02 and ED431C 2021/30) and the European Union (European Regional Development Fund - ERDF). Finally, it has also been funded by the Ministerio de Universidades of Spain in the FPU 2017 program (FPU17/04154)
DS Minerva
RD 27 abr 2026