Mostrar o rexistro simple do ítem
Ensemble and continual federated learning for classification tasks
dc.contributor.author | Casado, Fernando E. | |
dc.contributor.author | Lema, Dylan | |
dc.contributor.author | Iglesias, Roberto | |
dc.contributor.author | Regueiro, Carlos V. | |
dc.contributor.author | Barro, Senén | |
dc.date.accessioned | 2024-06-21T11:41:11Z | |
dc.date.available | 2024-06-21T11:41:11Z | |
dc.date.issued | 2023-09 | |
dc.identifier.citation | Casado, F.E., Lema, D., Iglesias, R. et al. Ensemble and continual federated learning for classification tasks. Mach Learn 112, 3413–3453 (2023). https://doi.org/10.1007/s10994-023-06330-z | es_ES |
dc.identifier.issn | 0885-6125 | |
dc.identifier.uri | http://hdl.handle.net/2183/37286 | |
dc.description | Financiado para publicación en acceso aberto: CRUE-CSIC/Springer Nature. | es_ES |
dc.description | The raw data used in the experiments described in Sect. 7 and Appendix A can be found on the following URL: https://citius.usc.es/t/30. | es_ES |
dc.description.abstract | [Abstract]: Federated learning is the state-of-the-art paradigm for training a learning model collaboratively across multiple distributed devices while ensuring data privacy. Under this framework, different algorithms have been developed in recent years and have been successfully applied to real use cases. The vast majority of work in federated learning assumes static datasets and relies on the use of deep neural networks. However, in real-world problems, it is common to have a continual data stream, which may be non-stationary, leading to phenomena such as concept drift. Besides, there are many multi-device applications where other, non-deep strategies are more suitable, due to their simplicity, explainability, or generalizability, among other reasons. In this paper we present Ensemble and Continual Federated Learning, a federated architecture based on ensemble techniques for solving continual classification tasks. We propose the global federated model to be an ensemble, consisting of several independent learners, which are locally trained. Thus, we enable a flexible aggregation of heterogeneous client models, which may differ in size, structure, or even algorithmic family. This ensemble-based approach, together with drift detection and adaptation mechanisms, also allows for continual adaptation in situations where data distribution changes over time. In order to test our proposal and illustrate how it works, we have evaluated it in different tasks related to human activity recognition using smartphones. | es_ES |
dc.description.sponsorship | Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This research has received financial support from AEI/FEDER (European Union) Grant Number PID2020-119367RB-I00, as well as the Consellería de Cultura, Educación e Universitade of Galicia (accreditation ED431G-2019/04, ED431G2019/01, and ED431C2018/29), 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). | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED431G-2019/04 | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED431G2019/01 | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED431C2018/29 | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | Springer | es_ES |
dc.relation | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-119367RB-I00/ES/APRENDIZAJE FEDERADO Y CONTINUO A PARTIR DE DATOS HETEROGENEOS EN DISPOSITIVOS Y ROBOTS | es_ES |
dc.relation | info:eu-repo/grantAgreement/MECD/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/FPU17%2F04154/ES/ | es_ES |
dc.relation.uri | https://doi.org/10.1007/s10994-023-06330-z | es_ES |
dc.rights | Attribution 4.0 International (CC BY) | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by/3.0/es/ | * |
dc.subject | Concept drift | es_ES |
dc.subject | Ensemble learning | es_ES |
dc.subject | Federated learning | es_ES |
dc.subject | Semi-supervised classification | es_ES |
dc.subject | Smartphones | es_ES |
dc.title | Ensemble and continual federated learning for classification tasks | es_ES |
dc.type | info:eu-repo/semantics/article | es_ES |
dc.rights.access | info:eu-repo/semantics/openAccess | es_ES |
UDC.journalTitle | Machine Learning | es_ES |
UDC.volume | 112 | es_ES |
UDC.issue | 9 | es_ES |
UDC.startPage | 3413 | es_ES |
UDC.endPage | 3453 | es_ES |
dc.identifier.doi | 10.1007/s10994-023-06330-z |
Ficheiros no ítem
Este ítem aparece na(s) seguinte(s) colección(s)
-
GI-GAC - Artigos [190]