A distillation-based approach integrating continual learning and federated learning for pervasive services - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

A distillation-based approach integrating continual learning and federated learning for pervasive services

Résumé

Federated Learning, a new machine learning paradigm enhancing the use of edge devices, is receiving a lot of attention in the pervasive community to support the development of smart services. Nevertheless, this approach still needs to be adapted to the specificity of the pervasive domain. In particular, issues related to continual learning need to be addressed. In this paper, we present a distillation-based approach dealing with catastrophic forgetting in federated learning scenario. Specifically, Human Activity Recognition tasks are used as a demonstration domain.
Fichier principal
Vignette du fichier
ijcai21-multiauthor.pdf (659.74 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03332046 , version 1 (04-09-2021)

Identifiants

Citer

Anastasiia Usmanova, François Portet, Philippe Lalanda, German Vega. A distillation-based approach integrating continual learning and federated learning for pervasive services. 3rd Workshop on Continual and Multimodal Learning for Internet of Things -- Co-located with IJCAI 2021, Aug 2021, Montreal, Canada. ⟨hal-03332046⟩
108 Consultations
174 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More