Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR

Résumé

Federated Learning is a new machine learning paradigm dealing with distributed model learning on independent devices. One of the many advantages of federated learning is that training data stay on devices (such as smartphones), and only learned models are shared with a centralized server. In the case of supervised learning, labeling is entrusted to the clients. However, acquiring such labels can be prohibitively expensive and error-prone for many tasks, such as human activity recognition. Hence, a wealth of data remains unlabelled and unexploited. Most existing federated learning approaches that focus mainly on supervised learning have mostly ignored this mass of unlabelled data. Furthermore, it is unclear whether standard federated Learning approaches are suited to self-supervised learning. The few studies that have dealt with the problem have limited themselves to the favorable situation of homogeneous datasets. This work lays the groundwork for a reference evaluation of federated Learning with Semi-Supervised Learning in a realistic setting. We show that standard lightweight autoencoder and standard Federated Averaging fail to learn a robust representation for Human Activity Recognition with several realistic heterogeneous datasets. These findings advocate for a more intensive research effort in Federated Self Supervised Learning to exploit the mass of heterogeneous unlabelled data present on mobile devices.

Dates et versions

hal-03727244 , version 1 (19-07-2022)

Identifiants

Citer

Sannara Ek, Romain Rombourg, François Portet, Philippe Lalanda. Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR. 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops), Mar 2022, Pisa, France. pp.557-562, ⟨10.1109/PerComWorkshops53856.2022.9767369⟩. ⟨hal-03727244⟩
17 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More