Personalised Federated Learning On Heterogeneous Feature Spaces - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Personalised Federated Learning On Heterogeneous Feature Spaces

Maxime Vono
Liva Ralaivola
  • Fonction : Auteur

Résumé

Most personalised federated learning (FL) approaches assume that raw data of all clients are defined in a common subspace i.e. all clients store their data according to the same schema. For real-world applications, this assumption is restrictive as clients, having their own systems to collect and then store data, may use heterogeneous data representations. We aim at filling this gap. To this end, we propose a general framework coined FLIC that maps client's data onto a common feature space via local embedding functions. The common feature space is learnt in a federated manner using Wasserstein barycenters while the local embedding functions are trained on each client via distribution alignment. We integrate this distribution alignement mechanism into a federated learning approach and provide the algorithmics of FLIC. We compare its perfomances against FL benchmarks involving heterogeneous input features spaces. In addition, we provide theoretical insights supporting the relevance of our methodology.
Fichier principal
Vignette du fichier
2301.11447.pdf (3.97 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03962195 , version 1 (30-01-2023)

Identifiants

  • HAL Id : hal-03962195 , version 1

Citer

Alain Rakotomamonjy, Maxime Vono, Hamlet Jesse Medina Ruiz, Liva Ralaivola. Personalised Federated Learning On Heterogeneous Feature Spaces. 2023. ⟨hal-03962195⟩
11 Consultations
18 Téléchargements

Partager

Gmail Facebook X LinkedIn More