Federated Learning for Data Streams - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Federated Learning for Data Streams

Othmane Marfoq
Giovanni Neglia
Richard Vidal
  • Function : Author
  • PersonId : 1081827

Abstract

Federated learning (FL) is an effective solution to train machine learning models on the increasing amount of data generated by IoT devices and smartphones while keeping such data localized. Most previous work on federated learning assumes that clients operate on static datasets collected before training starts. This approach may be inefficient because 1) it ignores new samples clients collect during training, and 2) it may require a potentially long preparatory phase for clients to collect enough data. Moreover, learning on static datasets may be simply impossible in scenarios with small aggregate storage across devices. It is, therefore, necessary to design federated algorithms able to learn from data streams. In this work, we formulate and study the problem of federated learning for data streams. We propose a general FL algorithm to learn from data streams through an opportune weighted empirical risk minimization. Our theoretical analysis provides insights to configure such an algorithm, and we evaluate its performance on a wide range of machine learning tasks.
Fichier principal
Vignette du fichier
2301.01542 (4).pdf (1.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04385635 , version 1 (10-01-2024)

Licence

Attribution

Identifiers

  • HAL Id : hal-04385635 , version 1

Cite

Othmane Marfoq, Giovanni Neglia, Laetitia Kameni, Richard Vidal. Federated Learning for Data Streams. AISTATS 2023 - The 26th International Conference on Artificial Intelligence and Statistics, Apr 2023, Valencia (Espagne), Spain. ⟨hal-04385635⟩
22 View
12 Download

Share

Gmail Facebook X LinkedIn More