Federated learning from big data over networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

This paper formulates and studies a novel algorithm for federated learning from large collections of local datasets. This algorithm capitalizes on an intrinsic network structure that relates the local datasets via an undirected “empirical” graph. We model such big data over networks using a networked linear regression model. Each local dataset has individual regression weights. The weights of close-knit sub-collections of local datasets are enforced to deviate only little. This lends naturally to a network Lasso problem which we solve using a primal-dual method. We obtain a distributed federated learning algorithm via a message passing implementation of this primal-dual method. We provide a detailed analysis of the statistical and computational properties of the resulting federated learning algorithm.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherIEEE
Pages3055-3059
Number of pages5
Volume2021-June
ISBN (Print)978-1-7281-7605-5
DOIs
Publication statusPublished - 2021
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Acoustics, Speech, and Signal Processing - Virtua, Online, Toronto, Canada
Duration: 6 Jun 202111 Jun 2021

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherIEEE
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleICASSP
Country/TerritoryCanada
CityToronto
Period06/06/202111/06/2021

Keywords

  • Complex networks
  • Convex optimization
  • Estimation
  • Federated learning
  • Machine learning

Fingerprint

Dive into the research topics of 'Federated learning from big data over networks'. Together they form a unique fingerprint.

Cite this