Dimensionality reduction in decentralized networks by Gossip aggregation of principal components analyzers

Jérôme Fellus 1 David Picard 1 Philippe-Henri Gosselin 2, 3
1 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
3 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This paper considers dimensionality reduction in large decentralized networks with limited node-local computing and memory resources and unreliable point-to-point connectivity (e.g peer-to-peer, sensors or ad-hoc mobile networks). We propose an asynchronous decentralized algorithm built on a Gossip consensus protocol that perform Principal Components Analysis (PCA) of data spread over such networks. All nodes obtain the same local basis that span the global principal subspace. Reported experiments show that obtained bases both reach a consensus and accurately estimate the global PCA solution.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00985721
Contributor : Philippe-Henri Gosselin <>
Submitted on : Wednesday, April 30, 2014 - 12:01:16 PM
Last modification on : Friday, November 16, 2018 - 1:24:10 AM
Document(s) archivé(s) le : Wednesday, July 30, 2014 - 12:25:29 PM

File

fellus14esann.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00985721, version 1

Citation

Jérôme Fellus, David Picard, Philippe-Henri Gosselin. Dimensionality reduction in decentralized networks by Gossip aggregation of principal components analyzers. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2014, Bruges, Belgium. pp.171-176, 2014. 〈hal-00985721〉

Share

Metrics

Record views

553

Files downloads

190