Peer-to-peer multi-class boosting

I. Hegedűs R. Busa-Fekete R. Ormándi M. Jelasity B. Kégl 1, 2
1 TAO - Machine Learning and Optimisation
Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, CNRS - Centre National de la Recherche Scientifique : UMR8623, LRI - Laboratoire de Recherche en Informatique
2 Appstat
LAL - Laboratoire de l'Accélérateur Linéaire, LRI - Laboratoire de Recherche en Informatique
Abstract : We focus on the problem of data mining over large-scale fully distributed databases, where each node stores only one data record. We assume that a data record is never allowed to leave the node it is stored at. Possible motivations for this assumption include privacy or a lack of a centralized infrastructure. To tackle this problem, earlier we proposed the generic gossip learning framework (GoLF), but so far we have studied only basic linear algorithms. In this paper we implement the well-known boosting technique in GoLF. Boosting techniques have attracted growing attention in machine learning due to their outstanding performance in many practical applications. Here, we present an implementation of a boosting algorithm that is based on FilterBoost. Our main algorithmic contribution is a derivation of a pure online multi-class version of FilterBoost, so that it can be employed in GoLF. We also propose improvements to GoLF, with the aim of maximizing the diversity of the evolving models gossiped in the network, a feature that we show to be important. We evaluate the robustness and the convergence speed of the algorithm empirically over three benchmark databases. We compare the algorithm with the sequential AdaBoost algorithm and we test its performance in a failure scenario involving message drop and delay, and node churn.
Type de document :
Communication dans un congrès
Christos Kaklamanis, Theodore Papatheodorou, Paul G. Spirakis. 18th International European Conference on Parallel and Distributed Computing (Euro-Par 2012), Aug 2012, Rhodes Island, Greece. Springer, 7484, pp.389-400, 2012, Lecture Notes In Computer Science


http://hal.in2p3.fr/in2p3-00726735
Contributeur : Sabine Starita <>
Soumis le : vendredi 31 août 2012 - 10:50:26
Dernière modification le : mercredi 20 juillet 2016 - 09:44:52
Document(s) archivé(s) le : samedi 1 décembre 2012 - 03:30:43

Fichier

EUROPAR2012.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : in2p3-00726735, version 1

Collections

Citation

I. Hegedűs, R. Busa-Fekete, R. Ormándi, M. Jelasity, B. Kégl. Peer-to-peer multi-class boosting. Christos Kaklamanis, Theodore Papatheodorou, Paul G. Spirakis. 18th International European Conference on Parallel and Distributed Computing (Euro-Par 2012), Aug 2012, Rhodes Island, Greece. Springer, 7484, pp.389-400, 2012, Lecture Notes In Computer Science. <in2p3-00726735>

Exporter

Partager

Métriques

Consultations de
la notice

202

Téléchargements du document

459