Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/26395
Title: Distributed Bayesian Probabilistic Matrix Factorization
Authors: Aa, Tom Vander
Chakroun, Imen
HABER, Tom 
Issue Date: 2017
Publisher: Elsevier Science BV
Source: Koumoutsakos, Petros; Lees, Michael; Krzhizhanovskaya, Valeria; Dongarra, Jack; Sloot, Peter M. A. (Ed.). International Conference on Computational Science, ICCS 2017, 12-14 June 2017, Zurich, Switzerland, Elsevier Science BV,p. 1030-1039
Series/Report: Procedia Computer Science
Series/Report no.: 108
Abstract: Using the matrix factorization technique in machine learning is very common mainly in areas like recommender systems. Despite its high prediction accuracy and its ability to avoid over-fitting of the data, the Bayesian Probabilistic Matrix Factorization algorithm (BPMF) has not been widely used on large scale data because of the prohibitive cost. In this paper, we propose a distributed high-performance parallel implementation of the BPMF using Gibbs sampling on shared and distributed architectures. We show by using efficient load balancing using work stealing on a single node, and by using asynchronous communication in the distributed version we beat state of the art implementations. (C) 2017 The Authors. Published by Elsevier B.V.
Notes: [Aa, Tom Vander; Chakroun, Imen] IMEC, Exascience Lab, Kapeldreef 75, B-3001 Leuven, Belgium. [Haber, Tom] Expertise Ctr Digital Media, Wetenschapspk 2, B-3590 Diepenbeek, Belgium.
Keywords: Probabilistic matrix factorization algorithm; Collaborative filtering; Machine learning; PGAS; multi-core;probabilistic matrix factorization algorithm; Collaborative filtering; machine learning; PGAS; multi-core
Document URI: http://hdl.handle.net/1942/26395
DOI: 10.1016/j.procs.2017.05.009
ISI #: 000404959000104
Rights: © 2017 The Authors. Published by Elsevier B.V. Peer-review under responsibility of the scientific committee of the International Conference on Computational Science
Category: C1
Type: Proceedings Paper
Validations: ecoom 2018
Appears in Collections:Research publications

Files in This Item:
File Description SizeFormat 
Haber.pdfPublished version535.69 kBAdobe PDFView/Open
Show full item record

SCOPUSTM   
Citations

7
checked on Sep 3, 2020

WEB OF SCIENCETM
Citations

10
checked on Oct 12, 2024

Page view(s)

58
checked on Sep 7, 2022

Download(s)

220
checked on Sep 7, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.