PDMFRec: A Decentralised Matrix Factorisation with Tunable User-centric Privacy

Files in This Item:
File Description SizeFormat 
insight_publication.pdf964.56 kBAdobe PDFDownload
Title: PDMFRec: A Decentralised Matrix Factorisation with Tunable User-centric Privacy
Authors: Duriakova, ErikaTragos, EliasSmyth, BarryHurley, Neil J.Peña, FranciscoSymeonidis, PanagiotisGeraci, JamesLawlor, Aonghus
Permanent link: http://hdl.handle.net/10197/11360
Date: 19-Sep-2019
Online since: 2020-04-30T15:04:50Z
Abstract: Conventional approaches to matrix factorisation (MF) typically rely on a centralised collection of user data for building a MF model. This approach introduces an increased risk when it comes to user privacy. In this short paper we propose an alternative, user-centric, privacy enhanced, decentralised approach to MF. Our method pushes the computation of the recommendation model to the user’s device, and eliminates the need to exchange sensitive personal information; instead only the loss gradients of local (device-based) MF models need to be shared. Moreover, users can select the amount and type of information to be shared, for enhanced privacy. We demonstrate the effectiveness of this approach by considering different levels of user privacy in comparison with state-of-the-art alternatives.
Funding Details: Science Foundation Ireland
metadata.dc.description.othersponsorship: Insight Research Centre
Samsung Research
Type of material: Conference Publication
Publisher: ACM
Copyright (published version): 2019 ACM
Keywords: Matrix factorisationDecentralised matrix factorisationPrivacy awareRating prediction
DOI: 10.1145/3298689.3347035
Other versions: https://recsys.acm.org/recsys19/
Language: en
Status of Item: Peer reviewed
Conference Details: The 13th ACM Conference on Recommender Systems (RecSys'19), Copenhagen, Denmark, 16-20 September 2019
ISBN: 978-1-4503-6243-6
Appears in Collections:Insight Research Collection

Show full item record

Page view(s)

Last Week
Last month
checked on Jun 5, 2020


checked on Jun 5, 2020

Google ScholarTM



This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.