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

被引：31

作者：

Duriakova, Erika ^{[1
]}

Tragos, Elias Z. ^{[1
]}

Smyth, Barry ^{[1
]}

Hurley, Neil ^{[1
]}

Pena, Francisco J. ^{[1
]}

Symeonidis, Panagiotis ^{[1
]}

Geraci, James ^{[2
]}

Lawlor, Aonghus ^{[1
]}

机构：

[1] Univ Coll Dublin, Insight Ctr Data Analyt, Dublin, Ireland

[2] Samsung Elect Co Ltd, Seoul, South Korea

来源：

RECSYS 2019: 13TH ACM CONFERENCE ON RECOMMENDER SYSTEMS | 2019年

关键词：

matrix factorisation; decentralised matrix factorisation; privacy aware; rating prediction;

D O I：

10.1145/3298689.3347035

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：457 / 461

页数：5