Personalized and Private Peer-to-Peer ...
Type de document :
Communication dans un congrès avec actes
Titre :
Personalized and Private Peer-to-Peer Machine Learning
Auteur(s) :
Bellet, Aurelien [Auteur]
Machine Learning in Information Networks [MAGNET]
Guerraoui, Rachid [Auteur]
Distributed Programming Laboratory [LPD]
Taziki, Mahsa [Auteur]
Ecole Polytechnique Fédérale de Lausanne [EPFL]
Tommasi, Marc [Auteur]
Machine Learning in Information Networks [MAGNET]
Machine Learning in Information Networks [MAGNET]
Guerraoui, Rachid [Auteur]
Distributed Programming Laboratory [LPD]
Taziki, Mahsa [Auteur]
Ecole Polytechnique Fédérale de Lausanne [EPFL]
Tommasi, Marc [Auteur]
Machine Learning in Information Networks [MAGNET]
Titre de la manifestation scientifique :
AISTATS 2018 - 21st International Conference on Artificial Intelligence and Statistics
Ville :
Lanzarote
Pays :
Espagne
Date de début de la manifestation scientifique :
2018-04-09
Date de publication :
2018
Discipline(s) HAL :
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Cryptographie et sécurité [cs.CR]
Informatique [cs]/Calcul parallèle, distribué et partagé [cs.DC]
Informatique [cs]/Systèmes et contrôle [cs.SY]
Statistiques [stat]/Autres [stat.ML]
Informatique [cs]/Cryptographie et sécurité [cs.CR]
Informatique [cs]/Calcul parallèle, distribué et partagé [cs.DC]
Informatique [cs]/Systèmes et contrôle [cs.SY]
Statistiques [stat]/Autres [stat.ML]
Résumé en anglais : [en]
The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy ...
Lire la suite >The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this paper, we introduce an efficient algorithm to address the above problem in a fully decentralized (peer-to-peer) and asynchronous fashion, with provable convergence rate. We show how to make the algorithm differentially private to protect against the disclosure of information about the personal datasets, and formally analyze the trade-off between utility and privacy. Our experiments show that our approach dramatically outperforms previous work in the non-private case, and that under privacy constraints, we can significantly improve over models learned in isolation.Lire moins >
Lire la suite >The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this paper, we introduce an efficient algorithm to address the above problem in a fully decentralized (peer-to-peer) and asynchronous fashion, with provable convergence rate. We show how to make the algorithm differentially private to protect against the disclosure of information about the personal datasets, and formally analyze the trade-off between utility and privacy. Our experiments show that our approach dramatically outperforms previous work in the non-private case, and that under privacy constraints, we can significantly improve over models learned in isolation.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.inria.fr/hal-01745796/document
- Accès libre
- Accéder au document
- http://arxiv.org/pdf/1705.08435
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-01745796/document
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-01745796/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- aistats18_supp.pdf
- Accès libre
- Accéder au document
- 1705.08435
- Accès libre
- Accéder au document