Personalized and Private Peer-to-Peer Machine Learning

Aurélien Bellet, Rachid Guerraoui, Mahsa Taziki, Marc Tommasi
Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, PMLR 84:473-481, 2018.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v84-bellet18a, title = {Personalized and Private Peer-to-Peer Machine Learning}, author = {Bellet, Aurélien and Guerraoui, Rachid and Taziki, Mahsa and Tommasi, Marc}, booktitle = {Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics}, pages = {473--481}, year = {2018}, editor = {Storkey, Amos and Perez-Cruz, Fernando}, volume = {84}, series = {Proceedings of Machine Learning Research}, month = {09--11 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v84/bellet18a/bellet18a.pdf}, url = {https://proceedings.mlr.press/v84/bellet18a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Personalized and Private Peer-to-Peer Machine Learning %A Aurélien Bellet %A Rachid Guerraoui %A Mahsa Taziki %A Marc Tommasi %B Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2018 %E Amos Storkey %E Fernando Perez-Cruz %F pmlr-v84-bellet18a %I PMLR %P 473--481 %U https://proceedings.mlr.press/v84/bellet18a.html %V 84 %X 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.
APA
Bellet, A., Guerraoui, R., Taziki, M. & Tommasi, M.. (2018). Personalized and Private Peer-to-Peer Machine Learning. Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 84:473-481 Available from https://proceedings.mlr.press/v84/bellet18a.html.

Related Material