Efficient Node Selection in Private Personalized Decentralized Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zec, Edvin Listo, Östman, Johan, Mogren, Olof, Gillblad, Daniel
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910296878088192
author Zec, Edvin Listo
Östman, Johan
Mogren, Olof
Gillblad, Daniel
author_facet Zec, Edvin Listo
Östman, Johan
Mogren, Olof
Gillblad, Daniel
contents Personalized decentralized learning is a promising paradigm for distributed learning, enabling each node to train a local model on its own data and collaborate with other nodes to improve without sharing any data. However, this approach poses significant privacy risks, as nodes may inadvertently disclose sensitive information about their data or preferences through their collaboration choices. In this paper, we propose Private Personalized Decentralized Learning (PPDL), a novel approach that combines secure aggregation and correlated adversarial multi-armed bandit optimization to protect node privacy while facilitating efficient node selection. By leveraging dependencies between different arms, represented by potential collaborators, we demonstrate that PPDL can effectively identify suitable collaborators solely based on aggregated models. Additionally, we show that PPDL surpasses previous non-private methods in model performance on standard benchmarks under label and covariate shift scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2301_12755
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Efficient Node Selection in Private Personalized Decentralized Learning
Zec, Edvin Listo
Östman, Johan
Mogren, Olof
Gillblad, Daniel
Machine Learning
Personalized decentralized learning is a promising paradigm for distributed learning, enabling each node to train a local model on its own data and collaborate with other nodes to improve without sharing any data. However, this approach poses significant privacy risks, as nodes may inadvertently disclose sensitive information about their data or preferences through their collaboration choices. In this paper, we propose Private Personalized Decentralized Learning (PPDL), a novel approach that combines secure aggregation and correlated adversarial multi-armed bandit optimization to protect node privacy while facilitating efficient node selection. By leveraging dependencies between different arms, represented by potential collaborators, we demonstrate that PPDL can effectively identify suitable collaborators solely based on aggregated models. Additionally, we show that PPDL surpasses previous non-private methods in model performance on standard benchmarks under label and covariate shift scenarios.
title Efficient Node Selection in Private Personalized Decentralized Learning
topic Machine Learning
url https://arxiv.org/abs/2301.12755