Private Node Selection in Personalized Decentralized Learning

01/30/2023
by   Edvin Listo Zec, et al.
0

In this paper, we propose a novel approach for privacy-preserving node selection in personalized decentralized learning, which we refer to as Private Personalized Decentralized Learning (PPDL). Our method mitigates the risk of inference attacks through the use of secure aggregation while simultaneously enabling efficient identification of collaborators. This is achieved by leveraging adversarial multi-armed bandit optimization that exploits dependencies between the different arms. Through comprehensive experimentation on various benchmarks under label and covariate shift, we demonstrate that our privacy-preserving approach outperforms previous non-private methods in terms of model performance.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset