Efficient Node Selection in Private Personalized Decentralized Learning
This addresses privacy concerns for nodes in distributed learning systems, though it appears incremental by building on existing personalized decentralized learning with added privacy mechanisms.
The paper tackles the privacy risks in personalized decentralized learning by proposing Private Personalized Decentralized Learning (PPDL), which uses secure aggregation and correlated adversarial multi-armed bandit optimization to protect node privacy during collaboration, and demonstrates that it surpasses non-private methods in model performance on standard benchmarks under label and covariate shift scenarios.
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.