Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learning

TL;DR

This paper introduces P4, a decentralized method for personalized, private, and robust peer-to-peer learning in IoT devices, achieving high accuracy and resilience against attacks with minimal overhead.

Contribution

We propose P4, a lightweight decentralized algorithm that enables private client similarity detection and collaborative training, enhancing privacy and robustness in resource-constrained IoT environments.

Findings

P4 outperforms existing approaches with 5-30% higher accuracy.

It maintains robustness with up to 30% malicious clients.

Deployment on IoT devices incurs only ~7 seconds overhead.

Abstract

The growing adoption of Artificial Intelligence (AI) in Internet of Things (IoT) ecosystems has intensified the need for personalized learning methods that can operate efficiently and privately across heterogeneous, resource-constrained devices. However, enabling effective personalized learning in decentralized settings introduces several challenges, including efficient knowledge transfer between clients, protection of data privacy, and resilience against poisoning attacks. In this paper, we address these challenges by developing P4 (Personalized, Private, Peer-to-Peer) -- a method designed to deliver personalized models for resource-constrained IoT devices while ensuring differential privacy and robustness against poisoning attacks. Our solution employs a lightweight, fully decentralized algorithm to privately detect client similarity and form collaborative groups. Within each group, clients leverage differentially private knowledge distillation to co-train their models, maintaining high accuracy while ensuring robustness to the presence of malicious clients. We evaluate P4 on popular benchmark datasets using both linear and CNN-based architectures across various heterogeneity settings and attack scenarios. Experimental results show that P4 achieves 5% to 30% higher accuracy than leading differentially private peer-to-peer approaches and maintains robustness with up to 30% malicious clients. Additionally, we demonstrate its practicality by deploying it on resource-constrained devices, where collaborative training between two clients adds only ~7 seconds of overhead.