P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices

TL;DR

P3SL introduces a personalized split learning framework that enables heterogeneous edge devices to maintain local models and privacy levels tailored to their resources and conditions, using bi-level optimization to select split points without sharing sensitive data.

Contribution

The paper proposes a novel personalized split learning approach with bi-level optimization for resource-constrained, heterogeneous edge devices, addressing privacy and environmental variability.

Findings

Effective personalization of privacy and model customization achieved.

Bi-level optimization enables clients to select split points without sharing sensitive info.

System evaluated on diverse devices with promising results.

Abstract

Split Learning (SL) is an emerging privacy-preserving machine learning technique that enables resource constrained edge devices to participate in model training by partitioning a model into client-side and server-side sub-models. While SL reduces computational overhead on edge devices, it encounters significant challenges in heterogeneous environments where devices vary in computing resources, communication capabilities, environmental conditions, and privacy requirements. Although recent studies have explored heterogeneous SL frameworks that optimize split points for devices with varying resource constraints, they often neglect personalized privacy requirements and local model customization under varying environmental conditions. To address these limitations, we propose P3SL, a Personalized Privacy-Preserving Split Learning framework designed for heterogeneous, resource-constrained edge device systems. The key contributions of this work are twofold. First, we design a personalized sequential split learning pipeline that allows each client to achieve customized privacy protection and maintain personalized local models tailored to their computational resources, environmental conditions, and privacy needs. Second, we adopt a bi-level optimization technique that empowers clients to determine their own optimal personalized split points without sharing private sensitive information (i.e., computational resources, environmental conditions, privacy requirements) with the server. This approach balances energy consumption and privacy leakage risks while maintaining high model accuracy. We implement and evaluate P3SL on a testbed consisting of 7 devices including 4 Jetson Nano P3450 devices, 2 Raspberry Pis, and 1 laptop, using diverse model architectures and datasets under varying environmental conditions.