Optimal Resource Allocation for U-Shaped Parallel Split Learning

TL;DR

This paper introduces a U-shaped parallel split learning framework with an optimal resource allocation scheme, LSCRA, enhancing privacy and efficiency in edge network training.

Contribution

It proposes a novel parallel U-shaped split learning architecture and an optimal resource allocation algorithm, LSCRA, to improve privacy and performance in edge networks.

Findings

LSCRA effectively optimizes resource allocation.

U-shaped split learning preserves label privacy.

Performance comparable to existing split learning methods.

Abstract

Split learning (SL) has emerged as a promising approach for model training without revealing the raw data samples from the data owners. However, traditional SL inevitably leaks label privacy as the tail model (with the last layers) should be placed on the server. To overcome this limitation, one promising solution is to utilize U-shaped architecture to leave both early layers and last layers on the user side. In this paper, we develop a novel parallel U-shaped split learning and devise the optimal resource optimization scheme to improve the performance of edge networks. In the proposed framework, multiple users communicate with an edge server for SL. We analyze the end-to-end delay of each client during the training process and design an efficient resource allocation algorithm, called LSCRA, which finds the optimal computing resource allocation and split layers. Our experimental results show the effectiveness of LSCRA and that U-shaped parallel split learning can achieve a similar performance with other SL baselines while preserving label privacy. Index Terms: U-shaped network, split learning, label privacy, resource allocation, 5G/6G edge networks.