Optimal Resource Allocation for U-Shaped Parallel Split Learning
This work addresses privacy concerns for data owners in edge networks, though it is incremental as it builds on existing split learning methods with a U-shaped architecture.
The paper tackles the problem of label privacy leakage in traditional split learning by proposing a U-shaped parallel split learning framework, and it develops an optimal resource allocation algorithm (LSCRA) that achieves similar performance to other baselines while preserving privacy.
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.