Lightweight User-Personalization Method for Closed Split Computing

Abstract

Split Computing enables collaborative inference between edge devices and the cloud by partitioning a deep neural network into an edge-side head and a server-side tail, reducing latency and limiting exposure of raw input data. However, inference performance often degrades in practical deployments due to user-specific data distribution shifts, unreliable communication, and privacy-oriented perturbations, especially in closed environments where model architectures and parameters are inaccessible. To address this challenge, we propose SALT (Split-Adaptive Lightweight Tuning), a lightweight adaptation framework for closed Split Computing systems. SALT introduces a compact client-side adapter that refines intermediate representations produced by a frozen head network, enabling effective model adaptation without modifying the head or tail networks or increasing communication overhead. By modifying only the training conditions, SALT supports multiple adaptation objectives, including user personalization, communication robustness, and privacy-aware inference. Experiments using ResNet-18 on CIFAR-10 and CIFAR-100 show that SALT achieves higher accuracy than conventional retraining and fine-tuning while significantly reducing training cost. On CIFAR-10, SALT improves personalized accuracy from 88.1% to 93.8% while reducing training latency by more than 60%. SALT also maintains over 90% accuracy under 75% packet loss and preserves high accuracy (about 88% at sigma = 1.0) under noise injection. These results demonstrate that SALT provides an efficient and practical adaptation framework for real-world Split Computing systems.

Figures (12)

• Figure 1: Overview of practical challenges in Split Computing. Client devices execute a fixed head network and transmit intermediate representations to a server-side tail network under heterogeneous conditions. User-specific data distributions and varying communication quality can directly degrade inference performance, while transmitted representations may also be exposed to privacy threats such as inversion attacks in real-world edge--cloud systems.
• Figure 2: Architecture of SALT, where a trainable adapter applies a correction to the latent feature produced by a frozen head network. The adapted feature is perturbed by noise and forwarded to a frozen tail network on the server. Only the adapter parameters are updated during training.
• Figure 3: Definition of split points in ResNet-18. The head network consists of the layers before the selected split point, while the tail network includes the remaining layers. We consider four split locations: BeforeBlock1, AfterBlock1, AfterBlock2, and AfterBlock3.
• Figure 4: Illustration of the adaptation setting. While the model is pre-trained on a complete dataset, only a subset of these classes is used to simulate user-specific data.
• Figure 5: Accuracy vs. Total Training Latency for each method on CIFAR-10. SALT maintains high accuracy with low training cost. Error bars indicate $95\%$ confidence intervals over 10 trials.