# Lightweight User-Personalization Method for Closed Split Computing

arXiv: https://arxiv.org/abs/2603.14958 · HTML: https://mlsanity.com/paper/2603.14958/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach](https://mlsanity.com/paper/2102.04170/) (2021)
- [JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1801.08618/) (2018)
- [NoPeek: Information leakage reduction to share activations in distributed deep learning](https://mlsanity.com/paper/2008.09161/) (2020)
- [PockEngine: Sparse and Efficient Fine-tuning in a Pocket](https://mlsanity.com/paper/2310.17752/) (2023)
- [Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information](https://mlsanity.com/paper/2305.04146/) (2023)
- [Packet-Loss-Tolerant Split Inference for Delay-Sensitive Deep Learning in Lossy Wireless Networks](https://mlsanity.com/paper/2104.13629/) (2021)
- [Communication-oriented Model Fine-tuning for Packet-loss Resilient Distributed Inference under Highly Lossy IoT Networks](https://mlsanity.com/paper/2112.09407/) (2021)
- [Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges](https://mlsanity.com/paper/2411.18199/) (2024)
- [Neural Architecture Search for Improving Latency-Accuracy Trade-off in Split Computing](https://mlsanity.com/paper/2208.13968/) (2022)
- [Measuring and Controlling Split Layer Privacy Leakage Using Fisher Information](https://mlsanity.com/paper/2209.10119/) (2022)
- [Label Privacy in Split Learning for Large Models with Parameter-Efficient Training](https://mlsanity.com/paper/2412.16669/) (2024)
- [SALT: A Lightweight Model Adaptation Method for Closed Split Computing Environments](https://mlsanity.com/paper/2506.07355/) (2025)

## Abstract (arXiv)

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.