Lightweight User-Personalization Method for Closed Split Computing

Yuya Okada; Takayuki Nishio

cs.LGMar 16, 2026

Lightweight User-Personalization Method for Closed Split Computing

Authors: Yuya Okada, Takayuki Nishio

Organizations: School of Engineering, Institute of Science Tokyo, Tokyo 152-8550, Japan

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 & tables

Fig. 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.

Work	Primary Focus	Adaptation / Targeted Issue	Model Access Required
Neurosurgeon [ neurosurgeon ]	Split point scheduling	Latency / energy efficiency	Full
JointDNN [ jointdnn ]	Split training/inference framework	Latency / energy efficiency	Full
Split Computing & Early Exiting Survey [ sc_ee_survey ]	Survey / challenges	Research landscape	–
TinyTL [ tinytl ]	Memory-efficient fine-tuning	Task / domain shift	Full
Adapters (NLP) [ houlsby_adapters ]	Parameter-efficient transfer	Task adaptation	Full
Residual Adapters [ residual_adapters_visual_domains ]	Multi-domain adaptation	Domain shift	Full

TABLE I: Summary of related work discussed in this work and their assumptions in split computing.

Fig. 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.

Fig. 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.

Configuration Item	Details
Optimizer	Adam
Loss Function	Cross Entropy Loss (on tail network outputs)
Learning Rate	$1\mathrm{e}{-3}$
Batch Size	$128$
Training Epochs	$100$ (or until validation loss plateaus)
Activation Function	ReLU

TABLE II: Training configuration and environment used for all experiments.

Fig. 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.

Method	Adaptation Target	Parameter Access	Training Cost	Closed-Model Applicable
No Adaptation	None	–	None	✓
Head Retraining	Head Network	Full	High	$\times$
Head Fine-Tuning	Head Network	Partial	Medium	$\times$
SALT (Insertion)	Latent Features	Local Only	Medium–Low	✓
SALT (Adapter)	Latent Features	Local Only	Low	✓

TABLE III: Comparison of adaptation strategies in Split Computing.

Method	CIFAR-10				CIFAR-100
Method	Accuracy	Epochs	Comp./Comm. Latency [s]	Inf. Latency [s]	Accuracy	Epochs	Comp./Comm. Latency [s]	Inf. Latency [s]
Original	$0.881$	-	- / -	$5.3$	$0.669$	-	- / -	$1.0$
Retrain	$0.924$	$54.0$	$857.7$ / $1110.2$	$5.4$	$0.824$	$49.6$	$122.1$ / $208.3$	$1.0$
Tune	$0.920$	$26.0$	$372.3$ / $534.6$	$5.4$	$0.889$	$39.6$	$101.3$ / $166.3$	$1.0$
SALT (Insertion Adapter)	$0.934$	$25.3$	$287.6$ / $520.2$	$5.3$	$0.902$	$27.2$	$60.7$ / $114.2$	$1.0$
SALT (Residual Adapter)	$0.938$	$20.5$	$260.6$ / $421.5$	$5.3$	$0.902$	$21.2$	$54.0$ / $89.0$	$1.0$

TABLE IV: Performance Comparison of Adaptation Methods on CIFAR-10 and CIFAR-100

Fig. 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.

Fig. 6: Accuracy vs. Total Training Latency for each method on CIFAR-100. SALT maintains high accuracy with low training cost.

Fig. 7: Accuracy comparison across different split points on CIFAR-10. SALT consistently outperforms baseline methods regardless of split depth, achieving stable personalization without accessing or fine-tuning the head network.

Fig. 8: Accuracy under varying packet loss rates on CIFAR-10. While the original split model collapses under severe packet loss, SALT maintains stable and high accuracy across all loss rates without accessing the head or tail network parameters.

Fig. 9: Intermediate representations before packet loss under different loss rates. The figure shows channel-wise latent features (CH16) before feature dropping, for models trained with different packet loss rates. Higher loss rates lead to more spatially distributed representations, indicating redundancy-aware feature learning that improves robustness to packet loss.

Fig. 10: Visual comparison of inversion attack results under noise injection with and without SALT. The attacker is trained on noise-free representations and evaluated on noisy ones; reconstruction quality degrades similarly in both cases, indicating that SALT does not weaken noise-based privacy protection.

Fig. 11: Effect of noise strength on inversion attack performance (SSIM). SSIM decreases rapidly with increasing noise strength, and the nearly identical trends confirm that SALT does not degrade noise-based privacy defenses.

Fig. 12: Effect of noise strength on main-task classification accuracy. While noise injection severely degrades accuracy without adaptation, SALT maintains high accuracy across a wide range of noise strengths, demonstrating robustness to privacy-oriented perturbations.

Edge Computing

Edge computing places computation and AI near data sources to reduce latency, bandwidth use, and reliance on centralized clouds.

See all 198 papers

Unsupervised Head Network Personalization for Split Computing via Federated Learning
Oct 20, 2026Yutaro Horikawa, Takayuki NishioFederated Learning
School of Engineering, Institute of Science Tokyo, Tokyo 152-8550, Japan
TSFLora: Token-Compressed Split Fine-Tuning for Wireless Edge Networks
May 17, 2026Xianke Qiang, Zheng Chang, Li Wang +1Communication-Efficient Distributed Training Edge Computing
School of Computer Science and Engineering, UESTC, 611731 Chengdu, China · School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, 100876, China. · Center for Intelligent Networking and Communications, UESTC, 611731 Chengdu, China.
LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections (Full Version)
May 13, 2026Mert Cihangiroglu, Alessandro Pegoraro, Phillip Rieger +2Communication-Efficient Distributed Training Privacy-Preserving ML
University of Pavia · Technical University of Darmstadt

Oct 20, 2026J/K move · Enter open · S save

Unsupervised Head Network Personalization for Split Computing via Federated Learning

Yutaro Horikawa, Takayuki Nishio

School of Engineering, Institute of Science Tokyo, Tokyo 152-8550, Japan

Federated Learning

Open paper AskPDF arXiv

Split Computing (SC) is a distributed inference method designed for balancing computational load and reducing latency by partitioning a neural network into head and tail networks and deploying them across both a mobile device and a server, respectively. Due to the limited bandwidth and computational power of mobile devices, the head network is often replaced with a neural network that requires lower computational and communication resources. However, it is challenging to prepare a sufficient quantity and quality of labeled data on the mobile device side for training the replacement head network. Furthermore, the data prepared by mobile users often contains sensitive privacy information, making data aggregation difficult. In this paper, we propose a data-efficient head network training method for SC. This method utilizes federated learning and knowledge distillation to train the head network using a small amount of non-IID and unlabeled data from mobile devices, ensuring that the training datasets are not exposed. Moreover, by introducing personalization, we enhance the accuracy to levels comparable to or exceeding those of existing methods. The experimental evaluations demonstrate that, despite data constraints imposed only on our method, it achieves accuracy comparable to the baselines. Furthermore, it significantly reduces the communication requirements by 95% on mobile devices, with only a 3-5 percentage point drop in accuracy from the original model.

Abstract

Edge Computing

Explore similar work

Unsupervised Head Network Personalization for Split Computing via Federated Learning

TSFLora: Token-Compressed Split Fine-Tuning for Wireless Edge Networks

LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections (Full Version)