SALT: A Lightweight Model Adaptation Method for Closed Split Computing Environments

• URL: http://arxiv.org/abs/2506.07355v2
• Date: Sat, 14 Jun 2025 10:41:57 GMT
• Title: SALT: A Lightweight Model Adaptation Method for Closed Split Computing Environments
• Authors: Yuya Okada, Takayuki Nishio,
• Abstract summary: SALT is a lightweight model adaptation framework for Split Computing under closed constraints.<n>We introduce a compact, trainable adapter on the client side to refine latent features from the head network.<n>We demonstrate improved accuracy with lower training latency compared to fine-tuning methods.
• Score: 2.847466645223566
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose SALT (Split-Adaptive Lightweight Tuning), a lightweight model adaptation framework for Split Computing under closed constraints, where the head and tail networks are proprietary and inaccessible to users. In such closed environments, conventional adaptation methods are infeasible since they require access to model parameters or architectures. SALT addresses this challenge by introducing a compact, trainable adapter on the client side to refine latent features from the head network, enabling user-specific adaptation without modifying the original models or increasing communication overhead. We evaluate SALT on user-specific classification tasks with CIFAR-10 and CIFAR-100, demonstrating improved accuracy with lower training latency compared to fine-tuning methods. Furthermore, SALT facilitates model adaptation for robust inference over lossy networks, a common challenge in edge-cloud environments. With minimal deployment overhead, SALT offers a practical solution for personalized inference in edge AI systems under strict system constraints.

Related papers

• SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios [7.594528129456989]
  Homomorphic Encryption (HE) prevails in securing Federated Learning (FL), but suffers from high overhead and adaptation cost.<n>We propose SenseCrypt, a Sensitivity-guided selective Homomorphic EnCryption framework, to adaptively balance security and HE overhead per cross-device FL client.<n>Experiments demonstrate that SenseCrypt ensures security against the state-of-the-art inversion attacks, while achieving normal model accuracy as on IID data, and reducing training time by 58.4%-88.7% as compared to traditional HE methods.
  arXiv  Detail & Related papers  (2025-08-06T05:42:41Z)
• Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation [0.6554326244334866]
  We present an efficient and scalable Federated Learning framework tailored for real-world client adaptation in industrial settings.<n>By freezing the backbone and classifier during client adaptation on resource-constrained devices, we allow the domain adaptive linear layer to handle target domain adaptation.<n>Our framework accommodates sporadic model updates within resource-constrained environments, ensuring practical and seamless deployment.
  arXiv  Detail & Related papers  (2025-07-14T11:18:33Z)
• Adaptive Deadline and Batch Layered Synchronized Federated Learning [66.93447103966439]
  Federated learning (FL) enables collaborative model training across distributed edge devices while preserving data privacy, and typically operates in a round-based synchronous manner.<n>We propose ADEL-FL, a novel framework that jointly optimize per-round deadlines and user-specific batch sizes for layer-wise aggregation.
  arXiv  Detail & Related papers  (2025-05-29T19:59:18Z)
• Efficient Federated Split Learning for Large Language Models over Communication Networks [14.461758448289908]
  Fine-tuning pre-trained large language models (LLM) in a distributed manner poses significant challenges on resource-constrained edge devices.<n>We propose FedsLLM, a novel framework that integrates split federated learning with parameter-efficient fine-tuning techniques.
  arXiv  Detail & Related papers  (2025-04-20T16:16:54Z)
• Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing [58.56017169759816]
  We introduce a novel method in which the face anti-spoofing model can be adapted by the client itself to a target domain at test time.<n>Specifically, we develop a prototype-based base model and an optimal transport-guided adaptor.<n>In cross-domain and cross-attack settings, compared with recent methods, our method achieves average relative improvements of 19.17% in HTER and 8.58% in AUC.
  arXiv  Detail & Related papers  (2025-03-29T06:10:34Z)
• Client-Centric Federated Adaptive Optimization [78.30827455292827]
  Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private.<n>We propose Federated-Centric Adaptive Optimization, which is a class of novel federated optimization approaches.
  arXiv  Detail & Related papers  (2025-01-17T04:00:50Z)
• FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning [5.622065847054885]
  Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices.<n>We introduce a novel method called textbfFedAA, which optimize client contributions via textbfAdaptive textbfAggregation to enhance model robustness against malicious clients.
  arXiv  Detail & Related papers  (2024-02-08T10:22:12Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-08-11T09:58:47Z)
• User-Centric Federated Learning: Trading off Wireless Resources for Personalization [18.38078866145659]
  In Federated Learning (FL) systems, Statistical Heterogeneousness increases the algorithm convergence time and reduces the generalization performance. To tackle the above problems without violating the privacy constraints that FL imposes, personalized FL methods have to couple statistically similar clients without directly accessing their data. In this work, we design user-centric aggregation rules that are based on readily available gradient information and are capable of producing personalized models for each FL client. Our algorithm outperforms popular personalized FL baselines in terms of average accuracy, worst node performance, and training communication overhead.
  arXiv  Detail & Related papers  (2023-04-25T15:45:37Z)
• Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning [28.185096784982544]
  Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data. We propose a heterogeneous-aware FL framework, called FedCG, with adaptive client selection and gradient compression. Experiments on both real-world prototypes and simulations show that FedCG can provide up to 5.3$times$ speedup compared to other methods.
  arXiv  Detail & Related papers  (2022-12-19T14:19:07Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.