Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learning

• URL: http://arxiv.org/abs/2603.09792v2
• Date: Wed, 18 Mar 2026 07:37:48 GMT
• Title: Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learning
• Abstract summary: Split learning (SL) transfers most of the training workload to the server.<n>This incurs significant communication overhead when a large number of client devices are involved.<n>We propose an adaptive channel pruning-aided SL (ACP-SL) scheme.
• Score: 30.881311483100575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Split learning (SL) transfers most of the training workload to the server, which alleviates computational burden on client devices. However, the transmission of intermediate feature representations, referred to as smashed data, incurs significant communication overhead, particularly when a large number of client devices are involved. To address this challenge, we propose an adaptive channel pruning-aided SL (ACP-SL) scheme. In ACP-SL, a label-aware channel importance scoring (LCIS) module is designed to generate channel importance scores, distinguishing important channels from less important ones. Based on these scores, an adaptive channel pruning (ACP) module is developed to prune less important channels, thereby compressing the corresponding smashed data and reducing the communication overhead. Experimental results show that ACP-SL consistently outperforms benchmark schemes in test accuracy. Furthermore, it reaches a target test accuracy in fewer training rounds, thereby reducing communication overhead.

Related papers

• BASC : Behavior-Aligned Quantization and Pruning for Low-Bit Spiking Neural Networks [6.5713207503171285]
  Spiking Neural Networks (SNNs) encode information through binary spikes and compute in an event-driven manner.<n>High-performance SNNs incur substantial memory and timestep-wise costs that hinder deployment on resource-constrained devices.<n>We propose Behavior-Aligned SNN Compression (BASC), a unified framework with two lightweight modules.
  arXiv  Detail & Related papers  (2026-08-12T03:39:24Z)
• Channel-Aware Probing for Multi-Channel Imaging [9.507520646516719]
  Training and evaluating vision encoders on Multi-Channel Imaging (MCI) data remains challenging.<n>ChannelAware Probing (CAP) exploits intrinsic inter-channel diversity by controlling feature flow at both encoder and probe levels.
  arXiv  Detail & Related papers  (2026-02-13T08:03:27Z)
• Integrated Sensing, Communication, and Computation for Over-the-Air Federated Edge Learning [52.904670248426626]
  This paper studies an over-the-air federated edge learning (Air-FEEL) system with integrated sensing, communication, and computation.<n>We derive a low-complexity I SCC algorithm by alternately optimizing the batch size control and the network resource allocation.
  arXiv  Detail & Related papers  (2025-08-21T02:46:46Z)
• SL-ACC: A Communication-Efficient Split Learning Framework with Adaptive Channel-wise Compression [25.47831071744755]
  Split learning (SL) offers a promising solution by offloading the primary computing load from edge devices to a server.<n>As the number of participating devices increases, the transmission of excessive smashed data becomes a major bottleneck for SL.<n>We propose a communication-efficient SL framework, named SL-ACC, which comprises two key components.
  arXiv  Detail & Related papers  (2025-08-18T15:02:10Z)
• Federated Split Learning with Improved Communication and Storage Efficiency [9.277834710955766]
  Federated learning (FL) is one of the popular distributed machine learning (ML) solutions but incurs significant communication and computation costs at edge devices.<n>This paper proposes a novel communication and storage efficient federated split learning method, CSE-FSL, which utilizes an auxiliary network to locally update the clients while keeping a single model at the server.
  arXiv  Detail & Related papers  (2025-07-21T17:21:16Z)
• SignSGD with Federated Voting [69.06621279967865]
  SignSGD with majority voting (signSGD-MV) is an effective distributed learning algorithm that can significantly reduce communication costs by one-bit quantization. We propose a novel signSGD with textitfederated voting (signSGD-FV) The idea of federated voting is to exploit learnable weights to perform weighted majority voting. We demonstrate that the proposed signSGD-FV algorithm has a theoretical convergence guarantee even when edge devices use heterogeneous mini-batch sizes.
  arXiv  Detail & Related papers  (2024-03-25T02:32:43Z)
• Communication and Storage Efficient Federated Split Learning [19.369076939064904]
  Federated Split Learning preserves the parallel model training principle of FL. Server has to maintain separate models for every client, resulting in a significant computation and storage requirement. This paper proposes a communication and storage efficient federated and split learning strategy.
  arXiv  Detail & Related papers  (2023-02-11T04:44:29Z)
• Age of Information in Deep Learning-Driven Task-Oriented Communications [78.84264189471936]
  This paper studies the notion of age in task-oriented communications that aims to execute a task at a receiver utilizing the data at its transmitter. The transmitter-receiver operations are modeled as an encoder-decoder pair of deep neural networks (DNNs) that are jointly trained.
  arXiv  Detail & Related papers  (2023-01-11T04:15:51Z)
• Match to Win: Analysing Sequences Lengths for Efficient Self-supervised Learning in Speech and Audio [19.865050806327147]
  Self-supervised learning has proven vital in speech and audio-related applications. This paper provides the first empirical study of SSL pre-training for different specified sequence lengths. We find that training on short sequences can dramatically reduce resource costs while retaining a satisfactory performance for all tasks.
  arXiv  Detail & Related papers  (2022-09-30T16:35:42Z)
• Disentangled Representation Learning for RF Fingerprint Extraction under Unknown Channel Statistics [77.13542705329328]
  We propose a framework of disentangled representation learning(DRL) that first learns to factor the input signals into a device-relevant component and a device-irrelevant component via adversarial learning. The implicit data augmentation in the proposed framework imposes a regularization on the RFF extractor to avoid the possible overfitting of device-irrelevant channel statistics. Experiments validate that the proposed approach, referred to as DR-RFF, outperforms conventional methods in terms of generalizability to unknown complicated propagation environments.
  arXiv  Detail & Related papers  (2022-08-04T15:46:48Z)
• Model-based Deep Learning Receiver Design for Rate-Splitting Multiple Access [65.21117658030235]
  This work proposes a novel design for a practical RSMA receiver based on model-based deep learning (MBDL) methods. The MBDL receiver is evaluated in terms of uncoded Symbol Error Rate (SER), throughput performance through Link-Level Simulations (LLS) and average training overhead. Results reveal that the MBDL outperforms by a significant margin the SIC receiver with imperfect CSIR.
  arXiv  Detail & Related papers  (2022-05-02T12:23:55Z)
• You Only Need End-to-End Training for Long-Tailed Recognition [8.789819609485225]
  Cross-entropy loss tends to produce highly correlated features on imbalanced data. We propose two novel modules, Block-based Relatively Balanced Batch Sampler (B3RS) and Batch Embedded Training (BET) Experimental results on the long-tailed classification benchmarks, CIFAR-LT and ImageNet-LT, demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2021-12-11T11:44:09Z)
• CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization [61.71504948770445]
  We propose a novel channel pruning method via Class-Aware Trace Ratio Optimization (CATRO) to reduce the computational burden and accelerate the model inference. We show that CATRO achieves higher accuracy with similar cost or lower cost with similar accuracy than other state-of-the-art channel pruning algorithms. Because of its class-aware property, CATRO is suitable to prune efficient networks adaptively for various classification subtasks, enhancing handy deployment and usage of deep networks in real-world applications.
  arXiv  Detail & Related papers  (2021-10-21T06:26:31Z)
• FedRec: Federated Learning of Universal Receivers over Fading Channels [92.15358738530037]
  We propose a neural network-based symbol detection technique for downlink fading channels. Multiple users collaborate to jointly learn a universal data-driven detector, hence the name FedRec. The performance of the resulting receiver is shown to approach the MAP performance in diverse channel conditions without requiring knowledge of the fading statistics.
  arXiv  Detail & Related papers  (2020-11-14T11:29:55Z)

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.