mlsanityData to 7 Oct 2026

Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learning

arXiv 2603.09792 ↗First posted 10 Mar 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 27 references that are in the map. First posted on arXiv 10 Mar 2026.

Builds on

23 of 27 references.

References · 23

  1. 2023Mistral 7Bcited by 3,065
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  3. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  4. 2023Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networkscited by 95
  5. 2023Split Learning in 6G Edge Networkscited by 68
  6. 2024AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networkscited by 64
  7. 2024SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 60
  8. 2024Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 49
  9. 2023FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networkscited by 38
  10. 2024Hierarchical Split Federated Learning: Convergence Analysis and System Optimizationcited by 38
  11. 2025HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 30
  12. 2023Reducing Communication for Split Learning by Randomized Top-k Sparsificationcited by 22
11 more
  1. 2023Communication-Efficient Split Learning via Adaptive Feature-Wise Compressioncited by 18
  2. 2025HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systemscited by 15
  3. 2024Sums: Sniffing Unknown Multiband Signals under Low Sampling Ratescited by 12
  4. 2022Binarizing Split Learning for Data Privacy Enhancement and Computation Reductioncited by 11
  5. 2026HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Expertscited by 11
  6. 2025Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoringcited by 10
  7. 2025LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systemscited by 8
  8. 2024Federated Split Learning with Model Pruning and Gradient Quantization in Wireless Networkscited by 7
  9. 2026Conflict-Aware Client Selection for Multi-Server Federated Learningcited by 5
  10. 2024SplitFedZip: Learned Compression for Data Transfer Reduction in Split-Federated Learningcited by 4
  11. 2026Transformer-Based Multipath Congestion Control: A Decoupled Approach for Wireless Uplinkscited by 1

Built on by

Not cited yet.