mlsanityData to 14 Oct 2026

SL-FAC: A Communication-Efficient Split Learning Framework with Frequency-Aware Compression

arXiv 2604.07316 ↗First posted 8 Apr 2026cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

The growing complexity of neural networks hinders the deployment of distributed machine learning on resource-constrained devices. Split learning (SL) offers a promising solution by partitioning the large model and offloading the primary training workload from edge devices to an edge server. However, the increasing number of participating devices and model complexity leads to significant communication overhead from the transmission of smashed data (e.g., activations and gradients), which constitutes a critical bottleneck for SL. To tackle this challenge, we propose SL-FAC, a communication-efficient SL framework comprising two key components: adaptive frequency decomposition (AFD) and frequency-based quantization compression (FQC). AFD first transforms the smashed data into the frequency domain and decomposes it into spectral components with distinct information. FQC then applies customized quantization bit widths to each component based on its spectral energy distribution. This collaborative approach enables SL-FAC to achieve significant communication reduction while strategically preserving the information most crucial for model convergence. Extensive experiments confirm the superior performance of SL-FAC for improving the training efficiency.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 8 Apr 2026.

Builds on

27 of 40 references.

References · 27

  1. 2023Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networkscited by 95
  2. 2019BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Servicescited by 68
  3. 2023Split Learning in 6G Edge Networkscited by 68
  4. 2024AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networkscited by 64
  5. 2024Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 49
  6. 2020Channel Interaction Networks for Fine-Grained Image Categorizationcited by 47
  7. 2023FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networkscited by 38
  8. 2024Hierarchical Split Federated Learning: Convergence Analysis and System Optimizationcited by 38
  9. 2023Optimal Resource Allocation for U-Shaped Parallel Split Learningcited by 33
  10. 2025HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 31
  11. 2023Reducing Communication for Split Learning by Randomized Top-k Sparsificationcited by 22
  12. 2024SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Frameworkcited by 21
15 more
  1. 2023PowerQuant: Automorphism Search for Non-Uniform Quantizationcited by 20
  2. 2024IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengerscited by 20
  3. 2023Communication-Efficient Split Learning via Adaptive Feature-Wise Compressioncited by 18
  4. 2024EasyQuant: An Efficient Data-free Quantization Algorithm for LLMscited by 17
  5. 2025HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systemscited by 15
  6. 2020Harmonic Convolutional Networks based on Discrete Cosine Transformcited by 14
  7. 2026HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Expertscited by 11
  8. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learningcited by 8
  9. 2025LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systemscited by 8
  10. 2025LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learningcited by 6
  11. 2025RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computingcited by 5
  12. 2026Conflict-Aware Client Selection for Multi-Server Federated Learningcited by 5
  13. 2024STanH : Parametric Quantization for Variable Rate Learned Image Compressioncited by 4
  14. 2026NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learningcited by 4
  15. 2026Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data Heterogeneitycited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Adaptive Joint Compression and Synchronisation in Federated Split Learning for IoT Rainfall Predictioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Quantized-Tinyllava: a new multimodal foundation model enables efficient split learning
  2. 2021Unbiased Single-scale and Multi-scale Quantizers for Distributed Optimization
  3. 2025Trustworthy Efficient Communication for Distributed Learning using LQ-SGD Algorithm
  4. 2021Learned Gradient Compression for Distributed Deep Learning
  5. 2024Beyond Throughput and Compression Ratios: Towards High End-to-end Utility of Gradient Compression
  6. 2026AutoEncoder-Compressed Parallel Split Learning for Pre-trained Model Fine-Tuning
  7. 2022Fundamental Limits of Communication Efficiency for Model Aggregation in Distributed Learning: A Rate-Distortion Approach
  8. 2026SplitLite: Low-Rank Residual Compression for Split Learning