mlsanityData to 14 Oct 2026

The Impact of Cut Layer Selection in Split Federated Learning

arXiv 2412.15536 ↗First posted 20 Dec 2024cs.DC cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Split Federated Learning (SFL) is a distributed machine learning paradigm that combines federated learning and split learning. In SFL, a neural network is partitioned at a cut layer, with the initial layers deployed on clients and remaining layers on a training server. There are two main variants of SFL: SFL-V1 where the training server maintains separate server-side models for each client, and SFL-V2 where the training server maintains a single shared model for all clients. While existing studies have focused on algorithm development for SFL, a comprehensive quantitative analysis of how the cut layer selection affects model performance remains unexplored. This paper addresses this gap by providing numerical and theoretical analysis of SFL performance and convergence relative to cut layer selection. We find that SFL-V1 is relatively invariant to the choice of cut layer, which is consistent with our theoretical results. Numerical experiments on four datasets and two neural networks show that the cut layer selection significantly affects the performance of SFL-V2. Moreover, SFL-V2 with an appropriate cut layer selection outperforms FedAvg on heterogeneous data.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 30 of its 49 references that are in the map. First posted on arXiv 20 Dec 2024.

Builds on

30 of 49 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  5. 2021Model-Contrastive Federated Learningcited by 766
  6. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  7. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
  8. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
  9. 2020SplitFed: When Federated Learning Meets Split Learningcited by 310
  10. 2018Distributed learning of deep neural network over multiple agentscited by 279
  11. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 163
  12. 2020Minibatch vs Local SGD for Heterogeneous Distributed Learningcited by 147
18 more
  1. 2019Detailed comparison of communication efficiency of split learning and federated learningcited by 77
  2. 2022ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learningcited by 36
  3. 2020Federated Edge Learning : Design Issues and Challengescited by 26
  4. 2023Convergence Analysis of Sequential Federated Learning on Heterogeneous Datacited by 23
  5. 2023Privacy and Efficiency of Communications in Federated Split Learningcited by 21
  6. 2021SplitAVG: A heterogeneity-aware federated deep learning method for medical imagingcited by 19
  7. 2024Convergence Analysis of Split Federated Learning on Heterogeneous Datacited by 17
  8. 2024ESFL: Efficient Split Federated Learning over Resource-Constrained Heterogeneous Wireless Devicescited by 16
  9. 2023MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulationcited by 13
  10. 2022Robust Split Federated Learning for U-shaped Medical Image Networkscited by 11
  11. 2023Communication and Storage Efficient Federated Split Learningcited by 11
  12. 2023Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learningcited by 9
  13. 2024FedUV: Uniformity and Variance for Heterogeneous Federated Learningcited by 9
  14. 2021AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learningcited by 8
  15. 2023FedSplitX: Federated Split Learning for Computationally-Constrained Heterogeneous Clientscited by 7
  16. 2024COMSPLIT: A Communication-Aware Split Learning Design for Heterogeneous IoT Platformscited by 5
  17. 2023SplitGNN: Splitting GNN for Node Classification with Heterogeneous Attentioncited by 4
  18. 2023SplitFed resilience to packet loss: Where to split, that is the questioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025Fast AI Model Partition for Split Learning over Edge Networkscited by 1
  2. 2026ASFL: An Adaptive Model Splitting and Resource Allocation Framework for Split Federated Learningcited by 1
  3. 2026Decoupled Split Learning via Auxiliary Losscited by 0
  4. 2026QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learningcited by 0
  5. 2026BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gradient Leakagecited by 0
  6. 2026Unveiling the Depth-Performance Dilemma in Split-Federated Fine-tuning of LLMscited by 0