mlsanityData to 7 Oct 2026

Detailed comparison of communication efficiency of split learning and federated learning

arXiv 1909.09145 ↗First posted 18 Sep 2019cs.LG cs.DC stat.MLcited by 76

Not on the map. Why?

Abstract (arXiv)

We compare communication efficiencies of two compelling distributed machine learning approaches of split learning and federated learning. We show useful settings under which each method outperforms the other in terms of communication efficiency. We consider various practical scenarios of distributed learning setup and juxtapose the two methods under various real-life scenarios. We consider settings of small and large number of clients as well as small models (1M - 6M parameters), large models (10M - 200M parameters) and very large models (1 Billion-100 Billion parameters). We show that increasing number of clients or increasing model size favors split learning setup over the federated while increasing the number of data samples while keeping the number of clients or model size low makes federated learning more communication efficient.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 16; 2023: 14; 2024: 19; 2025: 8; 2026: 6.

76 papers.

Sort:

By area:

  1. 2021Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modelingcited by 69
  2. 2022Vertical Federated Learning: Challenges, Methodologies and Experimentscited by 55
  3. 2024Tiny Machine Learning: Progress and Futurescited by 40
  4. 2021FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Datacited by 31
  5. 2023Split-and-Denoise: Protect large language model inference with local differential privacycited by 30
  6. 2022A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learningcited by 28
  7. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  8. 2021Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Thingscited by 20
  9. 2021SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learningcited by 20
  10. 2022A Survey on Over-the-Air Computationcited by 19
  11. 2021Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthinesscited by 15
  12. 2022Similarity-based Label Inference Attack against Training and Inference of Split Learningcited by 15
38 more
  1. 2023Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learningcited by 15
  2. 2022Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directionscited by 14
  3. 2024Synergizing Foundation Models and Federated Learning: A Surveycited by 14
  4. 2022Differentially Private CutMix for Split Learning with Vision Transformercited by 13
  5. 2021Communication and Computation Reduction for Split Learning using Asynchronous Trainingcited by 11
  6. 2022Binarizing Split Learning for Data Privacy Enhancement and Computation Reductioncited by 11
  7. 2022Robust Split Federated Learning for U-shaped Medical Image Networkscited by 11
  8. 2021Towards Representation Identical Privacy-Preserving Graph Neural Network via Split Learningcited by 10
  9. 2021Splitfed learning without client-side synchronization: Analyzing client-side split network portion size to overall performancecited by 10
  10. 2023Passive Inference Attacks on Split Learning via Adversarial Regularizationcited by 9
  11. 2021AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learningcited by 8
  12. 2023Vertical Federated Learning: Taxonomies, Threats, and Prospectscited by 8
  13. 2023Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiencycited by 8
  14. 2025SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)cited by 7
  15. 2022CDKT-FL: Cross-Device Knowledge Transfer using Proxy Dataset in Federated Learningcited by 6
  16. 2023Split Without a Leak: Reducing Privacy Leakage in Split Learningcited by 6
  17. 2024The Impact of Cut Layer Selection in Split Federated Learningcited by 6
  18. 2022LSTMSPLIT: Effective SPLIT Learning based LSTM on Sequential Time-Series Datacited by 5
  19. 2023Distributed Machine Learning for UAV Swarms: Computing, Sensing, and Semanticscited by 5
  20. 2024COMSPLIT: A Communication-Aware Split Learning Design for Heterogeneous IoT Platformscited by 5
  21. 2021Homogeneous Learning: Self-Attention Decentralized Deep Learningcited by 4
  22. 2022Split-U-Net: Preventing Data Leakage in Split Learning for Collaborative Multi-Modal Brain Tumor Segmentationcited by 4
  23. 2023SplitGNN: Splitting GNN for Node Classification with Heterogeneous Attentioncited by 4
  24. 2023SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detectioncited by 4
  25. 2024Multiple Access in the Era of Distributed Computing and Edge Intelligencecited by 4
  26. 2024Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splittingcited by 4
  27. 2022UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenescited by 3
  28. 2023Digital Twin-Assisted Knowledge Distillation Framework for Heterogeneous Federated Learningcited by 3
  29. 2023PFSL: Personalized & Fair Split Learning with Data & Label Privacy for thin clientscited by 3
  30. 2023Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computingcited by 3
  31. 2024FedBaF: Federated Learning Aggregation Biased by a Foundation Modelcited by 3
  32. 2025Federated Split Learning with Improved Communication and Storage Efficiencycited by 3
  33. 2021Vulnerability Due to Training Order in Split Learningcited by 2
  34. 2022PiPar: Pipeline Parallelism for Collaborative Machine Learningcited by 2
  35. 2024SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustmentscited by 2
  36. 2024Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMixcited by 2
  37. 2024SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problemscited by 2
  38. 2024Training on Fake Labels: Mitigating Label Leakage in Split Learning via Secure Dimension Transformationcited by 2

50 most cited of 76 All 76 (JSON)