mlsanityData to 7 Oct 2026

AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks

arXiv 2403.13101 ↗First posted 19 Mar 2024cs.LG cs.AI cs.DCcited by 64

Not on the map. Why?

Abstract (arXiv)

The increasing complexity of deep neural networks poses significant barriers to democratizing them to resource-limited edge devices. To address this challenge, split federated learning (SFL) has emerged as a promising solution by of floading the primary training workload to a server via model partitioning while enabling parallel training among edge devices. However, although system optimization substantially influences the performance of SFL under resource-constrained systems, the problem remains largely uncharted. In this paper, we provide a convergence analysis of SFL which quantifies the impact of model splitting (MS) and client-side model aggregation (MA) on the learning performance, serving as a theoretical foundation. Then, we propose AdaptSFL, a novel resource-adaptive SFL framework, to expedite SFL under resource-constrained edge computing systems. Specifically, AdaptSFL adaptively controls client-side MA and MS to balance communication-computing latency and training convergence. Extensive simulations across various datasets validate that our proposed AdaptSFL framework takes considerably less time to achieve a target accuracy than benchmarks, demonstrating the effectiveness of the proposed strategies.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 35 of its 77 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

35 of 77 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  5. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  6. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 496
  7. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  8. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  9. 2017Don't Decay the Learning Rate, Increase the Batch Sizecited by 313
  10. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  11. 2018Don't Use Large Mini-Batches, Use Local SGDcited by 201
  12. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
23 more
  1. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
  2. 2019On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimizationcited by 178
  3. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 104
  4. 2021Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applicationscited by 96
  5. 2023Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networkscited by 95
  6. 2018Towards an Intelligent Edge: Wireless Communication Meets Machine Learningcited by 94
  7. 2017On the convergence properties of a K-step averaging stochastic gradient descent algorithm for nonconvex optimizationcited by 91
  8. 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
  9. 2023Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunitiescited by 89
  10. 2022Split Learning over Wireless Networks: Parallel Design and Resource Managementcited by 74
  11. 2023Split Learning in 6G Edge Networkscited by 68
  12. 2015Perturbed Iterate Analysis for Asynchronous Stochastic Optimizationcited by 67
  13. 2023FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networkscited by 38
  14. 2022Faster Adaptive Federated Learningcited by 35
  15. 2023Optimal Resource Allocation for U-Shaped Parallel Split Learningcited by 33
  16. 2024Collaborative Perception for Connected and Autonomous Driving: Challenges, Possible Solutions and Opportunitiescited by 32
  17. 2021Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learningcited by 22
  18. 2023Adaptive Communications in Collaborative Perception with Domain Alignment for Autonomous Drivingcited by 19
  19. 2022Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networkingcited by 18
  20. 2024D2-JSCC: Digital Deep Joint Source-channel Coding for Semantic Communicationscited by 18
  21. 2019On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimizationcited by 14
  22. 2022Low-latency Federated Learning with DNN Partition in Distributed Industrial IoT Networkscited by 13
  23. 2022Actions at the Edge: Jointly Optimizing the Resources in Multi-access Edge Computingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 18; 2025: 29; 2026: 17.

64 papers.

Sort:

By area:

  1. 2024Mobile Edge Intelligence for Large Language Models: A Contemporary Surveycited by 125
  2. 2024SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 60
  3. 2024Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 49
  4. 2024AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learningcited by 40
  5. 2024Hierarchical Split Federated Learning: Convergence Analysis and System Optimizationcited by 38
  6. 2025HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 30
  7. 2024FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Datacited by 25
  8. 2025LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networkscited by 22
  9. 2024SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Frameworkcited by 21
  10. 2024IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengerscited by 20
  11. 2024IFViT: Interpretable Fixed-Length Representation for Fingerprint Matching via Vision Transformercited by 16
  12. 2025HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systemscited by 15
38 more
  1. 2024SATSense: Multi-Satellite Collaborative Framework for Spectrum Sensingcited by 14
  2. 2026Multimodal Multi-Agent Empowered Legal Judgment Predictioncited by 14
  3. 2024CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perceptioncited by 13
  4. 2026HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Expertscited by 11
  5. 2025Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoringcited by 10
  6. 2025LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systemscited by 8
  7. 2024Federated Split Learning with Model Pruning and Gradient Quantization in Wireless Networkscited by 7
  8. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learningcited by 7
  9. 2025Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attackscited by 7
  10. 2025FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimationcited by 7
  11. 2024An Efficient Privacy-aware Split Learning Framework for Satellite Communicationscited by 6
  12. 2025SL-ACC: A Communication-Efficient Split Learning Framework with Adaptive Channel-wise Compressioncited by 6
  13. 2025LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learningcited by 6
  14. 2025Rethinking Membership Inference Attacks Against Transfer Learningcited by 5
  15. 2025Revisiting Outage for Edge Inference Systemscited by 5
  16. 2026Conflict-Aware Client Selection for Multi-Server Federated Learningcited by 5
  17. 2024Privacy-preserving Universal Adversarial Defense for Black-box Modelscited by 3
  18. 2025Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generationcited by 3
  19. 2024Channel-Aware Throughput Maximization for Cooperative Data Fusion in CAVcited by 2
  20. 2025Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edgecited by 2
  21. 2025Collaborative Split Federated Learning with Parallel Training and Aggregationcited by 2
  22. 2025A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observationcited by 2
  23. 2025Sample Efficient Experience Replay in Non-stationary Environmentscited by 2
  24. 2026Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learningcited by 2
  25. 2024t-READi: Transformer-Powered Robust and Efficient Multimodal Inference for Autonomous Drivingcited by 1
  26. 2024LoLaFL: Low-Latency Federated Learning via Forward-only Propagationcited by 1
  27. 2025Secure Resource Allocation via Constrained Deep Reinforcement Learningcited by 1
  28. 2025SFL-LEO: Asynchronous Split-Federated Learning Design for LEO Satellite-Ground Network Frameworkcited by 1
  29. 2025Efficient Split Federated Learning for Large Language Models over Communication Networkscited by 1
  30. 2025Intra-DP: A High Performance Collaborative Inference System for Mobile Edge Computingcited by 1
  31. 2025FlexP-SFT: A Flexible Aggregation-Free Framework for On-Device Personalized Split Federated Fine-Tuning of LLMscited by 1
  32. 2025Bayes-Split-Edge: Bayesian Optimization for Constrained Collaborative Inference in Wireless Edge Systemscited by 1
  33. 2025Enabling Near-realtime Remote Sensing via Satellite-Ground Collaboration of Large Vision-Language Modelscited by 1
  34. 2025CycleSL: Server-Client Cyclical Update Driven Scalable Split Learningcited by 1
  35. 2026ASFL: An Adaptive Model Splitting and Resource Allocation Framework for Split Federated Learningcited by 1
  36. 2026SL-FAC: A Communication-Efficient Split Learning Framework with Frequency-Aware Compressioncited by 1
  37. 2026Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classificationcited by 1
  38. 2024Tracing Human Stress from Physiological Signals using UWB Radarcited by 0

50 most cited of 64 All 64 (JSON)