mlsanityData to 14 Oct 2026

AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devices

arXiv 2312.10935 ↗First posted 18 Dec 2023cs.DC cs.AI cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) has achieved significant achievements recently, enabling collaborative model training on distributed data over edge devices. Iterative gradient or model exchanges between devices and the centralized server in the standard FL paradigm suffer from severe efficiency bottlenecks on the server. While enabling collaborative training without a central server, existing decentralized FL approaches either focus on the synchronous mechanism that deteriorates FL convergence or ignore device staleness with an asynchronous mechanism, resulting in inferior FL accuracy. In this paper, we propose an Asynchronous Efficient Decentralized FL framework, i.e., AEDFL, in heterogeneous environments with three unique contributions. First, we propose an asynchronous FL system model with an efficient model aggregation method for improving the FL convergence. Second, we propose a dynamic staleness-aware model update approach to achieve superior accuracy. Third, we propose an adaptive sparse training method to reduce communication and computation costs without significant accuracy degradation. Extensive experimentation on four public datasets and four models demonstrates the strength of AEDFL in terms of accuracy (up to 16.3% higher), efficiency (up to 92.9% faster), and computation costs (up to 42.3% lower).

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 46 of its 74 references that are in the map. First posted on arXiv 18 Dec 2023.

Builds on

46 of 74 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  6. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  7. 2019Towards Federated Learning at Scale: System Designcited by 832
  8. 2019Deep Double Descent: Where Bigger Models and More Data Hurtcited by 672
  9. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  10. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
  11. 2019PyHessian: Neural Networks Through the Lens of the Hessiancited by 292
  12. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 292
34 more
  1. 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 204
  2. 2021Federated Learning for Smart Healthcare: A Surveycited by 184
  3. 2019Privacy-preserving Federated Brain Tumour Segmentationcited by 169
  4. 2014EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimizationcited by 160
  5. 2017Asynchronous Decentralized Parallel Stochastic Gradient Descentcited by 159
  6. 2018Stochastic Gradient Push for Distributed Deep Learningcited by 152
  7. 2020Federated Visual Classification with Real-World Data Distributioncited by 128
  8. 2020Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regimecited by 95
  9. 2021Papaya: Practical, Private, and Scalable Federated Learningcited by 90
  10. 2019SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overheadcited by 82
  11. 2016Decentralized Collaborative Learning of Personalized Models over Networkscited by 76
  12. 2020Understanding Double Descent Requires a Fine-Grained Bias-Variance Decompositioncited by 76
  13. 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
  14. 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 66
  15. 2023Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimizationcited by 65
  16. 2021Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocationcited by 56
  17. 2021Exponential Graph is Provably Efficient for Decentralized Deep Trainingcited by 56
  18. 2021Decentralized Federated Learning: Balancing Communication and Computing Costscited by 55
  19. 2021Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Bettercited by 55
  20. 2021Hessian-Aware Pruning and Optimal Neural Implantcited by 45
  21. 2015Staleness-aware Async-SGD for Distributed Deep Learningcited by 43
  22. 2022Topology-aware Generalization of Decentralized SGDcited by 38
  23. 2023FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Updatecited by 32
  24. 2022Achieving Personalized Federated Learning with Sparse Local Modelscited by 31
  25. 2021Efficient Device Scheduling with Multi-Job Federated Learningcited by 29
  26. 2022FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Servercited by 29
  27. 2021Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneitycited by 27
  28. 2022Accelerated Federated Learning with Decoupled Adaptive Optimizationcited by 23
  29. 2021Decentralized Federated Learning for UAV Networks: Architecture, Challenges, and Opportunitiescited by 22
  30. 2022FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneitycited by 20
  31. 2022Multi-Job Intelligent Scheduling with Cross-Device Federated Learningcited by 20
  32. 2021HeterPS: Distributed Deep Learning With Reinforcement Learning Based Scheduling in Heterogeneous Environmentscited by 15
  33. 2023Distributed and Deep Vertical Federated Learning with Big Datacited by 10
  34. 2022Asynchronous Decentralized Federated Learning for Collaborative Fault Diagnosis of PV Stationscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 6; 2025: 6; 2026: 2.

15 papers.

Sort:

By area:

  1. 2024Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directionscited by 13
  2. 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11
  3. 2023Efficient Asynchronous Federated Learning with Sparsification and Quantizationcited by 9
  4. 2024Enhancing Trust and Privacy in Distributed Networks: A Comprehensive Survey on Blockchain-based Federated Learningcited by 9
  5. 2025Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustnesscited by 8
  6. 2024Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Datacited by 6
  7. 2024Fisher Information-based Efficient Curriculum Federated Learning with Large Language Modelscited by 6
  8. 2024Review of Mathematical Optimization in Federated Learningcited by 3
  9. 2025SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignmentcited by 3
  10. 2025FedEL: Federated Elastic Learning for Heterogeneous Devicescited by 3
  11. 2025Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learningcited by 2
  12. 2025Argus: Federated Non-convex Bilevel Learning over 6G Space-Air-Ground Integrated Networkcited by 2
3 more
  1. 2025Efficient Federated Learning with Heterogeneous Data and Adaptive Dropoutcited by 2
  2. 2026Model-Consistent Byzantine-Resilient Decentralized Federated Learning for Collaborative Missionscited by 1
  3. 2026Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregationcited by 0