mlsanityData to 7 Oct 2026

Semi-Decentralized Federated Edge Learning with Data and Device Heterogeneity

arXiv 2112.10313 ↗First posted 20 Dec 2021cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Federated edge learning (FEEL) has attracted much attention as a privacy-preserving paradigm to effectively incorporate the distributed data at the network edge for training deep learning models. Nevertheless, the limited coverage of a single edge server results in an insufficient number of participated client nodes, which may impair the learning performance. In this paper, we investigate a novel framework of FEEL, namely semi-decentralized federated edge learning (SD-FEEL), where multiple edge servers are employed to collectively coordinate a large number of client nodes. By exploiting the low-latency communication among edge servers for efficient model sharing, SD-FEEL can incorporate more training data, while enjoying much lower latency compared with conventional federated learning. We detail the training algorithm for SD-FEEL with three main steps, including local model update, intra-cluster, and inter-cluster model aggregations. The convergence of this algorithm is proved on non-independent and identically distributed (non-IID) data, which also helps to reveal the effects of key parameters on the training efficiency and provides practical design guidelines. Meanwhile, the heterogeneity of edge devices may cause the straggler effect and deteriorate the convergence speed of SD-FEEL. To resolve this issue, we propose an asynchronous training algorithm with a staleness-aware aggregation scheme for SD-FEEL, of which, the convergence performance is also analyzed. The simulation results demonstrate the effectiveness and efficiency of the proposed algorithms for SD-FEEL and corroborate our analysis.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 20 Dec 2021.

Builds on

25 of 44 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
  3. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  4. 2017Federated Multi-Task Learningcited by 669
  5. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  6. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
  7. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  8. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  9. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 303
  10. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 298
  11. 2019Asynchronous Federated Optimizationcited by 264
  12. 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
13 more
  1. 2019Federated Learning over Wireless Fading Channelscited by 178
  2. 2019The Roadmap to 6G -- AI Empowered Wireless Networkscited by 150
  3. 2018D2: Decentralized Training over Decentralized Datacited by 140
  4. 2020Communication-Efficient Edge AI: Algorithms and Systemscited by 95
  5. 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
  6. 2019SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overheadcited by 82
  7. 2018Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGDcited by 76
  8. 2021Decentralized Federated Learning: Balancing Communication and Computing Costscited by 54
  9. 20216G Internet of Things: A Comprehensive Surveycited by 39
  10. 2021Quantized Federated Learning under Transmission Delay and Outage Constraintscited by 37
  11. 2021Semi-Decentralized Federated Edge Learning for Fast Convergence on Non-IID Datacited by 12
  12. 2020Multi-Level Local SGD for Heterogeneous Hierarchical Networkscited by 9
  13. 2021Asynchronous Semi-Decentralized Federated Edge Learning for Heterogeneous Clientscited by 4

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 6; 2025: 1.

12 papers.

  1. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  2. 2022Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networkingcited by 18
  3. 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learningcited by 9
  4. 2024Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clientscited by 7
  5. 2024An Empirical Study on Large Language Models in Accuracy and Robustness under Chinese Industrial Scenarioscited by 3
  6. 2023Communication-Efficient Federated Optimization over Semi-Decentralized Networkscited by 2
  7. 2024Heterogeneity-Aware Cooperative Federated Edge Learning with Adaptive Computation and Communication Compressioncited by 2
  8. 2024A Comprehensive Survey on Joint Resource Allocation Strategies in Federated Edge Learningcited by 1
  9. 2022Resource-Constrained Decentralized Federated Learning via Personalized Event-Triggeringcited by 0
  10. 2024Trust-free Personalized Decentralized Learningcited by 0
  11. 2024TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learningcited by 0
  12. 2025Towards a Distributed Federated Learning Aggregation Placement using Particle Swarm Intelligencecited by 0