mlsanityData to 7 Oct 2026

Semi-Synchronous Personalized Federated Learning over Mobile Edge Networks

arXiv 2209.13115 ↗First posted 27 Sep 2022cs.LG cs.NIcited by 5

Not on the map. Why?

Abstract (arXiv)

Personalized Federated Learning (PFL) is a new Federated Learning (FL) approach to address the heterogeneity issue of the datasets generated by distributed user equipments (UEs). However, most existing PFL implementations rely on synchronous training to ensure good convergence performances, which may lead to a serious straggler problem, where the training time is heavily prolonged by the slowest UE. To address this issue, we propose a semi-synchronous PFL algorithm, termed as Semi-Synchronous Personalized FederatedAveraging (PerFedS2), over mobile edge networks. By jointly optimizing the wireless bandwidth allocation and UE scheduling policy, it not only mitigates the straggler problem but also provides convergent training loss guarantees. We derive an upper bound of the convergence rate of PerFedS2 in terms of the number of participants per global round and the number of rounds. On this basis, the bandwidth allocation problem can be solved using analytical solutions and the UE scheduling policy can be obtained by a greedy algorithm. Experimental results verify the effectiveness of PerFedS2 in saving training time as well as guaranteeing the convergence of training loss, in contrast to synchronous and asynchronous PFL algorithms.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 20 of its 41 references that are in the map. First posted on arXiv 27 Sep 2022.

Builds on

20 of 41 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2018LEAF: A Benchmark for Federated Settingscited by 780
  5. 2020The Future of Digital Health with Federated Learningcited by 625
  6. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  7. 2020Adaptive Personalized Federated Learningcited by 353
  8. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  9. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
  10. 2021Personalized Federated Learning using Hypernetworkscited by 210
  11. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
  12. 2019On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithmscited by 132
8 more
  1. 2015Asynchronous Parallel Stochastic Gradient for Nonconvex Optimizationcited by 115
  2. 2021Asynchronous Federated Learning on Heterogeneous Devices: A Surveycited by 93
  3. 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
  4. 2019SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overheadcited by 82
  5. 2021Personalized Federated Learning with Gaussian Processescited by 76
  6. 2021Fast-adapting and Privacy-preserving Federated Recommender Systemcited by 30
  7. 2021Semi-Synchronous Federated Learning for Energy-Efficient Training and Accelerated Convergence in Cross-Silo Settingscited by 11
  8. 2021CSAFL: A Clustered Semi-Asynchronous Federated Learning Frameworkcited by 10

Built on by

Cited by year

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

5 papers.

  1. 2023Hierarchical Personalized Federated Learning Over Massive Mobile Edge Computing Networkscited by 7
  2. 2024Dynamic Scheduling for Vehicle-to-Vehicle Communications Enhanced Federated Learningcited by 3
  3. 2025Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Schedulingcited by 1
  4. 2025Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learningcited by 0
  5. 2025Accelerating Wireless Distributed Learning via Hybrid Split and Federated Learning Optimizationcited by 0