mlsanityData to 7 Oct 2026

A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control

arXiv 2504.01752 ↗First posted 2 Apr 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables distributed devices to train a shared machine learning (ML) model collaboratively while protecting their data privacy. However, the resource-limited mobile devices suffer from intensive computation-and-communication costs of model parameters. In this paper, we observe the phenomenon that the model parameters tend to be stabilized long before convergence during training process. Based on this observation, we propose a two-timescale FL framework by joint optimization of freezing stabilized parameters and controlling transmit power for the unstable parameters to balance the energy consumption and convergence. First, we analyze the impact of model parameter freezing and unreliable transmission on the convergence rate. Next, we formulate a two-timescale optimization problem of parameter freezing percentage and transmit power to minimize the model convergence error subject to the energy budget. To solve this problem, we decompose it into parallel sub-problems and decompose each sub-problem into two different timescales problems using the Lyapunov optimization method. The optimal parameter freezing and power control strategies are derived in an online fashion. Experimental results demonstrate the superiority of the proposed scheme compared with the benchmark schemes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 2 Apr 2025.

Builds on

29 of 46 references.

References · 29

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  3. 2021Convex optimizationcited by 2,479
  4. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  5. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  6. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
  7. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  8. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
  9. 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 108
  10. 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 102
  11. 2022FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extractioncited by 102
  12. 2021Fast Federated Learning in the Presence of Arbitrary Device Unavailabilitycited by 72
17 more
  1. 2020Energy-Efficient Resource Management for Federated Edge Learning with CPU-GPU Heterogeneous Computingcited by 39
  2. 2021Quantized Federated Learning under Transmission Delay and Outage Constraintscited by 37
  3. 2018Application of Machine Learning in Wireless Networks: Key Techniques and Open Issuescited by 29
  4. 2021Low-Latency Federated Learning over Wireless Channels with Differential Privacycited by 24
  5. 2023Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reductioncited by 24
  6. 2020Energy Efficient Federated Learning over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless Transmissioncited by 22
  7. 2023Accelerating Split Federated Learning over Wireless Communication Networkscited by 16
  8. 2019Machine Intelligence at the Edge with Learning Centric Power Allocationcited by 14
  9. 2022Federated Learning and Meta Learning: Approaches, Applications, and Directionscited by 12
  10. 2022SAFARI: Sparsity enabled Federated Learning with Limited and Unreliable Communicationscited by 11
  11. 2023Adaptive Federated Pruning in Hierarchical Wireless Networkscited by 10
  12. 2024Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networkscited by 9
  13. 2022Knowledge-aided Federated Learning for Energy-limited Wireless Networkscited by 8
  14. 2023AQUILA: Communication Efficient Federated Learning with Adaptive Quantization in Device Selection Strategycited by 7
  15. 2022Client Selection for Federated Bayesian Learningcited by 4
  16. 2023Asynchronous Wireless Federated Learning with Probabilistic Client Selectioncited by 4
  17. 2023Adaptive Model Pruning and Personalization for Federated Learning over Wireless Networkscited by 2

Built on by

Not cited yet.