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

• URL: http://arxiv.org/abs/2504.01752v1
• Date: Wed, 02 Apr 2025 14:05:45 GMT
• Title: A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control
• Authors: Jinhao Ouyang, Yuan Liu, Hang Liu,
• Abstract summary: Federated learning (FL) enables distributed devices to train a shared machine learning (ML) model collaboratively.<n>Mobile devices suffer from intensive computation-and-communication costs of model parameters.<n>We propose a two-timescale FL framework by joint optimization of freezing stabilized parameters and controlling transmit power.
• Score: 5.933362098579029
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Biased Federated Learning under Wireless Heterogeneity [7.3716675761469945]
  Federated learning (FL) is a promising framework for computation, enabling collaborative model training without sharing private data.<n>Existing wireless computation works primarily adopt two communication strategies: (1) over-the-air (OTA) which exploits wireless signal superposition, and (2) over-the-air (OTA) which allocates resources for convergence.<n>This paper proposes novel OTA and digital FL updates that allow a structured, time-in-place bias, thereby reducing variance in FL updates.
  arXiv  Detail & Related papers  (2025-03-08T05:55:14Z)
• Mitigating Parameter Degeneracy using Joint Conditional Diffusion Model for WECC Composite Load Model in Power Systems [2.7212274374272543]
  We develop a joint conditional diffusion model-based inverse problem solver (JCDI) JCDI incorporates a joint conditioning architecture with simultaneous inputs of multi-event observations to improve parameter generalizability. Simulation studies on the WECC CLM show that the proposed JCDI effectively reduces uncertainties of degenerate parameters.
  arXiv  Detail & Related papers  (2024-11-15T18:53:08Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Online Variational Sequential Monte Carlo [49.97673761305336]
  We build upon the variational sequential Monte Carlo (VSMC) method, which provides computationally efficient and accurate model parameter estimation and Bayesian latent-state inference. Online VSMC is capable of performing efficiently, entirely on-the-fly, both parameter estimation and particle proposal adaptation.
  arXiv  Detail & Related papers  (2023-12-19T21:45:38Z)
• Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models [109.06052781040916]
  We introduce a technique to enhance the inference efficiency of parameter-shared language models. We also propose a simple pre-training technique that leads to fully or partially shared models. Results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs.
  arXiv  Detail & Related papers  (2023-10-19T15:13:58Z)
• Performance Optimization for Variable Bitwidth Federated Learning in Wireless Networks [103.22651843174471]
  This paper considers improving wireless communication and computation efficiency in federated learning (FL) via model quantization. In the proposed bitwidth FL scheme, edge devices train and transmit quantized versions of their local FL model parameters to a coordinating server, which aggregates them into a quantized global model and synchronizes the devices. We show that the FL training process can be described as a Markov decision process and propose a model-based reinforcement learning (RL) method to optimize action selection over iterations.
  arXiv  Detail & Related papers  (2022-09-21T08:52:51Z)
• Resource-Efficient and Delay-Aware Federated Learning Design under Edge Heterogeneity [10.702853653891902]
  Federated learning (FL) has emerged as a popular methodology for distributing machine learning across wireless edge devices. In this work, we consider optimizing the tradeoff between model performance and resource utilization in FL. Our proposed StoFedDelAv incorporates a localglobal model combiner into the FL computation step.
  arXiv  Detail & Related papers  (2021-12-27T22:30:15Z)
• An Artificial Neural Network-Based Model Predictive Control for Three-phase Flying Capacitor Multi-Level Inverter [2.3513645401551333]
  Model predictive control (MPC) has been used widely in power electronics due to its simple concept, fast dynamic response, and good reference tracking. It suffers from parametric uncertainties, since it relies on the mathematical model of the system to predict the optimal switching states. This paper offers a model-free control strategy on the basis of artificial neural networks (ANNs)
  arXiv  Detail & Related papers  (2021-10-15T13:54:08Z)
• Embedding Power Flow into Machine Learning for Parameter and State Estimation [4.416484585765027]
  We show how modern Machine Learning (ML) allows to resolve the iterative loop more efficiently. We extend the scheme to the case of incomplete observations, where Phasor Measurement Units are available only at the generators. Considering it from the implementation perspective, our methodology of resolving the parameter and state estimation problem can be viewed as embedding of the Power Flow (PF) solver into the training loop of the ML framework.
  arXiv  Detail & Related papers  (2021-03-26T04:16:20Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)
• Gradient Statistics Aware Power Control for Over-the-Air Federated Learning [59.40860710441232]
  Federated learning (FL) is a promising technique that enables many edge devices to train a machine learning model collaboratively in wireless networks. This paper studies the power control problem for over-the-air FL by taking gradient statistics into account.
  arXiv  Detail & Related papers  (2020-03-04T14:06:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.