A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Scheduling and Power Control for Wireless Multicast Systems via Deep Reinforcement Learning
Multicasting in wireless systems is a natural way to exploit the redundancy in user requests in a Content Centric Network. Power control and optimal scheduling can significantly improve the wireless multicast network's p…
Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Scheduling+1Edge Deep Learning Enabled Freezing of Gait Detection in Parkinson's Patients
This paper presents the design of a wireless sensor network for detecting and alerting the freezing of gait (FoG) symptoms in patients with Parkinson's disease. Three sensor nodes, each integrating a 3-axis accelerometer…
Deep LearningLearning to Transmit with Provable Guarantees in Wireless Federated Learning
We propose a novel data-driven approach to allocate transmit power for federated learning (FL) over interference-limited wireless networks. The proposed method is useful in challenging scenarios where the wireless channe…
Federated LearningCommunication-Learning Co-Design for Differentially Private Over-the-Air Federated Distillation
The ever-growing learning model size nowadays challenges the communication efficiency and privacy preservation of the traditional federated learning (FL). In this paper, we propose a novel differentially private (DP) ove…
Federated LearningPower Allocation for Wireless Federated Learning using Graph Neural Networks
We propose a data-driven approach for power allocation in the context of federated learning (FL) over interference-limited wireless networks. The power policy is designed to maximize the transmitted information during th…
Federated Learning