Related papers: Private Federated Learning with Dynamic Power Control via Non-Coherent Over-the-Air Computation

Private Federated Learning with Dynamic Power Control via Non-Coherent Over-the-Air Computation

URL: http://arxiv.org/abs/2308.02881v1
Date: Sat, 5 Aug 2023 13:46:50 GMT
Title: Private Federated Learning with Dynamic Power Control via Non-Coherent Over-the-Air Computation
Authors: Anbang Zhang, Shuaishuai Guo, Shuai Liu
Abstract summary: scheme based on dynamic power control is proposed. We show that the whole scheme can mitigate the impact of the time synchronization error, channel fading and noise.
Score: 12.56727008993937
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: To further preserve model weight privacy and improve model performance in Federated Learning (FL), FL via Over-the-Air Computation (AirComp) scheme based on dynamic power control is proposed. The edge devices (EDs) transmit the signs of local stochastic gradients by activating two adjacent orthogonal frequency division multi-plexing (OFDM) subcarriers, and majority votes (MVs) at the edge server (ES) are obtained by exploiting the energy accumulation on the subcarriers. Then, we propose a dynamic power control algorithm to further offset the biased aggregation of the MV aggregation values. We show that the whole scheme can mitigate the impact of the time synchronization error, channel fading and noise. The theoretical convergence proof of the scheme is re-derived.

Related papers

Function Approximation for Reinforcement Learning Controller for Energy from Spread Waves [69.9104427437916]
Multi-generator Wave Energy Converters (WEC) must handle multiple simultaneous waves coming from different directions called spread waves. These complex devices need controllers with multiple objectives of energy capture efficiency, reduction of structural stress to limit maintenance, and proactive protection against high waves. In this paper, we explore different function approximations for the policy and critic networks in modeling the sequential nature of the system dynamics.
arXiv Detail & Related papers (2024-04-17T02:04:10Z)
Generation of C-NOT, SWAP, and C-Z Gates for Two Qubits Using Coherent and Incoherent Controls and Stochastic Optimization [56.47577824219207]
We consider a general form of the dynamics of open quantum systems determined by the Gorini-Kossakowsky-Sudarchhan-Lindblad type master equation. We analyze the control problems of generating two-qubit C-NOT, SWAP, and C-Z gates using piecewise constant controls and optimization.
arXiv Detail & Related papers (2023-12-09T17:55:47Z)
Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer [128.19212716007794]
We propose a Transformer-based Multi-Agent Actor-Critic framework (T-MAAC) to stabilize voltage in power distribution networks. In addition, we adopt a novel auxiliary-task training process tailored to the voltage control task, which improves the sample efficiency.
arXiv Detail & Related papers (2022-06-08T07:48:42Z)
Over-the-Air Federated Multi-Task Learning via Model Sparsification and Turbo Compressed Sensing [48.19771515107681]
We propose an over-the-air FMTL framework, where multiple learning tasks deployed on edge devices share a non-orthogonal fading channel under the coordination of an edge server. In OA-FMTL, the local updates of edge devices are sparsified, compressed, and then sent over the uplink channel in a superimposed fashion. We analyze the performance of the proposed OA-FMTL framework together with the M-Turbo-CS algorithm.
arXiv Detail & Related papers (2022-05-08T08:03:52Z)
Graph-based Algorithm Unfolding for Energy-aware Power Allocation in Wireless Networks [27.600081147252155]
We develop a novel graph sumable framework to maximize energy efficiency in wireless communication networks. We show the permutation training which is a desirable property for models of wireless network data. Results demonstrate its generalizability across different network topologies.
arXiv Detail & Related papers (2022-01-27T20:23:24Z)
End-to-End Learning of OFDM Waveforms with PAPR and ACLR Constraints [15.423422040627331]
We propose to use a neural network (NN) at the transmitter to learn a high-dimensional modulation scheme allowing to control the PAPR and adjacent channel leakage ratio (ACLR) The two NNs operate on top of OFDM, and are jointly optimized in and end-to-end manner using a training algorithm that enforces constraints on the PAPR and ACLR.
arXiv Detail & Related papers (2021-06-30T13:09:30Z)
Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysis [65.31074639627226]
Principal component analysis (PCA) is a technique for extracting the linear structure of a dataset. We propose the deployment of PCA over a multi-access channel based on the algorithm of gradient descent. Over-the-air aggregation is adopted to reduce the multi-access latency, giving the name over-the-air PCA.
arXiv Detail & Related papers (2021-04-20T16:28:33Z)
Cluster-Based Cooperative Digital Over-the-Air Aggregation for Wireless Federated Edge Learning [9.179817518536545]
We study a federated learning system at the wireless edge that uses over-the-air computation (AirComp) In such a system, users transmit their messages over a multi-access channel concurrently to achieve fast model aggregation. We propose an improved digital AirComp scheme to relax its requirements on the transmitters, where users perform phase correction and transmit with full power.
arXiv Detail & Related papers (2020-08-03T16:29:52Z)
Federated Learning in the Sky: Joint Power Allocation and Scheduling with UAV Swarms [98.78553146823829]
Unmanned aerial vehicle (UAV) swarms must exploit machine learning (ML) in order to execute various tasks. In this paper, a novel framework is proposed to implement distributed learning (FL) algorithms within a UAV swarm.
arXiv Detail & Related papers (2020-02-19T14:04:01Z)

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