Over-the-Air Federated Averaging with Limited Power and Privacy Budgets
Not on the map. Why?
Abstract (arXiv)
To jointly overcome the communication bottleneck and privacy leakage of wireless federated learning (FL), this paper studies a differentially private over-the-air federated averaging (DP-OTA-FedAvg) system with a limited sum power budget. With DP-OTA-FedAvg, the gradients are aligned by an alignment coefficient and aggregated over the air, and channel noise is employed to protect privacy. We aim to improve the learning performance by jointly designing the device scheduling, alignment coefficient, and the number of aggregation rounds of federated averaging (FedAvg) subject to sum power and privacy constraints. We first present the privacy analysis based on differential privacy (DP) to quantify the impact of the alignment coefficient on privacy preservation in each communication round. Furthermore, to study how the device scheduling, alignment coefficient, and the number of the global aggregation affect the learning process, we conduct the convergence analysis of DP-OTA-FedAvg in the cases of convex and non-convex loss functions. Based on these analytical results, we formulate an optimization problem to minimize the optimality gap of the DP-OTA-FedAvg subject to limited sum power and privacy budgets. The problem is solved by decoupling it into two sub-problems. Given the number of communication rounds, we conclude the relationship between the number of scheduled devices and the alignment coefficient, which offers a set of potential optimal solution pairs of device scheduling and the alignment coefficient. Thanks to the reduced search space, the optimal solution can be efficiently obtained. The effectiveness of the proposed policy is validated through simulations.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 50 references that are in the map. First posted on arXiv 5 May 2023.
Builds on
31 of 50 references.
References · 31
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
- 2013Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programmingcited by 716
- 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
- 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
- 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
- 2018Federated Learning via Over-the-Air Computationcited by 215
- 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
- 2017Machine Learning Models that Remember Too Muchcited by 165
- 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 108
- 2018Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learningcited by 75
19 more
- 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 72
- 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 66
- 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 62
- 2020Wireless Federated Learning with Local Differential Privacycited by 50
- 2021Optimized Power Control Design for Over-the-Air Federated Edge Learningcited by 45
- 2019The Complexity of Finding Stationary Points with Stochastic Gradient Descentcited by 34
- 2020Federated Learning for 6G Communications: Challenges, Methods, and Future Directionscited by 32
- 2021Learning Rate Optimization for Federated Learning Exploiting Over-the-air Computationcited by 27
- 2021Low-Latency Federated Learning over Wireless Channels with Differential Privacycited by 24
- 2020Energy Efficient Federated Learning over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless Transmissioncited by 22
- 2022Joint Device Selection and Power Control for Wireless Federated Learningcited by 19
- 2020Fast Convergence Algorithm for Analog Federated Learningcited by 16
- 2020Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noisecited by 14
- 2021Joint Optimization of Communications and Federated Learning Over the Aircited by 13
- 2021Federated Learning over Wireless Networks: A Band-limited Coordinated Descent Approachcited by 11
- 2021User Scheduling for Federated Learning Through Over-the-Air Computationcited by 7
- 2020Optimizing Over-the-Air Computation in IRS-Aided C-RAN Systemscited by 5
- 2021Wireless Federated Learning over MIMO Networks: Joint Device Scheduling and Beamforming Designcited by 2
- 2023Over-the-Air Federated Edge Learning with Error-Feedback One-Bit Quantization and Power Controlcited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.