# Low-Latency Federated Learning over Wireless Channels with Differential Privacy

arXiv: https://arxiv.org/abs/2106.13039 · HTML: https://mlsanity.com/paper/2106.13039/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 20 Jun 2021.

## Builds on (most cited first, 25 of 25)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Adaptive Federated Learning in Resource Constrained Edge Computing Systems](https://mlsanity.com/paper/1804.05271/) (2018)
- [A Joint Learning and Communications Framework for Federated Learning over Wireless Networks](https://mlsanity.com/paper/1909.07972/) (2019)
- [Scheduling Policies for Federated Learning in Wireless Networks](https://mlsanity.com/paper/1908.06287/) (2019)
- [One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysis](https://mlsanity.com/paper/2001.05713/) (2020)
- [Reliable Federated Learning for Mobile Networks](https://mlsanity.com/paper/1910.06837/) (2019)
- [Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning](https://mlsanity.com/paper/2007.07174/) (2020)
- [Convergence Time Optimization for Federated Learning over Wireless Networks](https://mlsanity.com/paper/2001.07845/) (2020)
- [Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanism](https://mlsanity.com/paper/1911.05642/) (2019)
- [Combinatorial Sleeping Bandits with Fairness Constraints](https://mlsanity.com/paper/1901.04891/) (2019)
- [Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control](https://mlsanity.com/paper/2006.05459/) (2020)
- [An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee](https://mlsanity.com/paper/2011.01783/) (2020)
- [Federated Learning with Bayesian Differential Privacy](https://mlsanity.com/paper/1911.10071/) (2019)
- [Multi-Armed Bandit Based Client Scheduling for Federated Learning](https://mlsanity.com/paper/2007.02315/) (2020)
- [On Safeguarding Privacy and Security in the Framework of Federated Learning](https://mlsanity.com/paper/1909.06512/) (2019)
- [Wireless Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2002.05151/) (2020)
- [DP-ADMM: ADMM-based Distributed Learning with Differential Privacy](https://mlsanity.com/paper/1808.10101/) (2018)
- [Federated Learning for 6G Communications: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/2006.02931/) (2020)
- [Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective](https://mlsanity.com/paper/2003.00866/) (2020)
- [Collaborative Multi-Agent Multi-Armed Bandit Learning for Small-Cell Caching](https://mlsanity.com/paper/2001.03835/) (2020)
- [Privacy Preservation in Location-Based Services: A Novel Metric and Attack Model](https://mlsanity.com/paper/1805.06104/) (2018)
- [Privacy Preserving Location Data Publishing: A Machine Learning Approach](https://mlsanity.com/paper/1902.08934/) (2019)

## Built on by (most cited first, 25 of 25)

- [Robust Information Bottleneck for Task-Oriented Communication with Digital Modulation](https://mlsanity.com/paper/2209.10382/) (2022)
- [Context-Aware Online Client Selection for Hierarchical Federated Learning](https://mlsanity.com/paper/2112.00925/) (2021)
- [Machine Unlearning: A Survey](https://mlsanity.com/paper/2306.03558/) (2023)
- [Interference Management for Over-the-Air Federated Learning in Multi-Cell Wireless Networks](https://mlsanity.com/paper/2206.02398/) (2022)
- [Federated Learning in Intelligent Transportation Systems: Recent Applications and Open Problems](https://mlsanity.com/paper/2309.11039/) (2023)
- [Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learning](https://mlsanity.com/paper/2303.04274/) (2023)
- [Federated Learning over Wireless IoT Networks with Optimized Communication and Resources](https://mlsanity.com/paper/2110.11775/) (2021)
- [Machine Unlearning for Traditional Models and Large Language Models: A Short Survey](https://mlsanity.com/paper/2404.01206/) (2024)
- [Social-Aware Clustered Federated Learning with Customized Privacy Preservation](https://mlsanity.com/paper/2212.13992/) (2022)
- [Gradient Sparsification for Efficient Wireless Federated Learning with Differential Privacy](https://mlsanity.com/paper/2304.04164/) (2023)
- [On Differential Privacy for Federated Learning in Wireless Systems with Multiple Base Stations](https://mlsanity.com/paper/2208.11848/) (2022)
- [Explainable Semantic Federated Learning Enabled Industrial Edge Network for Fire Surveillance](https://mlsanity.com/paper/2412.19979/) (2024)
- [Hierarchical Federated Learning for Social Network with Mobility](https://mlsanity.com/paper/2509.14938/) (2025)
- [Design of Two-Level Incentive Mechanisms for Hierarchical Federated Learning](https://mlsanity.com/paper/2304.04162/) (2023)
- [Over-the-Air Federated Averaging with Limited Power and Privacy Budgets](https://mlsanity.com/paper/2305.03547/) (2023)
- [Differentially Private Wireless Federated Learning Using Orthogonal Sequences](https://mlsanity.com/paper/2306.08280/) (2023)
- [Federated Meta-Learning for Few-Shot Fault Diagnosis with Representation Encoding](https://mlsanity.com/paper/2310.09002/) (2023)
- [Energy-Efficient Wireless Federated Learning via Doubly Adaptive Quantization](https://mlsanity.com/paper/2402.12957/) (2024)
- [Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Design](https://mlsanity.com/paper/2410.05662/) (2024)
- [Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations](https://mlsanity.com/paper/2405.06993/) (2024)
- [Resource Efficient Asynchronous Federated Learning for Digital Twin Empowered IoT Network](https://mlsanity.com/paper/2408.14298/) (2024)
- [A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control](https://mlsanity.com/paper/2504.01752/) (2025)
- [Dyn-D2P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee](https://mlsanity.com/paper/2505.06651/) (2025)
- [Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning](https://mlsanity.com/paper/2506.14251/) (2025)
- [Convergence-Latency-Aware Adaptive Modulation and Resource Allocation in RIS-Assisted Wireless Federated Learning](https://mlsanity.com/paper/2607.19759/) (2026)

## Abstract (arXiv)

In federated learning (FL), model training is distributed over clients and local models are aggregated by a central server. The performance of uploaded models in such situations can vary widely due to imbalanced data distributions, potential demands on privacy protections, and quality of transmissions. In this paper, we aim to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy (DP) requirement. We solve this problem in the framework of multi-agent multi-armed bandit (MAMAB) to deal with the situation where there are multiple clients confornting different unknown transmission environments, e.g., channel fading and interferences. Specifically, we first transform the long-term constraints on both training performance and each client's DP into a virtual queue based on the Lyapunov drift technique. Then, we convert the MAMAB to a max-min bipartite matching problem at each communication round, by estimating rewards with the upper confidence bound (UCB) approach. More importantly, we propose two efficient solutions to this matching problem, i.e., modified Hungarian algorithm and greedy matching with a better alternative (GMBA), in which the first one can achieve the optimal solution with a high complexity while the second one approaches a better trade-off by enabling a verified low-complexity with little performance loss. In addition, we develop an upper bound on the expected regret of this MAMAB based FL framework, which shows a linear growth over the logarithm of communication rounds, justifying its theoretical feasibility. Extensive experimental results are conducted to validate the effectiveness of our proposed algorithms, and the impacts of various parameters on the FL performance over wireless edge networks are also discussed.