Over-the-Air Federated Learning from Heterogeneous Data
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) is a framework for distributed learning of centralized models. In FL, a set of edge devices train a model using their local data, while repeatedly exchanging their trained updates with a central server. This procedure allows tuning a centralized model in a distributed fashion without having the users share their possibly private data. In this paper, we focus on over-the-air (OTA) FL, which has been suggested recently to reduce the communication overhead of FL due to the repeated transmissions of the model updates by a large number of users over the wireless channel. In OTA FL, all users simultaneously transmit their updates as analog signals over a multiple access channel, and the server receives a superposition of the analog transmitted signals. However, this approach results in the channel noise directly affecting the optimization procedure, which may degrade the accuracy of the trained model. We develop a Convergent OTA FL (COTAF) algorithm which enhances the common local stochastic gradient descent (SGD) FL algorithm, introducing precoding at the users and scaling at the server, which gradually mitigates the effect of the noise. We analyze the convergence of COTAF to the loss minimizing model and quantify the effect of a statistically heterogeneous setup, i.e. when the training data of each user obeys a different distribution. Our analysis reveals the ability of COTAF to achieve a convergence rate similar to that achievable over error-free channels. Our simulations demonstrate the improved convergence of COTAF over vanilla OTA local SGD for training using non-synthetic datasets. Furthermore, we numerically show that the precoding induced by COTAF notably improves the convergence rate and the accuracy of models trained via OTA FL.
Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Sep 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 14; 2022: 13; 2023: 20; 2024: 11; 2025: 8; 2026: 6.
72 papers.
Sort:
- 2022Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learningcited by 59
- 2021Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregationscited by 50
- 2021Federated Learning: A Signal Processing Perspectivecited by 49
- 2021Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraintscited by 34
- 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 34
- 2021Fusion of Federated Learning and Industrial Internet of Things: A Surveycited by 28
- 2021Federated Edge Learning with Misaligned Over-The-Air Computationcited by 28
- 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21
- 2021Edge Federated Learning Via Unit-Modulus Over-The-Air Computationcited by 16
- 2023On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharingcited by 16
- 2021Accelerated Gradient Descent Learning over Multiple Access Fading Channelscited by 14
- 2024Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directionscited by 12
38 more
- 2021Hierarchical Over-the-Air Federated Edge Learningcited by 11
- 2022Over-the-Air Federated Edge Learning with Hierarchical Clusteringcited by 10
- 2023Over-the-Air Federated Learning and Optimizationcited by 10
- 2022Over-the-Air Computation Based on Balanced Number Systems for Federated Edge Learningcited by 9
- 2023Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interferencecited by 9
- 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learningcited by 9
- 2021Federated Learning over Noisy Channels: Convergence Analysis and Design Examplescited by 8
- 2022Over-the-Air Federated Learning with Joint Adaptive Computation and Power Controlcited by 8
- 2023Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approachcited by 8
- 2021Over-the-Air Federated Multi-Task Learning Over MIMO Multiple Access Channelscited by 7
- 2021AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learningcited by 6
- 2022Federated Multi-Armed Bandits Under Byzantine Attackscited by 6
- 2021Robust Federated Learning via Over-The-Air Computationcited by 5
- 2022Robust Federated Learning with Connectivity Failures: A Semi-Decentralized Framework with Collaborative Relayingcited by 5
- 2022Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbationscited by 5
- 2022Over-The-Air Federated Learning under Byzantine Attackscited by 4
- 2022Over-the-Air Computation over Balanced Numeralscited by 4
- 2023Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noisecited by 4
- 2023AirFL-Mem: Improving Communication-Learning Trade-Off by Long-Term Memorycited by 4
- 2024Rendering Wireless Environments Useful for Gradient Estimators: A Zero-Order Stochastic Federated Learning Methodcited by 4
- 2024Stragglers-Aware Low-Latency Synchronous Federated Learning via Layer-Wise Model Updatescited by 4
- 2024Federated Learning With Energy Harvesting Devices: An MDP Frameworkcited by 4
- 2025Biased Federated Learning under Wireless Heterogeneitycited by 4
- 2021Over-the-Air Statistical Estimationcited by 3
- 2024An Element-Wise Weights Aggregation Method for Federated Learningcited by 3
- 2024Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offscited by 3
- 2024Communication-efficient Vertical Federated Learning via Compressed Error Feedbackcited by 3
- 2024Energy-Efficient Channel Decoding for Wireless Federated Learning: Convergence Analysis and Adaptive Designcited by 3
- 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processingcited by 3
- 2022Over-The-Air Federated Learning Over Scalable Cell-free Massive MIMOcited by 2
- 2023Federated Learning in Wireless Networks via Over-the-Air Computationscited by 2
- 2023Convergence Analysis of Over-the-Air FL with Compression and Power Control via Clippingcited by 2
- 2023How Robust is Federated Learning to Communication Error? A Comparison Study Between Uplink and Downlink Channelscited by 2
- 2023Sparse Training for Federated Learning with Regularized Error Correctioncited by 2
- 2024Biased Over-the-Air Federated Learning under Wireless Heterogeneitycited by 2
- 2023Digital Over-the-Air Federated Learning in Multi-Antenna Systemscited by 1
- 2023Accelerating Wireless Federated Learning via Nesterov's Momentum and Distributed Principle Component Analysiscited by 1
- 2023Over-the-Air Federated Averaging with Limited Power and Privacy Budgetscited by 1
50 most cited of 72 All 72 (JSON)
- 2026Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks26 Sep 2026
- 2026FedGenSC: Federated Generative Semantic Communication with Channel-Aware Adaptation8 Sep 2026
- 2026Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling8 Sep 2026
- 2026Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networks5 Jul 2026
- 2026Resource-Element Energy Difference for Noncoherent Over-the-Air Federated Learning8 May 2026
- 2026Event-Triggered Gossip for Distributed Learning22 Feb 2026
- 2025Timely Parameter Updating in Over-the-Air Federated Learning22 Dec 2025
- 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing3 Dec 2025
- 2025Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-off30 Oct 2025
- 2025Rethinking Federated Learning Over the Air: The Blessing of Scaling Up25 Aug 2025
- 2025OLALa: Online Learned Adaptive Lattice Codes for Heterogeneous Federated Learning25 Jun 2025
- 2025Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning16 May 2025
38 more
- 2025Noise Resilient Over-The-Air Federated Learning In Heterogeneous Wireless Networks25 Mar 2025
- 2025Biased Federated Learning under Wireless Heterogeneity8 Mar 2025
- 2024Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions19 Nov 2024
- 2024Energy-Efficient Channel Decoding for Wireless Federated Learning: Convergence Analysis and Adaptive Design26 Jun 2024
- 2024Communication-efficient Vertical Federated Learning via Compressed Error Feedback20 Jun 2024
- 2024Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offs17 Jun 2024
- 2024Mixed-Precision Federated Learning via Multi-Precision Over-The-Air Aggregation4 Jun 2024
- 2024Federated Learning With Energy Harvesting Devices: An MDP Framework17 May 2024
- 2024An Element-Wise Weights Aggregation Method for Federated Learning24 Apr 2024
- 2024Biased Over-the-Air Federated Learning under Wireless Heterogeneity28 Mar 2024
- 2024Stragglers-Aware Low-Latency Synchronous Federated Learning via Layer-Wise Model Updates27 Mar 2024
- 2024Boosting Fairness and Robustness in Over-the-Air Federated Learning7 Mar 2024
- 2024Rendering Wireless Environments Useful for Gradient Estimators: A Zero-Order Stochastic Federated Learning Method30 Jan 2024
- 2023Sparse Training for Federated Learning with Regularized Error Correction21 Dec 2023
- 2023A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems6 Dec 2023
- 2023Federated Learning over Hierarchical Wireless Networks: Training Latency Minimization via Submodel Partitioning27 Oct 2023
- 2023How Robust is Federated Learning to Communication Error? A Comparison Study Between Uplink and Downlink Channels25 Oct 2023
- 2023AirFL-Mem: Improving Communication-Learning Trade-Off by Long-Term Memory25 Oct 2023
- 2023Over-the-Air Federated Learning and Optimization16 Oct 2023
- 2023Over-the-Air Federated Learning with Compressed Sensing: Is Sparsification Necessary?5 Oct 2023
- 2023Joint Power Control and Data Size Selection for Over-the-Air Computation Aided Federated Learning17 Aug 2023
- 2023Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noise14 Jul 2023
- 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions3 Jul 2023
- 2023Differentially Private Wireless Federated Learning Using Orthogonal Sequences14 Jun 2023
- 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning26 May 2023
- 2023Convergence Analysis of Over-the-Air FL with Compression and Power Control via Clipping18 May 2023
- 2023Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interference10 May 2023
- 2023Federated Learning in Wireless Networks via Over-the-Air Computations8 May 2023
- 2023Over-the-Air Federated Averaging with Limited Power and Privacy Budgets5 May 2023
- 2023Accelerating Wireless Federated Learning via Nesterov's Momentum and Distributed Principle Component Analysis31 Mar 2023
- 2023On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharing19 Mar 2023
- 2023Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach18 Mar 2023
- 2023Digital Over-the-Air Federated Learning in Multi-Antenna Systems4 Feb 2023
- 2022Over-The-Air Federated Learning Over Scalable Cell-free Massive MIMO13 Dec 2022
- 2022Secure Over-the-Air Computation using Zero-Forced Artificial Noise8 Dec 2022
- 2022Random Orthogonalization for Federated Learning in Massive MIMO Systems18 Oct 2022
- 2022Over-the-Air Computation Based on Balanced Number Systems for Federated Edge Learning13 Oct 2022
- 2022Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations5 Oct 2022
50 newest of 72 All 72 (JSON)
- 2022Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learningcited by 59
- 2021Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregationscited by 50
- 2021Federated Learning: A Signal Processing Perspectivecited by 49
- 2021Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraintscited by 34
- 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 34
- 2021Fusion of Federated Learning and Industrial Internet of Things: A Surveycited by 28
- 2021Federated Edge Learning with Misaligned Over-The-Air Computationcited by 28
- 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21
- 2021Edge Federated Learning Via Unit-Modulus Over-The-Air Computationcited by 16
- 2023On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharingcited by 16
- 2021Accelerated Gradient Descent Learning over Multiple Access Fading Channelscited by 14
- 2024Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directionscited by 12
12 most cited of 72 All 72 (JSON)
- 2026Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks26 Sep 2026
- 2026FedGenSC: Federated Generative Semantic Communication with Channel-Aware Adaptation8 Sep 2026
- 2026Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling8 Sep 2026
- 2026Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networks5 Jul 2026
- 2026Resource-Element Energy Difference for Noncoherent Over-the-Air Federated Learning8 May 2026
- 2026Event-Triggered Gossip for Distributed Learning22 Feb 2026
- 2025Timely Parameter Updating in Over-the-Air Federated Learning22 Dec 2025
- 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing3 Dec 2025
- 2025Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-off30 Oct 2025
- 2025Rethinking Federated Learning Over the Air: The Blessing of Scaling Up25 Aug 2025
- 2025OLALa: Online Learned Adaptive Lattice Codes for Heterogeneous Federated Learning25 Jun 2025
- 2025Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning16 May 2025
12 newest of 72 All 72 (JSON)