mlsanityData to 14 Oct 2026

Adaptive Federated Learning Over the Air

arXiv 2403.06528 ↗First posted 11 Mar 2024cs.LG cs.IT cs.NIcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. This approach capitalizes on the inherent superposition property of wireless channels, facilitating fast and scalable parameter aggregation. Meanwhile, it enhances the robustness of the model training process by dynamically adjusting the stepsize in accordance with the global gradient update. We derive the convergence rate of the training algorithms, encompassing the effects of channel fading and interference, for a broad spectrum of nonconvex loss functions. Our analysis shows that the AdaGrad-based algorithm converges to a stationary point at the rate of O( ln(T) / T^ 1 - frac1α ), where α represents the tail index of the electromagnetic interference. This result indicates that the level of heavy-tailedness in interference distribution plays a crucial role in the training efficiency: the heavier the tail, the slower the algorithm converges. In contrast, an Adam-like algorithm converges at the O( 1/T ) rate, demonstrating its advantage in expediting the model training process. We conduct extensive experiments that corroborate our theoretical findings and affirm the practical efficacy of our proposed federated adaptive gradient methods.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 30 of its 59 references that are in the map. First posted on arXiv 11 Mar 2024.

Builds on

30 of 59 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  6. 2020Adaptive Federated Optimizationcited by 1,046
  7. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  8. 2018Federated Learning via Over-the-Air Computationcited by 219
  9. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  10. 2018AdaGrad stepsizes: Sharp convergence over nonconvex landscapescited by 182
  11. 2020A Simple Convergence Proof of Adam and Adagradcited by 171
  12. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
18 more
  1. 2019Federated Learning for Wireless Communications: Motivation, Opportunities and Challengescited by 129
  2. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 62
  3. 2021Optimized Power Control Design for Over-the-Air Federated Edge Learningcited by 48
  4. 2021Mobility-Aware Cluster Federated Learning in Hierarchical Wireless Networkscited by 35
  5. 2021Federated Edge Learning with Misaligned Over-The-Air Computationcited by 30
  6. 2022A Survey on Over-the-Air Computationcited by 21
  7. 2020Fast Convergence Algorithm for Analog Federated Learningcited by 17
  8. 2023Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancercited by 17
  9. 2021Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysiscited by 14
  10. 2021Accelerated Gradient Descent Learning over Multiple Access Fading Channelscited by 14
  11. 2023FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Schedulercited by 13
  12. 2022Over-the-Air Federated Learning via Second-Order Optimizationcited by 11
  13. 2021Over-the-Air Aggregation for Federated Learning: Waveform Superposition and Prototype Validationcited by 10
  14. 2022Over-the-Air Computation Based on Balanced Number Systems for Federated Edge Learningcited by 10
  15. 2022Over-the-Air Federated Learning with Joint Adaptive Computation and Power Controlcited by 9
  16. 2023Edge Intelligence Over the Air: Two Faces of Interference in Federated Learningcited by 5
  17. 2023Optimal Receive Filter Design for Misaligned Over-the-Air Computationcited by 4
  18. 2023Personalizing Federated Learning with Over-the-Air Computationscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Energy-Efficient Over-the-Air Federated Learning via Pinching Antenna Systemscited by 1
  2. 2026Resource-Element Energy Difference for Noncoherent Over-the-Air Federated Learningcited by 0
  3. 2026Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithmcited by 0
  4. 2026Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-off
  2. 2026Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks
  3. 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing
  4. 2025Biased Federated Learning under Wireless Heterogeneity
  5. 2021Over-the-Air Federated Multi-Task Learning Over MIMO Multiple Access Channels
  6. 2024Robust Federated Learning Over the Air: Combating Heavy-Tailed Noise with Median Anchored Clipping
  7. 2026Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling
  8. 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning