mlsanityData to 14 Oct 2026

Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing

arXiv 2512.03719 ↗First posted 3 Dec 2025cs.IT cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Over-the-Air Federated Learning (AirFL) is an emerging paradigm that tightly integrates wireless signal processing and distributed machine learning to enable scalable AI at the network edge. By exploiting wireless superposition over a shared multiple-access channel, AirFL turns simultaneous transmissions of local model updates into an analog aggregate at the receiver, thereby reducing communication latency, bandwidth usage, and energy consumption in wireless aggregation domains. This article develops a design-oriented tutorial view of analog AirFL. We organize existing schemes according to the signal-processing mechanism used to enable AirFL aggregation: transmitter-side channel compensation and power control, receiver-side equalization and high-dimensional processing, or learning-aware aggregation weighting. This viewpoint leads to three representative classes -- CSIT-aware, blind, and weighted AirFL -- and clarifies their assumptions, performance tradeoffs, complexity, and deployment limitations. We further discuss synchronization, digital and hybrid analog-digital realization, and open research directions for integrating AirFL into practical wireless edge-AI systems.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 34 of its 58 references that are in the map. First posted on arXiv 3 Dec 2025.

Builds on

34 of 58 references.

References · 34

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  3. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  4. 2018Federated Learning via Over-the-Air Computationcited by 219
  5. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  6. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 129
  7. 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 112
  8. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 73
  9. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 62
  10. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  11. 2020Blind Federated Edge Learningcited by 43
  12. 2020Federated Learning via Intelligent Reflecting Surfacecited by 38
22 more
  1. 2021Federated Edge Learning with Misaligned Over-The-Air Computationcited by 30
  2. 2022A Survey on Over-the-Air Computationcited by 21
  3. 2021Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysiscited by 14
  4. 2021Accelerated Gradient Descent Learning over Multiple Access Fading Channelscited by 14
  5. 2022Scalable Hierarchical Over-the-Air Federated Learningcited by 14
  6. 2020Hybrid Beamforming for Massive MIMO Over-the-Air Computationcited by 13
  7. 2021Over-the-Air Aggregation for Federated Learning: Waveform Superposition and Prototype Validationcited by 10
  8. 2022Over-the-Air Federated Edge Learning with Hierarchical Clusteringcited by 10
  9. 2023ChannelComp: A General Method for Computation by Communicationscited by 10
  10. 2021Over-the-Air Computation with DFT-spread OFDM for Federated Edge Learningcited by 9
  11. 2023Blind Federated Learning via Over-the-Air q-QAMcited by 8
  12. 2019Time Synchronization in 5G Wireless Edge: Requirements and Solutions for Critical-MTCcited by 7
  13. 2021Broadband Digital Over-the-Air Computation for Asynchronous Federated Edge Learningcited by 6
  14. 2022Broadband Digital Over-the-Air Computation for Wireless Federated Edge Learningcited by 6
  15. 2024Federated Learning via Lattice Joint Source-Channel Codingcited by 6
  16. 2024Waveforms for Computing Over the Aircited by 6
  17. 2021Bayesian Over-The-Air Computationcited by 5
  18. 2023Edge Intelligence Over the Air: Two Faces of Interference in Federated Learningcited by 5
  19. 2024Analog-digital Scheduling for Federated Learning: A Communication-Efficient Approachcited by 5
  20. 2024Compute-Update Federated Learning: A Lattice Coding Approach Over-the-Aircited by 5
  21. 2024Over-the-Air Federated Learning via Weighted Aggregationcited by 5
  22. 2025Adaptively Weighted Averaging Over-the-Air Computation and Its Application to Distributed Gaussian Process Regressioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Federated Multi Agent Deep Learning and Neural Networks for Advanced Distributed Sensing in Wireless Networkscited by 0
  2. 2026Out-of-Air Computation: Enabling Structured Function Extraction from Wireless Superpositioncited by 0
  3. 2026AirPASS: Over-the-Air Federated Learning via Pinching Antenna Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling
  2. 2022Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control
  3. 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions
  4. 2025Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-off
  5. 2025Learned Digital Over-the-Air Computing for Federated Edge Learning
  6. 2024Massive Digital Over-the-Air Computation for Communication-Efficient Federated Edge Learning
  7. 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning
  8. 2022CFLIT: Coexisting Federated Learning and Information Transfer