mlsanityData to 7 Oct 2026

Over-the-Air Federated Learning via Weighted Aggregation

arXiv 2409.07822 ↗First posted 12 Sep 2024cs.IT cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper introduces a new federated learning scheme that leverages over-the-air computation. A novel feature of this scheme is the proposal to employ adaptive weights during aggregation, a facet treated as predefined in other over-the-air schemes. This can mitigate the impact of wireless channel conditions on learning performance, without needing channel state information at transmitter side (CSIT). We provide a mathematical methodology to derive the convergence bound for the proposed scheme in the context of computational heterogeneity and general loss functions, supplemented with design insights. Accordingly, we propose aggregation cost metrics and efficient algorithms to find optimized weights for the aggregation. Finally, through numerical experiments, we validate the effectiveness of the proposed scheme. Even with the challenges posed by channel conditions and device heterogeneity, the proposed scheme surpasses other over-the-air strategies by an accuracy improvement of 15% over the scheme using CSIT and 30% compared to the one without CSIT.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 23 of its 39 references that are in the map. First posted on arXiv 12 Sep 2024.

Builds on

23 of 39 references.

References · 23

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2021Convex optimizationcited by 2,479
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  4. 2018Federated Learning via Over-the-Air Computationcited by 215
  5. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  6. 2019Federated Learning over Wireless Fading Channelscited by 178
  7. 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 108
  8. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 61
  9. 2021Optimized Power Control Design for Over-the-Air Federated Edge Learningcited by 45
  10. 2020Blind Federated Edge Learningcited by 42
  11. 2020Federated Learning via Intelligent Reflecting Surfacecited by 38
  12. 2021Cost-Effective Federated Learning in Mobile Edge Networkscited by 25
11 more
  1. 2022Joint Device Selection and Power Control for Wireless Federated Learningcited by 19
  2. 2022A Survey on Over-the-Air Computationcited by 19
  3. 2019Robust and Communication-Efficient Collaborative Learningcited 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. 2021Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysiscited by 13
  7. 2021Wirelessly Powered Federated Edge Learning: Optimal Tradeoffs Between Convergence and Power Transfercited by 10
  8. 2023Joint Age-based Client Selection and Resource Allocation for Communication-Efficient Federated Learning over NOMA Networkscited by 8
  9. 2024Hierarchical Over-the-Air Federated Learning with Awareness of Interference and Data Heterogeneitycited by 6
  10. 2024Federated Learning via Lattice Joint Source-Channel Codingcited by 6
  11. 2024Compute-Update Federated Learning: A Lattice Coding Approach Over-the-Aircited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processingcited by 3
  2. 2026Out-of-Air Computation: Enabling Structured Function Extraction from Wireless Superpositioncited by 0
  3. 2026Resource-Element Energy Difference for Noncoherent Over-the-Air Federated Learningcited by 0
  4. 2026AirPASS: Over-the-Air Federated Learning via Pinching Antenna Systemscited by 0
  5. 2026AirGC-CD: Gaussian-Circulant Precoding for Exactly Debiasable PAPR Reduction in Over-the-Air Federated Learningcited by 0