mlsanityData to 7 Oct 2026

AirFL-Mem: Improving Communication-Learning Trade-Off by Long-Term Memory

arXiv 2310.16606 ↗First posted 25 Oct 2023cs.IT cs.LG math.ITcited by 4

Not on the map. Why?

Abstract (arXiv)

Addressing the communication bottleneck inherent in federated learning (FL), over-the-air FL (AirFL) has emerged as a promising solution, which is, however, hampered by deep fading conditions. In this paper, we propose AirFL-Mem, a novel scheme designed to mitigate the impact of deep fading by implementing a long-term memory mechanism. Convergence bounds are provided that account for long-term memory, as well as for existing AirFL variants with short-term memory, for general non-convex objectives. The theory demonstrates that AirFL-Mem exhibits the same convergence rate of federated averaging (FedAvg) with ideal communication, while the performance of existing schemes is generally limited by error floors. The theoretical results are also leveraged to propose a novel convex optimization strategy for the truncation threshold used for power control in the presence of Rayleigh fading channels. Experimental results validate the analysis, confirming the advantages of a long-term memory mechanism for the mitigation of deep fading.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 25 Oct 2023.

Builds on

18 of 25 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2021Convex optimizationcited by 2,479
  3. 2018Sparsified SGD with Memorycited by 373
  4. 2019Error Feedback Fixes SignSGD and other Gradient Compression Schemescited by 306
  5. 2018Federated Learning via Over-the-Air Computationcited by 215
  6. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 192
  7. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  8. 2019Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computationscited by 179
  9. 2019Federated Learning over Wireless Fading Channelscited by 178
  10. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 72
  11. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 61
  12. 2021Optimized Power Control Design for Over-the-Air Federated Edge Learningcited by 45
6 more
  1. 2020Blind Federated Edge Learningcited by 42
  2. 2020Fast Convergence Algorithm for Analog Federated Learningcited by 16
  3. 2021Accelerated Gradient Descent Learning over Multiple Access Fading Channelscited by 14
  4. 2022Random Orthogonalization for Federated Learning in Massive MIMO Systemscited by 13
  5. 2023Imperfect CSI: A Key Factor of Uncertainty to Over-the-Air Federated Learningcited by 5
  6. 2023Communication-Efficient Federated Learning over Capacity-Limited Wireless Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024NCAirFL: CSI-Free Over-the-Air Federated Learning Based on Non-Coherent Detectioncited by 4
  2. 2024Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offscited by 3
  3. 2025Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Stationcited by 1
  4. 2026Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Schedulingcited by 0