mlsanityData to 14 Oct 2026

Timely Parameter Updating in Over-the-Air Federated Learning

arXiv 2512.19103 ↗First posted 22 Dec 2025cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Incorporating over-the-air computations (OAC) into the model training process of federated learning (FL) is an effective approach to alleviating the communication bottleneck in FL systems. Under OAC-FL, every client modulates its intermediate parameters, such as gradient, onto the same set of orthogonal waveforms and simultaneously transmits the radio signal to the edge server. By exploiting the superposition property of multiple-access channels, the edge server can obtain an automatically aggregated global gradient from the received signal. However, the limited number of orthogonal waveforms available in practical systems is fundamentally mismatched with the high dimensionality of modern deep learning models. To address this issue, we propose Freshness Freshness-mAgnItude awaRe top-k (FAIR-k), an algorithm that selects, in each communication round, the most impactful subset of gradients to be updated over the air. In essence, FAIR-k combines the complementary strengths of the Round-Robin and Top-k algorithms, striking a delicate balance between timeliness (freshness of parameter updates) and importance (gradient magnitude). Leveraging tools from Markov analysis, we characterize the distribution of parameter staleness under FAIR-k. Building on this, we establish the convergence rate of OAC-FL with FAIR-k, which discloses the joint effect of data heterogeneity, channel noise, and parameter staleness on the training efficiency. Notably, as opposed to conventional analyses that assume a universal Lipschitz constant across all the clients, our framework adopts a finer-grained model of the data heterogeneity. The analysis demonstrates that since FAIR-k promotes fresh (and fair) parameter updates, it not only accelerates convergence but also enhances communication efficiency by enabling an extended period of local training without significantly affecting overall training efficiency.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 22 Dec 2025.

Builds on

35 of 53 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  4. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  5. 2018Sparsified SGD with Memorycited by 376
  6. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 278
  7. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  8. 2017Sparse Communication for Distributed Gradient Descentcited by 249
  9. 2018Federated Learning via Over-the-Air Computationcited by 219
  10. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  11. 2019Federated Learning over Wireless Fading Channelscited by 183
  12. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
23 more
  1. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 73
  2. 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 63
  3. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 62
  4. 2021Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysiscited by 51
  5. 2021Optimized Power Control Design for Over-the-Air Federated Edge Learningcited by 48
  6. 2019Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networkscited by 39
  7. 2020rTop-k: A Statistical Estimation Approach to Distributed SGDcited by 27
  8. 2020Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learningcited by 24
  9. 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21
  10. 2022Joint Device Selection and Power Control for Wireless Federated Learningcited by 20
  11. 2020Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noisecited by 15
  12. 2021Federated Learning over Wireless Networks: A Band-limited Coordinated Descent Approachcited by 11
  13. 2021Over-the-Air Aggregation for Federated Learning: Waveform Superposition and Prototype Validationcited by 10
  14. 2022Distributed Learning over a Wireless Network with Non-coherent Majority Vote Computationcited by 9
  15. 2023LASER: Linear Compression in Wireless Distributed Optimizationcited by 6
  16. 2023Edge Intelligence Over the Air: Two Faces of Interference in Federated Learningcited by 5
  17. 2022A Demonstration of Over-the-Air Computation for Federated Edge Learningcited by 4
  18. 2022Over-the-Air Computation for Distributed Systems: Something Old and Something Newcited by 4
  19. 2024A New Theoretical Perspective on Data Heterogeneity in Federated Optimizationcited by 4
  20. 2024Robust Federated Learning Over the Air: Combating Heavy-Tailed Noise with Median Anchored Clippingcited by 3
  21. 2025Experimental Demonstration of Over the Air Federated Learning for Cellular Networkscited by 2
  22. 2025Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Aircited by 2
  23. 2025Rethinking Federated Learning Over the Air: The Blessing of Scaling Upcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning
  2. 2022Blind Asynchronous Over-the-Air Federated Edge Learning
  3. 2025Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-off
  4. 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing
  5. 2024Adaptive Federated Learning Over the Air
  6. 2022Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control
  7. 2024Analog-digital Scheduling for Federated Learning: A Communication-Efficient Approach
  8. 2024Fed-ZOE: Communication-Efficient Over-the-Air Federated Learning via Zeroth-Order Estimation