mlsanityData to 7 Oct 2026

Biased Over-the-Air Federated Learning under Wireless Heterogeneity

arXiv 2403.19849 ↗First posted 28 Mar 2024cs.LG eess.SPcited by 2

Not on the map. Why?

Abstract (arXiv)

Recently, Over-the-Air (OTA) computation has emerged as a promising federated learning (FL) paradigm that leverages the waveform superposition properties of the wireless channel to realize fast model updates. Prior work focused on the OTA device ``pre-scaler" design under homogeneous wireless conditions, in which devices experience the same average path loss, resulting in zero-bias solutions. Yet, zero-bias designs are limited by the device with the worst average path loss and hence may perform poorly in heterogeneous wireless settings. In this scenario, there may be a benefit in designing biased solutions, in exchange for a lower variance in the model updates. To optimize this trade-off, we study the design of OTA device pre-scalers by focusing on the OTA-FL convergence. We derive an upper bound on the model ``optimality error", which explicitly captures the effect of bias and variance in terms of the choice of the pre-scalers. Based on this bound, we identify two solutions of interest: minimum noise variance, and minimum noise variance zero-bias solutions. Numerical evaluations show that using OTA device pre-scalers that minimize the variance of FL updates, while allowing a small bias, can provide high gains over existing schemes.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 18 of its 21 references that are in the map. First posted on arXiv 28 Mar 2024.

Builds on

18 of 21 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  3. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  4. 2019Towards Federated Learning at Scale: System Designcited by 826
  5. 2014Convex Optimization: Algorithms and Complexitycited by 569
  6. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
  7. 2018Federated Learning via Over-the-Air Computationcited by 215
  8. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  9. 2019Federated Learning over Wireless Fading Channelscited by 178
  10. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
  11. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
  12. 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 108
6 more
  1. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 72
  2. 2020Multi-Stage Hybrid Federated Learning over Large-Scale D2D-Enabled Fog Networkscited by 42
  3. 2020Blind Federated Edge Learningcited by 42
  4. 2020Distributed Machine Learning for Wireless Communication Networks: Techniques, Architectures, and Applicationscited by 21
  5. 2024Analog-digital Scheduling for Federated Learning: A Communication-Efficient Approachcited by 5
  6. 2022Decentralized Federated Learning via Non-Coherent Over-the-Air Consensuscited by 4

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Biased Federated Learning under Wireless Heterogeneitycited by 4
  2. 2025Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-offcited by 1