mlsanityData to 14 Oct 2026

Private Federated Learning with Dynamic Power Control via Non-Coherent Over-the-Air Computation

arXiv 2308.02881 ↗First posted 5 Aug 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

To further preserve model weight privacy and improve model performance in Federated Learning (FL), FL via Over-the-Air Computation (AirComp) scheme based on dynamic power control is proposed. The edge devices (EDs) transmit the signs of local stochastic gradients by activating two adjacent orthogonal frequency division multi-plexing (OFDM) subcarriers, and majority votes (MVs) at the edge server (ES) are obtained by exploiting the energy accumulation on the subcarriers. Then, we propose a dynamic power control algorithm to further offset the biased aggregation of the MV aggregation values. We show that the whole scheme can mitigate the impact of the time synchronization error, channel fading and noise. The theoretical convergence proof of the scheme is re-derived.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 20 references that are in the map. First posted on arXiv 5 Aug 2023.

Builds on

17 of 20 references.

References · 17

  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. 2019Deep Leakage from Gradientscited by 1,021
  4. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 571
  5. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  6. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 263
  7. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  8. 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 158
  9. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 129
  10. 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 112
  11. 2017Natasha 2: Faster Non-Convex Optimization Than SGDcited by 49
  12. 2019Over-the-Air Computation Systems: Optimization, Analysis and Scaling Lawscited by 27
5 more
  1. 2021Distributed Learning over a Wireless Network with FSK-Based Majority Votecited by 13
  2. 2021Over-the-Air Computation with DFT-spread OFDM for Federated Edge Learningcited by 9
  3. 2022Multi-cell Non-coherent Over-the-Air Computation for Federated Edge Learningcited by 4
  4. 2022Transmit Power Control for Indoor Small Cells: A Method Based on Federated Reinforcement Learningcited by 3
  5. 2022SignSGD: Fault-Tolerance to Blind and Byzantine Adversariescited by 1

Built on by

Not cited yet.