mlsanityData to 7 Oct 2026

PolarAir: A Compressed Sensing Scheme for Over-the-Air Federated Learning

arXiv 2301.10110 ↗First posted 24 Jan 2023cs.IT cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

We explore a scheme that enables the training of a deep neural network in a Federated Learning configuration over an additive white Gaussian noise channel. The goal is to create a low complexity, linear compression strategy, called PolarAir, that reduces the size of the gradient at the user side to lower the number of channel uses needed to transmit it. The suggested approach belongs to the family of compressed sensing techniques, yet it constructs the sensing matrix and the recovery procedure using multiple access techniques. Simulations show that it can reduce the number of channel uses by ~30% when compared to conveying the gradient without compression. The main advantage of the proposed scheme over other schemes in the literature is its low time complexity. We also investigate the behavior of gradient updates and the performance of PolarAir throughout the training process to obtain insight on how best to construct this compression scheme based on compressed sensing.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 24 Jan 2023.

Builds on

13 of 23 references.

References · 13

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  5. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 561
  6. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  7. 2015Federated Optimization:Distributed Optimization Beyond the Datacentercited by 193
  8. 2019Federated Learning over Wireless Fading Channelscited by 178
  9. 2016QSGD: Communication-Efficient SGD via Gradient Quantization and Encodingcited by 147
  10. 2021Accelerated Gradient Descent Learning over Multiple Access Fading Channelscited by 14
  11. 2016Over-the-air Function Computation in Sensor Networkscited by 11
  12. 2021Temporal-Structure-Assisted Gradient Aggregation for Over-the-Air Federated Edge Learningcited by 10
1 more
  1. 2021Over-the-Air Statistical Estimationcited by 3

Built on by

Not cited yet.