mlsanityData to 14 Oct 2026

Federated Learning with Multi-resolution Model Broadcast

arXiv 2405.19886 ↗First posted 30 May 2024cs.NI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In federated learning, a server must periodically broadcast a model to the agents. We propose to use multi-resolution coding and modulation (also known as non-uniform modulation) for this purpose. In the simplest instance, broadcast transmission is used, whereby all agents are targeted with one and the same transmission (typically without any particular favored beam direction), which is coded using multi-resolution coding/modulation. This enables high-SNR agents, with high path gains to the server, to receive a more accurate model than the low-SNR agents do, without consuming more downlink resources. As one implementation, we use transmission with a non-uniform 8-PSK constellation, where a high-SNR receiver (agent) can separate all 8 constellation points (hence receive 3 bits) whereas a low-SNR receiver can only separate 4 points (hence receive 2 bits). By encoding the least significant information in the third bit, the high-SNR receivers can obtain the model with higher accuracy, while the low-SNR receiver can still obtain the model although with reduced accuracy, thereby facilitating at least some basic participation of the low-SNR receiver. We show the effectiveness of our proposed scheme via experimentation using federated learning with the MNIST data-set.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 28 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

16 of 28 references.

References · 16

  1. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 478
  2. 2019Federated Learning over Wireless Fading Channelscited by 183
  3. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
  4. 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
  5. 2018How Important Is a Neuron?cited by 73
  6. 2020Convergence of Update Aware Device Scheduling for Federated Learning at the Wireless Edgecited by 71
  7. 2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
  8. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  9. 2019Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networkscited by 39
  10. 2020Federated Learning in Unreliable and Resource-Constrained Cellular Wireless Networkscited by 29
  11. 2019Data-Importance Aware User Scheduling for Communication-Efficient Edge Machine Learningcited by 20
  12. 2021Federated Learning over Wireless IoT Networks with Optimized Communication and Resourcescited by 13
4 more
  1. 2021Fast Federated Edge Learning with Overlapped Communication and Computation and Channel-Aware Fair Client Schedulingcited by 9
  2. 2022Data-Quality Based Scheduling for Federated Edge Learningcited by 6
  3. 2022SlimFL: Federated Learning with Superposition Coding over Slimmable Neural Networkscited by 6
  4. 2022Variance-Reduced Heterogeneous Federated Learning via Stratified Client Selectioncited by 3

Built on by

Not cited yet.