mlsanityData to 7 Oct 2026

Mixed-Timescale Differential Coding for Downlink Model Broadcast in Wireless Federated Learning

arXiv 2607.13119 ↗First posted 14 Jul 2026cs.IT cs.DC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In standard federated learning systems, the parameter server broadcasts the global model to the participating devices in every iteration. Motivated by the temporal correlation between consecutive global models, differential coding can be applied to global model dissemination to reduce the information magnitude, thereby enabling communication with fewer quantization bits. However, due to wireless link failures, devices may occasionally miss differential updates and consequently fail to reconstruct the global model. As a result, they either continue local training based on an outdated model or remain idle until the next full-model broadcast becomes available. To address this challenge, we propose a mixed-timescale differential coding (MTDC) scheme that performs differential coding at two different levels by adjusting the reference model. With MTDC, a device can reconstruct the latest global model between two full-model broadcasts even if it misses a differential update. We provide a convergence analysis that motivates the design of an age-aware variant of MTDC, along with a device scheduling policy to further improve communication efficiency. Simulation results demonstrate that the proposed MTDC schemes achieve superior learning performance compared to baseline methods under similar communication resource budgets in the presence of downlink transmission failures.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 48 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

30 of 48 references.

References · 30

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  3. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
  4. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
  5. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 103
  6. 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
  7. 2020Convergence of Update Aware Device Scheduling for Federated Learning at the Wireless Edgecited by 71
  8. 2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
  9. 2021Adaptive Quantization of Model Updates for Communication-Efficient Federated Learningcited by 60
  10. 2021Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysiscited by 51
  11. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  12. 2020Design and Analysis of Uplink and Downlink Communications for Federated Learningcited by 48
18 more
  1. 2019Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networkscited by 39
  2. 2018An Exact Quantized Decentralized Gradient Descent Algorithmcited by 34
  3. 2020Convergence of Federated Learning over a Noisy Downlinkcited by 29
  4. 2020Federated Learning in Unreliable and Resource-Constrained Cellular Wireless Networkscited by 29
  5. 2019Data-Importance Aware User Scheduling for Communication-Efficient Edge Machine Learningcited by 20
  6. 2021Communication-Efficient Federated Learning via Quantized Compressed Sensingcited by 17
  7. 2021Federated Learning over Wireless IoT Networks with Optimized Communication and Resourcescited by 13
  8. 2021Slashing Communication Traffic in Federated Learning by Transmitting Clustered Model Updatescited by 10
  9. 2022Convergence Acceleration in Wireless Federated Learning: A Stackelberg Game Approachcited by 10
  10. 2025Unified Analysis of Decentralized Gradient Descent: a Contraction Mapping Frameworkcited by 10
  11. 2021Fast Federated Edge Learning with Overlapped Communication and Computation and Channel-Aware Fair Client Schedulingcited by 9
  12. 2022FedVQCS: Federated Learning via Vector Quantized Compressed Sensingcited by 9
  13. 2021Communication-Efficient Federated Learning via Predictive Codingcited by 5
  14. 2024Version age-based client scheduling policy for federated learningcited by 5
  15. 2022Over-the-Air Computation for Distributed Systems: Something Old and Something Newcited by 4
  16. 2025Age-Based Device Selection and Transmit Power Optimization in Over-the-Air Federated Learningcited by 3
  17. 2021Compressing gradients by exploiting temporal correlation in momentum-SGDcited by 2
  18. 2024Temporal Predictive Coding for Gradient Compression in Distributed Learningcited by 2

Built on by

Not cited yet.