mlsanityData to 7 Oct 2026

Time-Correlated Sparsification for Efficient Over-the-Air Model Aggregation in Wireless Federated Learning

arXiv 2202.08420 ↗First posted 17 Feb 2022cs.IT cs.LG math.ITcited by 7

Not on the map. Why?

Abstract (arXiv)

Federated edge learning (FEEL) is a promising distributed machine learning (ML) framework to drive edge intelligence applications. However, due to the dynamic wireless environments and the resource limitations of edge devices, communication becomes a major bottleneck. In this work, we propose time-correlated sparsification with hybrid aggregation (TCS-H) for communication-efficient FEEL, which exploits jointly the power of model compression and over-the-air computation. By exploiting the temporal correlations among model parameters, we construct a global sparsification mask, which is identical across devices, and thus enables efficient model aggregation over-the-air. Each device further constructs a local sparse vector to explore its own important parameters, which are aggregated via digital communication with orthogonal multiple access. We further design device scheduling and power allocation algorithms for TCS-H. Experiment results show that, under limited communication resources, TCS-H can achieve significantly higher accuracy compared to the conventional top-K sparsification with orthogonal model aggregation, with both i.i.d. and non-i.i.d. data distributions.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 15 of its 20 references that are in the map. First posted on arXiv 17 Feb 2022.

Builds on

15 of 20 references.

References · 15

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  3. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 561
  4. 2018Sparsified SGD with Memorycited by 373
  5. 2019Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computationscited by 179
  6. 2019Federated Learning over Wireless Fading Channelscited by 178
  7. 2016QSGD: Communication-Efficient SGD via Gradient Quantization and Encodingcited by 147
  8. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
  9. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
  10. 2018Wireless Network Intelligence at the Edgecited by 90
  11. 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
  12. 2021Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraintscited by 34
3 more
  1. 2021Time-Correlated Sparsification for Communication-Efficient Federated Learningcited by 25
  2. 2020Edge Learning with Timeliness Constraints: Challenges and Solutionscited by 10
  3. 2021Temporal-Structure-Assisted Gradient Aggregation for Over-the-Air Federated Edge Learningcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 1; 2024: 2; 2025: 0; 2026: 1.

7 papers.

  1. 2024Dynamic Scheduling for Vehicle-to-Vehicle Communications Enhanced Federated Learningcited by 3
  2. 2022Communication-Efficient and Privacy-Preserving Feature-based Federated Transfer Learningcited by 2
  3. 2023Differentially Private Wireless Federated Learning Using Orthogonal Sequencescited by 1
  4. 2024Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and Privacycited by 1
  5. 2022Private Federated Submodel Learning with Sparsificationcited by 0
  6. 2022Random Orthogonalization for Federated Learning in Massive MIMO Systemscited by 0
  7. 2026Exploiting Correlations in Federated Learning: Opportunities and Practical Limitationscited by 0