mlsanityData to 14 Oct 2026

Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsification

arXiv 2506.07328 ↗First posted 8 Jun 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Asynchronous Federated Learning (AFL) enables distributed model training across multiple mobile devices, allowing each device to independently update its local model without waiting for others. However, device mobility introduces intermittent connectivity, which necessitates gradient sparsification and leads to model staleness, jointly affecting AFL convergence. This paper develops a theoretical model to characterize the interplay among sparsification, model staleness and mobility-induced contact patterns, and their joint impact on AFL convergence. Based on the analysis, we propose a mobility-aware dynamic sparsification (MADS) algorithm that optimizes the sparsification degree based on contact time and model staleness. Closed-form solutions are derived, showing that under low-speed conditions, MADS increases the sparsification degree to enhance convergence, while under high-speed conditions, it reduces the sparsification degree to guarantee reliable uploads within limited contact time. Experimental results validate the theoretical findings. Compared with the state-of-the-art benchmarks, the MADS algorithm increases the image classification accuracy on the CIFAR-10 dataset by 8.76% and reduces the average displacement error in the Argoverse trajectory prediction dataset by 9.46%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 61 references that are in the map. First posted on arXiv 8 Jun 2025.

Builds on

33 of 61 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  3. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  4. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  5. 2018Sparsified SGD with Memorycited by 376
  6. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 263
  7. 2017Gradient Sparsification for Communication-Efficient Distributed Optimizationcited by 201
  8. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  9. 2019Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computationscited by 181
  10. 2019A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problemscited by 160
  11. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
  12. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 129
21 more
  1. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 107
  2. 2021Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applicationscited by 97
  3. 2020Scheduling for Cellular Federated Edge Learning with Importance and Channel Awarenesscited by 62
  4. 2020Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applicationscited by 62
  5. 2022Edge Learning for B5G Networks with Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensingcited by 56
  6. 2021Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraintscited by 36
  7. 2021Mobility-Aware Cluster Federated Learning in Hierarchical Wireless Networkscited by 35
  8. 2019High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learningcited by 32
  9. 2021Time-Correlated Sparsification for Communication-Efficient Federated Learningcited by 26
  10. 2022Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networkscited by 20
  11. 2021Adaptive Transmission Scheduling in Wireless Networks for Asynchronous Federated Learningcited by 15
  12. 2020Edge Learning with Timeliness Constraints: Challenges and Solutionscited by 11
  13. 2022Federated Learning via Unmanned Aerial Vehiclecited by 11
  14. 2024Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networkscited by 11
  15. 2022Accelerating Asynchronous Federated Learning Convergence via Opportunistic Mobile Relayingcited by 6
  16. 2022MEET: Mobility-Enhanced Edge inTelligence for Smart and Green 6G Networkscited by 5
  17. 2019Exploiting Moving Intelligence: Delay-Optimized Computation Offloading in Vehicular Fog Networkscited by 3
  18. 2022Dynamic Clustering and Power Control for Two-Tier Wireless Federated Learningcited by 3
  19. 2024UAV-Enabled Asynchronous Federated Learningcited by 3
  20. 2024Dynamic Scheduling for Vehicle-to-Vehicle Communications Enhanced Federated Learningcited by 3
  21. 2016Mobility-Aware Caching in D2D Networkscited by 2

Built on by

Not cited yet.