mlsanityData to 7 Oct 2026

Accelerating Asynchronous Federated Learning Convergence via Opportunistic Mobile Relaying

arXiv 2206.04742 ↗First posted 9 Jun 2022cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

This paper presents a study on asynchronous Federated Learning (FL) in a mobile network setting. The majority of FL algorithms assume that communication between clients and the server is always available, however, this is not the case in many real-world systems. To address this issue, the paper explores the impact of mobility on the convergence performance of asynchronous FL. By exploiting mobility, the study shows that clients can indirectly communicate with the server through another client serving as a relay, creating additional communication opportunities. This enables clients to upload local model updates sooner or receive fresher global models. We propose a new FL algorithm, called FedMobile, that incorporates opportunistic relaying and addresses key questions such as when and how to relay. We prove that FedMobile achieves a convergence rate O(frac1√NT), where N is the number of clients and T is the number of communication slots, and show that the optimal design involves an interesting trade-off on the best timing of relaying. The paper also presents an extension that considers data manipulation before relaying to reduce the cost and enhance privacy. Experiment results on a synthetic dataset and two real-world datasets verify our theoretical findings.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 9 Jun 2022.

Builds on

29 of 44 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  5. 2017Federated Multi-Task Learningcited by 669
  6. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  7. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  8. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 277
  9. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  10. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 192
  11. 2019Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computationscited by 179
  12. 2017Revisiting Distributed Synchronous SGDcited by 142
17 more
  1. 2019SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentumcited by 121
  2. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retrainingcited by 109
  3. 2016Asynchronous Stochastic Gradient Descent with Delay Compensationcited by 98
  4. 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 95
  5. 2019Peer-to-peer Federated Learning on Graphscited by 85
  6. 2020Privacy-preserving Traffic Flow Prediction: A Federated Learning Approachcited by 82
  7. 2019Accelerating Federated Learning via Momentum Gradient Descentcited by 75
  8. 2020FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tierscited by 64
  9. 2020Wireless Communications for Collaborative Federated Learningcited by 47
  10. 2020Decentralized Federated Learning via SGD over Wireless D2D Networkscited by 32
  11. 2016Asynchrony begets Momentum, with an Application to Deep Learningcited by 30
  12. 2018Toward Understanding the Impact of Staleness in Distributed Machine Learningcited by 28
  13. 2020Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noisecited by 21
  14. 2022Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realizationcited by 16
  15. 2021Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradientscited by 13
  16. 2013A Survey on Device-to-Device Communication in Cellular Networkscited by 10
  17. 2016Omnivore: An Optimizer for Multi-device Deep Learning on CPUs and GPUscited by 6

Built on by

Cited by year

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

6 papers.

  1. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  2. 2024Prioritizing Modalities: Flexible Importance Scheduling in Federated Multimodal Learningcited by 4
  3. 2023Joint Client Assignment and UAV Route Planning for Indirect-Communication Federated Learningcited by 1
  4. 2025Distribution-Aware Mobility-Assisted Decentralized Federated Learningcited by 1
  5. 2025Analysis of Asynchronous Federated Learning: Unraveling the Interactions between Gradient Compression, Delay, and Data Heterogeneitycited by 0
  6. 2025Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsificationcited by 0