The Impact Analysis of Delays in Asynchronous Federated Learning with Data Heterogeneity for Edge Intelligence
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) has provided a new methodology for coordinating a group of clients to train a machine learning model collaboratively, bringing an efficient paradigm in edge intelligence. Despite its promise, FL faces several critical challenges in practical applications involving edge devices, such as data heterogeneity and delays stemming from communication and computation constraints. This paper examines the impact of unknown causes of delay on training performance in an Asynchronous Federated Learning (AFL) system with data heterogeneity. Initially, an asynchronous error definition is proposed, based on which the solely adverse impact of data heterogeneity is theoretically analyzed within the traditional Synchronous Federated Learning (SFL) framework. Furthermore, Asynchronous Updates with Delayed Gradients (AUDG), a conventional AFL scheme, is discussed. Investigation into AUDG reveals that the negative influence of data heterogeneity is correlated with delays, while a shorter average delay from a specific client does not consistently enhance training performance. In order to compensate for the scenarios where AUDG are not adapted, Pseudo-synchronous Updates by Reusing Delayed Gradients (PSURDG) is proposed, and its theoretical convergence is analyzed. In both AUDG and PSURDG, only a random set of clients successfully transmits their updated results to the central server in each iteration. The critical difference between them lies in whether the delayed information is reused. Finally, both schemes are validated and compared through theoretical analysis and simulations, demonstrating more intuitively that discarding outdated information due to time delays is not always the best approach.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 6 Mar 2025.
Builds on
22 of 38 references.
References · 22
- 2018Federated Learning with Non-IID Datacited by 1,108
- 2018Federated Learning for Mobile Keyboard Predictioncited by 572
- 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
- 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 352
- 2021Federated Learning on Non-IID Data: A Surveycited by 346
- 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 305
- 2019Asynchronous Federated Optimizationcited by 267
- 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
- 2020Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challengescited by 139
- 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 96
- 2021Asynchronous Federated Learning on Heterogeneous Devices: A Surveycited by 93
- 2021GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learningcited by 74
10 more
- 2020Convergence of Update Aware Device Scheduling for Federated Learning at the Wireless Edgecited by 71
- 2020Fast-Convergent Federated Learning with Adaptive Weightingcited by 67
- 2020Inverse Distance Aggregation for Federated Learning with Non-IID Datacited by 44
- 2021Scaling Federated Learning for Fine-tuning of Large Language Modelscited by 36
- 2020Edge Intelligence for Autonomous Driving in 6G Wireless System: Design Challenges and Solutionscited by 22
- 2022Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networkscited by 20
- 2023HiFlash: Communication-Efficient Hierarchical Federated Learning with Adaptive Staleness Control and Heterogeneity-aware Client-Edge Associationcited by 17
- 2023Time-sensitive Learning for Heterogeneous Federated Edge Intelligencecited by 8
- 2021Device Scheduling and Update Aggregation Policies for Asynchronous Federated Learningcited by 7
- 2022Broadband Digital Over-the-Air Computation for Wireless Federated Edge Learningcited by 6
Built on by
Citing papers per year: 2025: 1.
1 paper.