• Home
  • Search
  • Adaptive Batch Size for Federated Learning in Resource-Constrained Edge Computing
  • Cite Icon93
  • https://doi.org/10.1109/tmc.2021.3075291Copy DOI Icon

Adaptive Batch Size for Federated Learning in Resource-Constrained Edge Computing

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The emerging Federated Learning (FL) enables IoT devices to collaboratively learn a shared model based on their local datasets. However, due to end devices’ heterogeneity, it will magnify the inherent synchronization barrier issue of FL and result in non-negligible waiting time when local models are trained with the identical batch size. Moreover, the useless waiting time will further lead to a great strain on devices’ limited battery life. Herein, we aim to alleviate the negative impact of synchronization barrier through adaptive batch size during model training. When using different batch sizes, stability and convergence of the global model should be enforced by assigning appropriate learning rates on different devices. Therefore, we first study the relationship between batch size and learning rate, and formulate a scaling rule to guide the setting of learning rate in terms of batch size. Then we theoretically analyze the convergence rate of global model and obtain a convergence upper bound. On these bases, we propose an efficient algorithm that adaptively adjusts batch size with scaled learning rate for heterogeneous devices to reduce the waiting time and save battery life. We conduct extensive simulations and testbed experiments, and the experimental results demonstrate the effectiveness of our method.

Similar Papers
  • Research Article

Energy-Efficient Adaptive Batching for Federated Learning Via Gradient Noise Scale Measurement in Mobile Edge Computing Networks

  • Jan 01, 2025
  • IEEE Transactions on Mobile Computing
  • Guozeng Xu +5
  • Research Article
  • Citations37

Privacy-Preserving Asynchronous Grouped Federated Learning for IoT

  • Apr 01, 2022
  • IEEE Internet of Things Journal
  • Tao Zhang +4
  • Research Article
  • Citations392

Convergence Time Optimization for Federated Learning Over Wireless Networks

  • Dec 11, 2020
  • IEEE Transactions on Wireless Communications
  • Mingzhe Chen +3
  • Conference Article
  • Citations18

TIFF: Tokenized Incentive for Federated Learning

  • Jul 01, 2022
  • Jingoo Han +7
  • Research Article
  • Citations5

Trusted Clustering Based Federated Learning in Edge Networks

  • Oct 01, 2025
  • IEEE Transactions on Mobile Computing
  • Yi-Jing Liu +6
  • Conference Article
  • Citations9

Research on Model Optimization Technology of Federated Learning

  • Mar 03, 2023
  • Hang Dai +1
  • Research Article
  • Citations13

Privacy-preserving detection and classification of diabetic retinopathy using federated learning with FedDEO optimization

  • Dec 07, 2024
  • Systems Science & Control Engineering
  • Dasari Bhulakshmi +1
  • Research Article
  • Citations29

BPFL: Blockchain-based privacy-preserving federated learning against poisoning attack

  • Feb 29, 2024
  • Information Sciences
  • Yanli Ren +4
  • Research Article
  • Citations3

Enforcing Differential Privacy in Federated Learning via Long-Term Contribution Incentives

  • Jan 01, 2025
  • IEEE Transactions on Information Forensics and Security
  • Xiangyun Tang +5
  • Research Article
  • Citations14

Wirelessly Powered Federated Learning Networks: Joint Power Transfer, Data Sensing, Model Training, and Resource Allocation

  • Nov 01, 2024
  • IEEE Internet of Things Journal
  • Mai Le +4
  • PDF
  • Research Article
  • Citations13

Hyperparameter Tuning and Automatic Image Augmentation for Deep Learning-Based Angle Classification on Intraoral Photographs-A Retrospective Study.

  • Jun 23, 2022
  • Diagnostics (Basel, Switzerland)
  • José Eduardo Cejudo Grano De Oro +6
  • Conference Article
  • Citations58

Distributed Rate Optimization for Intelligent Reflecting Surface with Federated Learning

  • Jun 01, 2020
  • Donghui Ma +5
  • Research Article
  • Citations4

FedMarket: A Cryptocurrency Driven Marketplace for Mobile Federated Learning Services

  • Jan 01, 2022
  • IEEE Access
  • Abdullah Yousafzai +4
  • PDF
  • Research Article
  • Citations17

Towards Convergence in Federated Learning via Non-IID Analysis in a Distributed Solar Energy Grid

  • Mar 27, 2023
  • Electronics
  • Hyeongok Lee
  • Research Article
  • Citations21

Ensemble Distillation Based Adaptive Quantization for Supporting Federated Learning in Wireless Networks

  • Jun 01, 2023
  • IEEE Transactions on Wireless Communications
  • Yi-Jing Liu +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.