FedCime: An Efficient Federated Learning Approach For Clients in Mobile Edge Computing

Federated learning (FL) enables collaborative training of a global model using localized data from multiple devices. However, in resource-constrained mobile edge computing (MEC) environments, non-independent and identically distributed (non-IID) data generated by these devices poses challenges for t...

Full description

Saved in:
Bibliographic Details
Main Authors: Agbaje, Paul, Anjum, Afia, Talukder, Zahidur, Islam, Mohammad, Nwafor, Ebelechukwu, Olufowobi, Habeeb
Format: Conference Proceeding
Language:English
Subjects:
Computational modeling
data heterogeneity
Data models
Distributed databases
Federated learning
Heuristic algorithms
machine learning
mobile edge computing
Multi-access edge computing
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Federated learning (FL) enables collaborative training of a global model using localized data from multiple devices. However, in resource-constrained mobile edge computing (MEC) environments, non-independent and identically distributed (non-IID) data generated by these devices poses challenges for traditional FL algorithms like Federated Averaging (FedAvg), leading to decreased accuracy of the global model. In addition, dynamic mobile networks with intermittent connectivity, dropouts, and high migration rates hinder the communication of model updates to the central server. To address these challenges, we present FedCime, a novel tier-based FL approach that selects high-utility mobile clients likely to complete training to replace migrating clients during the round of training. Our evaluation shows that FedCime is scalable and significantly improves training performance in terms of accuracy and computational efficiency compared to state-of-the-art FL algorithms.
ISSN:2767-9918
DOI:10.1109/EDGE60047.2023.00042