AOP: Towards Adaptive Offloading Point Approach in a Federated Learning Framework for Edge AI Applications

The study discusses challenges in deploying Artificial Intelligence (AI) on Internet-of-Things (IoT) devices and introduces a solution called Adaptive Offloading Point (AOP) for Federated Learning (FL) in Edge AI. AOP accelerates local training on resource-constrained devices and uses reinforcement...

Full description

Saved in:
Bibliographic Details
Main Authors: Khoa, Tran Anh, Nguyen, Do-Van, Dao, Minh-Son, Zettsu, Koji
Format: Conference Proceeding
Language:English
Subjects:
Adaptation models
Adaptive offloading point
Artificial neural networks
Data privacy
Edge AI
Federated learning
Image edge detection
Parallel processing
Reinforcement learning
Training
Transformer
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The study discusses challenges in deploying Artificial Intelligence (AI) on Internet-of-Things (IoT) devices and introduces a solution called Adaptive Offloading Point (AOP) for Federated Learning (FL) in Edge AI. AOP accelerates local training on resource-constrained devices and uses reinforcement learning-based clustering (RL) to determine which deep neural network (DNN) layers to offload to the server. Test results show that, in the VIT transformer model, AOP significantly reduces training time compared to classical FL and the baseline method called FedAdapt, making it a promising solution for Edge AI applications.
ISSN:2690-5965
DOI:10.1109/ICPADS60453.2023.00403