Resource Allocation for Federated Learning With Highly Distorted Model

Information loss has emerged and escalated as the information bottleneck of a deep encryption model surpasses the entropy of the data and reduces the data reconstruction efficiency at the decoder (i.e., lossy compression and high data encryption). Therefore, existing communication-effective federate...

Full description

Saved in:
Bibliographic Details
Main Authors: Ryu Junewoo, Nguyen Xuan Tung, Minh-Duong Nguyen, Quang-Vinh do, Won-Joo Hwang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10946888/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731110144049152
author Ryu Junewoo
Nguyen Xuan Tung
Minh-Duong Nguyen
Quang-Vinh do
Won-Joo Hwang
author_facet Ryu Junewoo
Nguyen Xuan Tung
Minh-Duong Nguyen
Quang-Vinh do
Won-Joo Hwang
author_sort Ryu Junewoo
collection DOAJ
description Information loss has emerged and escalated as the information bottleneck of a deep encryption model surpasses the entropy of the data and reduces the data reconstruction efficiency at the decoder (i.e., lossy compression and high data encryption). Therefore, existing communication-effective federated learning (FL) approaches (e.g., model quantization, data sparsification, and model compression) incurred a considerable trade-off between communication efficiency and global convergence rate when an extreme encryption rate is applied. Nonetheless, the trade-off becomes less severe as the FL network expands. By utilizing this fact, we formulate an optimization problem for encryption-aided FL that captures the relationship between the distortion rate, the number of participating Internet-of-Things (IoT) devices, and the convergence rate. The purpose of the formulated FL optimization problem is to simultaneously optimize both the energy efficiency and the FL performance at once while using various model encryption techniques. Thereafter, our theoretical analysis shows that by actively controlling the number of participating IoT devices, we can avoid the training divergence of encryption-assisted FL while maintaining communication efficiency.
format Article
id doaj-art-4544e77d8d9c44ae9475be3ca01e252a
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-4544e77d8d9c44ae9475be3ca01e252a2025-08-20T03:08:40ZengIEEEIEEE Access2169-35362025-01-0113631086311910.1109/ACCESS.2025.355678010946888Resource Allocation for Federated Learning With Highly Distorted ModelRyu Junewoo0Nguyen Xuan Tung1https://orcid.org/0000-0002-1945-8658Minh-Duong Nguyen2https://orcid.org/0000-0001-9856-2754Quang-Vinh do3https://orcid.org/0000-0002-6899-2347Won-Joo Hwang4https://orcid.org/0000-0001-8398-564XSchool of Computer Science and Engineering, Pusan National University, Busan, Republic of KoreaSchool of Computer Science and Engineering, Pusan National University, Busan, Republic of KoreaSchool of Computer Science and Engineering, Pusan National University, Busan, Republic of KoreaFaculty of Electrical and Electronics Engineering, Ton Duc Thang University, Ho Chi Minh City, VietnamSchool of Computer Science and Engineering, Pusan National University, Busan, Republic of KoreaInformation loss has emerged and escalated as the information bottleneck of a deep encryption model surpasses the entropy of the data and reduces the data reconstruction efficiency at the decoder (i.e., lossy compression and high data encryption). Therefore, existing communication-effective federated learning (FL) approaches (e.g., model quantization, data sparsification, and model compression) incurred a considerable trade-off between communication efficiency and global convergence rate when an extreme encryption rate is applied. Nonetheless, the trade-off becomes less severe as the FL network expands. By utilizing this fact, we formulate an optimization problem for encryption-aided FL that captures the relationship between the distortion rate, the number of participating Internet-of-Things (IoT) devices, and the convergence rate. The purpose of the formulated FL optimization problem is to simultaneously optimize both the energy efficiency and the FL performance at once while using various model encryption techniques. Thereafter, our theoretical analysis shows that by actively controlling the number of participating IoT devices, we can avoid the training divergence of encryption-assisted FL while maintaining communication efficiency.https://ieeexplore.ieee.org/document/10946888/Communication efficiencydata encryptionfederated learningIoTresource allocation
spellingShingle Ryu Junewoo
Nguyen Xuan Tung
Minh-Duong Nguyen
Quang-Vinh do
Won-Joo Hwang
Resource Allocation for Federated Learning With Highly Distorted Model
IEEE Access
Communication efficiency
data encryption
federated learning
IoT
resource allocation
title Resource Allocation for Federated Learning With Highly Distorted Model
title_full Resource Allocation for Federated Learning With Highly Distorted Model
title_fullStr Resource Allocation for Federated Learning With Highly Distorted Model
title_full_unstemmed Resource Allocation for Federated Learning With Highly Distorted Model
title_short Resource Allocation for Federated Learning With Highly Distorted Model
title_sort resource allocation for federated learning with highly distorted model
topic Communication efficiency
data encryption
federated learning
IoT
resource allocation
url https://ieeexplore.ieee.org/document/10946888/
work_keys_str_mv AT ryujunewoo resourceallocationforfederatedlearningwithhighlydistortedmodel
AT nguyenxuantung resourceallocationforfederatedlearningwithhighlydistortedmodel
AT minhduongnguyen resourceallocationforfederatedlearningwithhighlydistortedmodel
AT quangvinhdo resourceallocationforfederatedlearningwithhighlydistortedmodel
AT wonjoohwang resourceallocationforfederatedlearningwithhighlydistortedmodel