Hier-FedMeta: A Hierarchical Federated Meta-Learning Framework for Personalized and Efficient IoV Systems

Yiming Chen; Celimuge Wu; Du Zhaoyang; Yangfei Lin; Soufiene Djahel; Lei Zhong

Hier-FedMeta: A Hierarchical Federated Meta-Learning Framework for Personalized and Efficient IoV Systems

Yiming Chen, Celimuge Wu, Du Zhaoyang, Yangfei Lin, Soufiene Djahel, Lei Zhong

Centre for Future Transport and Cities

Research output: Contribution to conference › Paper › peer-review

35 Downloads (Pure)

Abstract

The Internet of Vehicles (IoV) enhances smart city functionalities by interconnecting diverse components, yet it introduces significant challenges in terms of user privacy, communication efficiency, and energy consumption. Traditional federated learning frameworks, while adept at addressing these concerns, fall short in personalization due to heterogeneous data distributions among clients. To overcome this, we introduce Hier-FedMeta, a novel framework that combines hierarchical federated learning with meta-learning to provide tailored and efficient solutions. Our comparative analyses with four established methods show Hier-FedMeta’s superior generalization capabilities and adaptability, achieving enhanced performance with minimal computational overhead after just one update step. Furthermore, our in-depth analysis of aggregation parameters offers valuable insights for the optimization of hierarchical federated meta-learning architectures, representing a significant step forward in personalized learning for IoV in smart cities.

Original language	English
Pages	(In-Press)
Publication status	Accepted/In press - 12 Mar 2024
Event	2024 IEEE 99th Vehicular Technology Conference - , Singapore Duration: 24 Jun 2024 → 27 Jun 2024 https://events.vtsociety.org/vtc2024-spring/

Conference

Conference	2024 IEEE 99th Vehicular Technology Conference
Abbreviated title	VTC 2024 Spring
Country/Territory	Singapore
Period	24/06/24 → 27/06/24
Internet address	https://events.vtsociety.org/vtc2024-spring/

Bibliographical note

© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders.

This document is the author’s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it.

Funding

This research is supported in part by JST ASPIRE Grant Number JPMJAP2325, Japan, and ROIS NII Open Collaborative Research under Grant 24S0601, Japan.

Funders	Funder number
Japan Science and Technology Agency	JPMJAP2325
Research Organization of Information and Systems	24S0601

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

Djahel2024AAMAccepted author manuscript, 1.06 MB

Empowering Vehicular IoT with Collaborative Intelligence for Next Generation ITS
Djahel, S. (Principal Investigator)
1/04/21 → 31/08/22
Project: Research

Cite this

@conference{ab709931149947a992f7bfdb692d5ed7,

title = "Hier-FedMeta: A Hierarchical Federated Meta-Learning Framework for Personalized and Efficient IoV Systems",

abstract = "The Internet of Vehicles (IoV) enhances smart city functionalities by interconnecting diverse components, yet it introduces significant challenges in terms of user privacy, communication efficiency, and energy consumption. Traditional federated learning frameworks, while adept at addressing these concerns, fall short in personalization due to heterogeneous data distributions among clients. To overcome this, we introduce Hier-FedMeta, a novel framework that combines hierarchical federated learning with meta-learning to provide tailored and efficient solutions. Our comparative analyses with four established methods show Hier-FedMeta{\textquoteright}s superior generalization capabilities and adaptability, achieving enhanced performance with minimal computational overhead after just one update step. Furthermore, our in-depth analysis of aggregation parameters offers valuable insights for the optimization of hierarchical federated meta-learning architectures, representing a significant step forward in personalized learning for IoV in smart cities.",

author = "Yiming Chen and Celimuge Wu and Du Zhaoyang and Yangfei Lin and Soufiene Djahel and Lei Zhong",

note = "{\textcopyright} 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Copyright {\textcopyright} and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders. This document is the author{\textquoteright}s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it. ; 2024 IEEE 99th Vehicular Technology Conference, VTC 2024 Spring ; Conference date: 24-06-2024 Through 27-06-2024",

year = "2024",

month = mar,

day = "12",

language = "English",

pages = "(In--Press)",

url = "https://events.vtsociety.org/vtc2024-spring/",

}

TY - CONF

T1 - Hier-FedMeta

T2 - 2024 IEEE 99th Vehicular Technology Conference

AU - Chen, Yiming

AU - Wu, Celimuge

AU - Zhaoyang, Du

AU - Lin, Yangfei

AU - Djahel, Soufiene

AU - Zhong, Lei

N1 - © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders. This document is the author’s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it.

PY - 2024/3/12

Y1 - 2024/3/12

N2 - The Internet of Vehicles (IoV) enhances smart city functionalities by interconnecting diverse components, yet it introduces significant challenges in terms of user privacy, communication efficiency, and energy consumption. Traditional federated learning frameworks, while adept at addressing these concerns, fall short in personalization due to heterogeneous data distributions among clients. To overcome this, we introduce Hier-FedMeta, a novel framework that combines hierarchical federated learning with meta-learning to provide tailored and efficient solutions. Our comparative analyses with four established methods show Hier-FedMeta’s superior generalization capabilities and adaptability, achieving enhanced performance with minimal computational overhead after just one update step. Furthermore, our in-depth analysis of aggregation parameters offers valuable insights for the optimization of hierarchical federated meta-learning architectures, representing a significant step forward in personalized learning for IoV in smart cities.

AB - The Internet of Vehicles (IoV) enhances smart city functionalities by interconnecting diverse components, yet it introduces significant challenges in terms of user privacy, communication efficiency, and energy consumption. Traditional federated learning frameworks, while adept at addressing these concerns, fall short in personalization due to heterogeneous data distributions among clients. To overcome this, we introduce Hier-FedMeta, a novel framework that combines hierarchical federated learning with meta-learning to provide tailored and efficient solutions. Our comparative analyses with four established methods show Hier-FedMeta’s superior generalization capabilities and adaptability, achieving enhanced performance with minimal computational overhead after just one update step. Furthermore, our in-depth analysis of aggregation parameters offers valuable insights for the optimization of hierarchical federated meta-learning architectures, representing a significant step forward in personalized learning for IoV in smart cities.

M3 - Paper

SP - (In-Press)

Y2 - 24 June 2024 through 27 June 2024

ER -

Hier-FedMeta: A Hierarchical Federated Meta-Learning Framework for Personalized and Efficient IoV Systems

Abstract

Conference

Bibliographical note

Funding

UN SDGs

Access to Document

Fingerprint

Projects

Empowering Vehicular IoT with Collaborative Intelligence for Next Generation ITS

Cite this