Home > Research > Publications & Outputs > PPFM

Electronic data

  • cynthia-PPFM

    Rights statement: ©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 581 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

PPFM: An Adaptive and Hierarchical Peer-to-Peer Federated Meta-Learning Framework

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

PPFM: An Adaptive and Hierarchical Peer-to-Peer Federated Meta-Learning Framework. / Yu, Zhengxin; Lu, Yang; Angelov, Plamen et al.
2022 18th International Conference on Mobility, Sensing and Networking (MSN). IEEE, 2023. p. 502-509.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Yu, Z, Lu, Y, Angelov, P & Suri, N 2023, PPFM: An Adaptive and Hierarchical Peer-to-Peer Federated Meta-Learning Framework. in 2022 18th International Conference on Mobility, Sensing and Networking (MSN). IEEE, pp. 502-509, 18th International Conference on Mobility, Sensing and Networking (MSN 2022), Guangzhou, China, 14/12/22. https://doi.org/10.1109/MSN57253.2022.00086

APA

Yu, Z., Lu, Y., Angelov, P., & Suri, N. (2023). PPFM: An Adaptive and Hierarchical Peer-to-Peer Federated Meta-Learning Framework. In 2022 18th International Conference on Mobility, Sensing and Networking (MSN) (pp. 502-509). IEEE. https://doi.org/10.1109/MSN57253.2022.00086

Vancouver

Yu Z, Lu Y, Angelov P, Suri N. PPFM: An Adaptive and Hierarchical Peer-to-Peer Federated Meta-Learning Framework. In 2022 18th International Conference on Mobility, Sensing and Networking (MSN). IEEE. 2023. p. 502-509 Epub 2022 Dec 14. doi: 10.1109/MSN57253.2022.00086

Author

Yu, Zhengxin ; Lu, Yang ; Angelov, Plamen et al. / PPFM : An Adaptive and Hierarchical Peer-to-Peer Federated Meta-Learning Framework. 2022 18th International Conference on Mobility, Sensing and Networking (MSN). IEEE, 2023. pp. 502-509

Bibtex

@inproceedings{1d039336972945a9bf135a44f83ab735,
title = "PPFM: An Adaptive and Hierarchical Peer-to-Peer Federated Meta-Learning Framework",
abstract = "With the advancement in Machine Learning (ML) techniques, a wide range of applications that leverage ML have emerged across research, industry, and society to improve application performance. However, existing ML schemes used within such applications struggle to attain high model accuracy due to the heterogeneous and distributed nature of their generated data, resulting in reduced model performance. In this paper we address this challenge by proposing PPFM: an adaptive and hierarchical Peer-to-Peer Federated Meta-learning framework. Instead of leveraging a conventional static ML scheme, PPFM uses multiple learning loops to dynamically self-adapt its own architecture to improve its training effectiveness for different generated data characteristics. Such an approach also allows for PPFM to remove reliance on a fixed centralized server in a distributed environment by utilizing peer-to-peer Federated Learning (FL) framework. Our results demonstrate PPFM provides significant improvement to model accuracy across multiple datasets when compared to contemporary ML approaches.",
author = "Zhengxin Yu and Yang Lu and Plamen Angelov and Neeraj Suri",
note = "{\textcopyright}2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. ; 18th International Conference on Mobility, Sensing and Networking (MSN 2022), MSN 2022 ; Conference date: 14-12-2022 Through 16-12-2022",
year = "2023",
month = mar,
day = "29",
doi = "10.1109/MSN57253.2022.00086",
language = "English",
isbn = "9781665464581",
pages = "502--509",
booktitle = "2022 18th International Conference on Mobility, Sensing and Networking (MSN)",
publisher = "IEEE",
url = "https://ieee-msn.org/2022/",

}

RIS

TY - GEN

T1 - PPFM

T2 - 18th International Conference on Mobility, Sensing and Networking (MSN 2022)

AU - Yu, Zhengxin

AU - Lu, Yang

AU - Angelov, Plamen

AU - Suri, Neeraj

N1 - Conference code: 18th

PY - 2023/3/29

Y1 - 2023/3/29

N2 - With the advancement in Machine Learning (ML) techniques, a wide range of applications that leverage ML have emerged across research, industry, and society to improve application performance. However, existing ML schemes used within such applications struggle to attain high model accuracy due to the heterogeneous and distributed nature of their generated data, resulting in reduced model performance. In this paper we address this challenge by proposing PPFM: an adaptive and hierarchical Peer-to-Peer Federated Meta-learning framework. Instead of leveraging a conventional static ML scheme, PPFM uses multiple learning loops to dynamically self-adapt its own architecture to improve its training effectiveness for different generated data characteristics. Such an approach also allows for PPFM to remove reliance on a fixed centralized server in a distributed environment by utilizing peer-to-peer Federated Learning (FL) framework. Our results demonstrate PPFM provides significant improvement to model accuracy across multiple datasets when compared to contemporary ML approaches.

AB - With the advancement in Machine Learning (ML) techniques, a wide range of applications that leverage ML have emerged across research, industry, and society to improve application performance. However, existing ML schemes used within such applications struggle to attain high model accuracy due to the heterogeneous and distributed nature of their generated data, resulting in reduced model performance. In this paper we address this challenge by proposing PPFM: an adaptive and hierarchical Peer-to-Peer Federated Meta-learning framework. Instead of leveraging a conventional static ML scheme, PPFM uses multiple learning loops to dynamically self-adapt its own architecture to improve its training effectiveness for different generated data characteristics. Such an approach also allows for PPFM to remove reliance on a fixed centralized server in a distributed environment by utilizing peer-to-peer Federated Learning (FL) framework. Our results demonstrate PPFM provides significant improvement to model accuracy across multiple datasets when compared to contemporary ML approaches.

U2 - 10.1109/MSN57253.2022.00086

DO - 10.1109/MSN57253.2022.00086

M3 - Conference contribution/Paper

SN - 9781665464581

SP - 502

EP - 509

BT - 2022 18th International Conference on Mobility, Sensing and Networking (MSN)

PB - IEEE

Y2 - 14 December 2022 through 16 December 2022

ER -