Sharing non-reversible data statistics for fast and secure Federated learning native to Extreme Learning Machine

Anton Akusok; Leonardo Espinosa-Leal; Kaj-Mikael Björk

doi:10.1145/3652037.3663891

Sharing non-reversible data statistics for fast and secure Federated learning native to Extreme Learning Machine

Anton Akusok, Leonardo Espinosa-Leal, Kaj-Mikael Björk

Not published at VTT

Arcada University of Applied Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

Extreme Learning Machine (ELM) is a fast and simple machine learning method with an exact solution. This work presents its integration into conventional federated learning frameworks that preserve the method’s native property of a non-iterative and exact solution in data-distributed systems. Low computational complexity and data privacy features make federated ELM a good candidate for on-device computing in privacy-sensitive applications.

Original language	English
Title of host publication	PETRA '24: Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments
Place of Publication	New York
Publisher	Association for Computing Machinery ACM
Pages	674-675
Number of pages	2
ISBN (Electronic)	9798400717604
ISBN (Print)	979-8-4007-1760-4
DOIs	https://doi.org/10.1145/3652037.3663891
Publication status	Published - 26 Jun 2024
MoE publication type	A4 Article in a conference publication
Event	PETRA '24: The PErvasive Technologies Related to Assistive Environments Conference - Crete, Greece Duration: 26 Jun 2024 → 28 Jun 2024

Conference

Conference	PETRA '24: The PErvasive Technologies Related to Assistive Environments Conference
Country/Territory	Greece
City	Crete
Period	26/06/24 → 28/06/24

Keywords

Extreme Learning Machine
Federated learning
One-shot learning
Secure Federated Learning

Access to Document

10.1145/3652037.3663891

Cite this

Akusok, A., Espinosa-Leal, L., & Björk, K.-M. (2024). Sharing non-reversible data statistics for fast and secure Federated learning native to Extreme Learning Machine. In PETRA '24: Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments (pp. 674-675). Association for Computing Machinery ACM. https://doi.org/10.1145/3652037.3663891

@inproceedings{01d4d1e239844f29aa5323f6ebfa8682,

title = "Sharing non-reversible data statistics for fast and secure Federated learning native to Extreme Learning Machine",

abstract = "Extreme Learning Machine (ELM) is a fast and simple machine learning method with an exact solution. This work presents its integration into conventional federated learning frameworks that preserve the method{\textquoteright}s native property of a non-iterative and exact solution in data-distributed systems. Low computational complexity and data privacy features make federated ELM a good candidate for on-device computing in privacy-sensitive applications.",

keywords = "Extreme Learning Machine, Federated learning, One-shot learning, Secure Federated Learning",

author = "Anton Akusok and Leonardo Espinosa-Leal and Kaj-Mikael Bj{\"o}rk",

year = "2024",

month = jun,

day = "26",

doi = "10.1145/3652037.3663891",

language = "English",

isbn = "979-8-4007-1760-4",

pages = "674--675",

booktitle = "PETRA '24: Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments",

publisher = "Association for Computing Machinery ACM",

address = "United States",

note = "PETRA '24: The PErvasive Technologies Related to Assistive Environments Conference ; Conference date: 26-06-2024 Through 28-06-2024",

}

Akusok, A, Espinosa-Leal, L & Björk, K-M 2024, Sharing non-reversible data statistics for fast and secure Federated learning native to Extreme Learning Machine. in PETRA '24: Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments. Association for Computing Machinery ACM, New York, pp. 674-675, PETRA '24: The PErvasive Technologies Related to Assistive Environments Conference, Crete, Greece, 26/06/24. https://doi.org/10.1145/3652037.3663891

Sharing non-reversible data statistics for fast and secure Federated learning native to Extreme Learning Machine. / Akusok, Anton; Espinosa-Leal, Leonardo; Björk, Kaj-Mikael.
PETRA '24: Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments. New York: Association for Computing Machinery ACM, 2024. p. 674-675.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Sharing non-reversible data statistics for fast and secure Federated learning native to Extreme Learning Machine

AU - Akusok, Anton

AU - Espinosa-Leal, Leonardo

AU - Björk, Kaj-Mikael

PY - 2024/6/26

Y1 - 2024/6/26

N2 - Extreme Learning Machine (ELM) is a fast and simple machine learning method with an exact solution. This work presents its integration into conventional federated learning frameworks that preserve the method’s native property of a non-iterative and exact solution in data-distributed systems. Low computational complexity and data privacy features make federated ELM a good candidate for on-device computing in privacy-sensitive applications.

AB - Extreme Learning Machine (ELM) is a fast and simple machine learning method with an exact solution. This work presents its integration into conventional federated learning frameworks that preserve the method’s native property of a non-iterative and exact solution in data-distributed systems. Low computational complexity and data privacy features make federated ELM a good candidate for on-device computing in privacy-sensitive applications.

KW - Extreme Learning Machine

KW - Federated learning

KW - One-shot learning

KW - Secure Federated Learning

UR - http://www.scopus.com/inward/record.url?scp=85198092345&partnerID=8YFLogxK

U2 - 10.1145/3652037.3663891

DO - 10.1145/3652037.3663891

M3 - Conference article in proceedings

SN - 979-8-4007-1760-4

SP - 674

EP - 675

BT - PETRA '24: Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments

PB - Association for Computing Machinery ACM

CY - New York

T2 - PETRA '24: The PErvasive Technologies Related to Assistive Environments Conference

Y2 - 26 June 2024 through 28 June 2024

ER -

Akusok A, Espinosa-Leal L, Björk KM. Sharing non-reversible data statistics for fast and secure Federated learning native to Extreme Learning Machine. In PETRA '24: Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments. New York: Association for Computing Machinery ACM. 2024. p. 674-675 doi: 10.1145/3652037.3663891

Sharing non-reversible data statistics for fast and secure Federated learning native to Extreme Learning Machine

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this