TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publication References
  4. MatchCurv: communication-efficient decentralized federated learning in heterogeneous environments
 
Options

MatchCurv: communication-efficient decentralized federated learning in heterogeneous environments

Publikationstyp
Conference Paper
Date Issued
2024
Sprache
English
Author(s)
Dussa, Harsha Praneeth
Haberer, Janek  
Landsiedel, Olaf  
TORE-URI
https://hdl.handle.net/11420/61637
Citation
1st Workshop on Enabling Machine Learning Operations for next-Gen Embedded Wireless Networked Devices (2024) at the 22nd International Conference on Embedded Wireless Systems and Networks, (EWSN 2025)
Contribution to Conference
1st Workshop on Enabling Machine Learning Operations for next-Gen Embedded Wireless Networked Devices (2024)  
22nd International Conference on Embedded Wireless Systems and Networks, (EWSN 2025)  
Publisher Link
https://ewsn.org/file-repository/ewsn2024/emerge24-final23.pdf
Scopus ID
2-s2.0-85218247524
Federated learning offers a privacy-preserving method for training machine learning models. Yet, traditional centralized federated learning has drawbacks like single points of failure and communication bottlenecks. While decentralized federated learning has been proposed to overcome these limitations, challenges such as statistical and system heterogeneity remain. Whereas most works focus on solving only one of these challenges, this paper introduces MatchCurv, a decentralized federated learning framework designed to handle statistical and system heterogeneity while improving communication efficiency. In our evaluation, for example, a multi-layer perceptron with two hidden layers of 128 units each shows a significant accuracy increase when using our framework compared to PD-SGD, achieving up to 17 percentage points more accuracy. The source code is available at https://github.com/ds-kiel/matchcurv.
Subjects
Decentralized Federated Learning
Deep Learning
FedCurv
Federated Learning
MATCHA
MLE@TUHH
DDC Class
600: Technology
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback