PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Mächler, L.* ; Ezhov, I.* ; Shit, S.* ; Paetzold, J.C.

FedPIDAvg: A PID Controller Inspired Aggregation Method for Federated Learning.

In:. Berlin [u.a.]: Springer, 2023. 209-217 (Lect. Notes Comput. Sc. ; 14092 LNCS)
DOI
Open Access Green as soon as Postprint is submitted to ZB.
This paper presents FedPIDAvg, the winning submission to the Federated Tumor Segmentation Challenge 2022 (FETS22). Inspired by FedCostWAvg, our winning contribution to FETS21, we contribute an improved aggregation strategy for federated and collaborative learning. FedCostWAvg is a weighted averaging method that not only considers the number of training samples of each cluster but also the size of the drop of the respective cost function in the last federated round. This can be interpreted as the derivative part of a PID controller (proportional-integral-derivative controller). In FedPIDAvg, we further add the missing integral term. Another key challenge was the vastly varying size of data samples per center. We addressed this by modeling the data center sizes as following a Poisson distribution and choosing the training iterations per center accordingly. Our method outperformed all other submissions.
Altmetric
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Conference contribution
Keywords Brain Tumor Segmentation ; Control ; Federated Learning ; Machine Learning ; Miccai Challenges ; Mri ; Multi-modal Medical Imaging
Language english
Publication Year 2023
HGF-reported in Year 2023
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Journal Lecture Notes in Computer Science
Quellenangaben Volume: 14092 LNCS, Issue: , Pages: 209-217 Article Number: , Supplement: ,
Publisher Springer
Publishing Place Berlin [u.a.]
Institute(s) Institute for Tissue Engineering and Regenerative Medicine (ITERM)
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-505800-001
Grants Graduate School of Bioengineering, Technical University of Munich
International Graduate School of Science and Engineering (IGSSE)
Technical University of Munich -Institute for Advanced Study - German Excellence Initiative
Translational Brain Imaging Training Network (TRABIT) under the European Union's 'Horizon 2020' research & innovation program
DCoMEX project - Federal Ministry of Education and Research of Germany
'Ecole normale superieure in Paris
DOI 10.1007/978-3-031-44153-0_20
WOS ID 001206018200020
Scopus ID 85185721597
Erfassungsdatum 2024-03-08
[➜Report correction]