Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yang, Q., Liu, Y., Cheng, Y., Kang, Y., Chen, T., Yu, H.: Federated learning. Synth. Lect. Artif. Intell. Mach. Learn. 13(3), 1–207 (2019)
Li, L., Fan, Y., Tse, M., Lin, K.Y.: A review of applications in federated learning. Comput. Ind. Eng. 149, 106854 (2020)
Rieke, N., et al.: The future of digital health with federated learning. NPJ Digital Med. 3(1), 1–7 (2020)
Healthcareitnews.com: Tens of thousands of patient records posted to dark web. https://www.healthcareitnews.com/news/tens-thousands-patient-records-posted-dark-web. Accessed 16 Jul 2021
Bakas, S., et al.: Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci. Data 4(1), 1–13 (2017)
Pati, S., et al.: The federated tumor segmentation (Fets) challenge. arXiv preprint arXiv:2105.05874 (2021)
Reina, G.A., et al.: OpenFL: an open-source framework for federated learning. arXiv preprint arXiv:2105.06413 (2021)
Sheller, M.J., et al.: Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Sci. Rep. 10(1), 1–12 (2020)
Baid, U., et al.: The RSNA-ASNR-MICCAI brats 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv preprint arXiv:2107.02314 (2021)
McMahan, B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial intelligence and statistics, pp. 1273–1282. PMLR (2017)
Mächler, L., et al.: FedCostWAvg: a new averaging for better federated learning. arXiv preprint arXiv:2111.08649 (2021)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2014)
Todorov, M.I., et al.: Machine learning analysis of whole mouse brain vasculature. Nat. Methods 17(4), 442–449 (2020)
Shit, S., et al.: clDice - a topology-preserving loss function for tubular structure segmentation. CoRR abs/2003.07311 (2020)
Acknowledgements
We appreciate the valuable input from our supervisors, David Naccache, Adrian Dalca, and Bjoern Menze. Moreover, we want to express our appreciation to the organizers of the Federated Tumor Segmentation Challenge 2022. Leon Mächler is supported by the École normale supérieure in Paris. Johannes C. Paetzold is supported by the DCoMEX project, financed by the Federal Ministry of Education and Research of Germany. Suprosanna Shit and Ivan Ezhov are supported by the Translational Brain Imaging Training Network (TRABIT) under the European Union’s ‘Horizon 2020’ research & innovation program (Grant agreement ID: 765148). With the support of the Technical University of Munich - Institute for Advanced Study, funded by the German Excellence Initiative. Ivan Ezhov is also supported by the International Graduate School of Science and Engineering (IGSSE). Johannes C. Paetzold and Suprosanna Shit are supported by the Graduate School of Bioengineering, Technical University of Munich.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mächler, L., Ezhov, I., Shit, S., Paetzold, J.C. (2023). FedPIDAvg: A PID Controller Inspired Aggregation Method for Federated Learning. In: Bakas, S., et al. Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2022. Lecture Notes in Computer Science, vol 14092. Springer, Cham. https://doi.org/10.1007/978-3-031-44153-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-44153-0_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44152-3
Online ISBN: 978-3-031-44153-0
eBook Packages: Computer ScienceComputer Science (R0)
