Personalized Retrogress-Resilient Framework for Real-World Medical Federated Learning

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationMedical Image Computing and Computer Assisted Intervention – MICCAI 2021
Subtitle of host publication24th International Conference Strasbourg, France, September 27 – October 1, 2021 Proceedings, Part III
EditorsMarleen de Bruijne, Philippe C. Cattin, Stéphane Cotin, Nicolas Padoy, Stefanie Speidel, Yefeng Zheng, Caroline Essert
PublisherSpringer, Cham
Pages347-356
ISBN (Electronic)978-3-030-87199-4
ISBN (Print)978-3-030-87198-7
Publication statusPublished - 2021

Publication series

NameLecture Notes in Computer Science (including subseries Image Processing, Computer Vision, Pattern Recognition, and Graphics)
Volume12903
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Title24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021)
LocationVirtual
PlaceFrance
CityStrasbourg
Period27 September - 1 October 2021

Abstract

Nowadays, deep learning methods with large-scale datasets can produce clinically useful models for computer-aided diagnosis. However, the privacy and ethical concerns are increasingly critical, which make it difficult to collect large quantities of data from multiple institutions. Federated Learning (FL) provides a promising decentralized solution to train model collaboratively by exchanging client models instead of private data. However, the server aggregation of existing  FL methods is observed to degrade the model performance in real world medical FL setting, which is termed as retrogress. To address this problem, we propose a personalized retrogress-resilient frame work to produce a superior personalized model for each client. Specifically, we devise a Progressive Fourier Aggregation (PFA) at the server to achieve more stable and effective global knowledge gathering by integrating client models from low-frequency to high-frequency gradually.  Moreover, with an introduced deputy model to receive the aggregated server model, we design a Deputy-Enhanced Transfer (DET) strategy at the client and conduct three steps of Recover-Exchange-Sublimate to ameliorate the personalized local model by transferring the global knowledge smoothly. Extensive experiments on real-world dermoscopic FL dataset prove that our personalized retrogress-resilient framework out performs state-of-the-art FL methods, as well as the generalization on an out-of-distribution cohort. The code and dataset are available athttps://github.com/CityU-AIM-Group/PRR-FL.

Research Area(s)

  • Federated learning, Skin lesions, Parameters aggregation

Citation Format(s)

Personalized Retrogress-Resilient Framework for Real-World Medical Federated Learning. / Chen, Zhen; Zhu, Meilu; Yang, Chen; Yuan, Yixuan.

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021: 24th International Conference Strasbourg, France, September 27 – October 1, 2021 Proceedings, Part III. ed. / Marleen de Bruijne; Philippe C. Cattin; Stéphane Cotin; Nicolas Padoy; Stefanie Speidel; Yefeng Zheng; Caroline Essert. Springer, Cham, 2021. p. 347-356 (Lecture Notes in Computer Science (including subseries Image Processing, Computer Vision, Pattern Recognition, and Graphics); Vol. 12903).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review