TY - JOUR
T1 - Personalized Retrogress-Resilient Federated Learning Toward Imbalanced Medical Data
AU - Chen, Zhen
AU - Yang, Chen
AU - Zhu, Meilu
AU - Peng, Zhe
AU - Yuan, Yixuan
N1 - This work was supported in part by the Shenzhen-Hong Kong Innovation Circle Category D Project under Grant SGDX2019081623300177 (CityU 9240008) and in part by the Guangdong Basic and Applied Basic Research Foundation under Grant 2020A1515111070.
Publisher Copyright:
© 1982-2012 IEEE.
PY - 2022/12
Y1 - 2022/12
N2 - Clinically oriented deep learning algorithms, combined with large-scale medical datasets, have significantly promoted computer-aided diagnosis. To address increasing ethical and privacy issues, Federated Learning (FL) adopts a distributed paradigm to collaboratively train models, rather than collecting samples from multiple institutions for centralized training. Despite intensive research on FL, two major challenges are still existing when applying FL in the real-world medical scenarios, including the performance degradation (i.e., retrogress) after each communication and the intractable class imbalance. Thus, in this paper, we propose a novel personalized FL framework to tackle these two problems. For the retrogress problem, we first devise a Progressive Fourier Aggregation (PFA) at the server side to gradually integrate parameters of client models in the frequency domain. Then, at the client side, we design a Deputy-Enhanced Transfer (DET) to smoothly transfer global knowledge to the personalized local model. For the class imbalance problem, we propose the Conjoint Prototype-Aligned (CPA) loss to facilitate the balanced optimization of the FL framework. Considering the inaccessibility of private local data to other participants in FL, the CPA loss calculates the global conjoint objective based on global imbalance, and then adjusts the client-side local training through the prototype-aligned refinement to eliminate the imbalance gap with such a balanced goal. Extensive experiments are performed on real-world dermoscopic and prostate MRI FL datasets. The experimental results demonstrate the advantages of our FL framework in real-world medical scenarios, by outperforming state-of-the-art FL methods with a large margin. The source code is available at https://github.com/CityU-AIM-Group/PRR-Imbalancehttps://github.com/CityU-AIM-Group/PRR-Imbalance.
AB - Clinically oriented deep learning algorithms, combined with large-scale medical datasets, have significantly promoted computer-aided diagnosis. To address increasing ethical and privacy issues, Federated Learning (FL) adopts a distributed paradigm to collaboratively train models, rather than collecting samples from multiple institutions for centralized training. Despite intensive research on FL, two major challenges are still existing when applying FL in the real-world medical scenarios, including the performance degradation (i.e., retrogress) after each communication and the intractable class imbalance. Thus, in this paper, we propose a novel personalized FL framework to tackle these two problems. For the retrogress problem, we first devise a Progressive Fourier Aggregation (PFA) at the server side to gradually integrate parameters of client models in the frequency domain. Then, at the client side, we design a Deputy-Enhanced Transfer (DET) to smoothly transfer global knowledge to the personalized local model. For the class imbalance problem, we propose the Conjoint Prototype-Aligned (CPA) loss to facilitate the balanced optimization of the FL framework. Considering the inaccessibility of private local data to other participants in FL, the CPA loss calculates the global conjoint objective based on global imbalance, and then adjusts the client-side local training through the prototype-aligned refinement to eliminate the imbalance gap with such a balanced goal. Extensive experiments are performed on real-world dermoscopic and prostate MRI FL datasets. The experimental results demonstrate the advantages of our FL framework in real-world medical scenarios, by outperforming state-of-the-art FL methods with a large margin. The source code is available at https://github.com/CityU-AIM-Group/PRR-Imbalancehttps://github.com/CityU-AIM-Group/PRR-Imbalance.
KW - class imbalance
KW - dermoscopic diagnosis
KW - Federated learning
KW - prostate segmentation
KW - retrogress
UR - http://www.scopus.com/inward/record.url?scp=85135218970&partnerID=8YFLogxK
UR - https://ieeexplore.ieee.org/document/9832948
U2 - 10.1109/TMI.2022.3192483
DO - 10.1109/TMI.2022.3192483
M3 - Journal article
C2 - 35853071
AN - SCOPUS:85135218970
SN - 0278-0062
VL - 41
SP - 3663
EP - 3674
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
IS - 12
ER -