Personalized federated adaptive regularization for heterogeneous medical image classification: COVID-19 CT results
Lists
Only you see this
Abstract
During outbreaks of large infectious diseases like COVID-19, there is a strain on healthcare resources worldwide. To alleviate the burden on healthcare workers during the initial stages of the outbreak, there is an urgent need for the development of automated tools. Federated learning offers a privacypreserving solution to the challenge that limited annotated data within single healthcare facilities. However, existing federated aggregation strategies cannot adapt to the real-world medical image data problem of mixed heterogeneous. This paper introduces Personalized Federated Adaptive Regularization (pFedAR), an adaptive framework for federated learning that effectively utilizes multi-site COVID-19 CT datasets with mixed heterogeneous of distribution discrepancies. To solve the mixed distribution of label skew and feature shift, we propose a two-stage adaptive regularization. In the client training stage, we use the balance loss term to balance the COVID-19 clients with missing label. In the aggregation stage, we correct the client gradient conflict. Our method is developed and evaluated using eight real-world COVID-19 diagnosis datasets composed of CT images. Extensive experiments demonstrate the consistent improvement achieved by our method across the datasets.
BibTeX
@inproceedings{liu2023personalized,
author = {Yuan Liu and Zhe Qu and Shu Wang and Tao Sheng and Xiaoqing Yu and Jian-xin Wang},
title = {{Personalized federated adaptive regularization for heterogeneous medical image classification: COVID-19 CT results}},
booktitle = {BIBM},
year = {2023},
url = {https://openreview.net/forum?id=HK0a2aAGnb},
}Loading related content...