Federated Learning for COVID-19 on Heterogeneous CXR Images with Noise
Lists
Only you see this
Abstract
In recent years, COVID-19 has spread rapidly around the world, leading to a global pandemic, which has become an unprecedented crisis for almost every country in the world. In this paper, we propose a novel federated learning (FL) algorithm to train a sensitivity-specificity-variable COVID-19 diagnosis model. By FL, patients' data stays at each hospital locally, and thus the privacy of patients is reserved. However, the commonly used FL algorithms, such as FedAvg cannot perform COVID-19 diagnosis efficiently because they did not consider the impact of noise and heterogeneity in the chest X-ray (CXR) data of different hospitals. Moreover, they commonly assumed that hospitals would voluntarily participate in FL without payments. To this end, our FL algorithm integrates a novel data selection module to distinguish participants having data with low noise, high representative distribution, and a payment scheme to incentivize each participant according to their contributions. Our contribution evaluation method is based on the Shapley value method widely applied in coalitional games. Compared to the existing works, our solution does not need to train models repeatedly, which significantly reduces the time and computation resource consumption, while achieving a competitive performance as shown in experiments.
BibTeX
@inproceedings{ding2023federated,
author = {Mengqing Ding and Juan Li and Changyan Yi and Jun Cai},
title = {{Federated Learning for COVID-19 on Heterogeneous CXR Images with Noise}},
booktitle = {ICC},
year = {2023},
url = {https://openreview.net/forum?id=BKg4re0Mbq},
}Loading related content...