FedSLD: Federated Learning with Shared Label Distribution for Medical Image Classification

TL;DR

FedSLD is a federated learning method that leverages shared label distribution knowledge to improve model training stability and accuracy across heterogeneous medical image datasets, addressing data privacy and distribution challenges.

Contribution

This work introduces FedSLD, a novel federated learning approach that utilizes shared label distribution information to mitigate data heterogeneity issues in medical image classification.

Findings

FedSLD outperforms existing FL algorithms in convergence speed.

Test accuracy improves by up to 5.50 percentage points with FedSLD.

Effective on four diverse non-IID medical image datasets.

Abstract

Machine learning in medical research, by nature, needs careful attention on obeying the regulations of data privacy, making it difficult to train a machine learning model over gathered data from different medical centers. Failure of leveraging data of the same kind may result in poor generalizability for the trained model. Federated learning (FL) enables collaboratively training a joint model while keeping the data decentralized for multiple medical centers. However, federated optimizations often suffer from the heterogeneity of the data distribution across medical centers. In this work, we propose Federated Learning with Shared Label Distribution (FedSLD) for classification tasks, a method that assumes knowledge of the label distributions for all the participating clients in the federation. FedSLD adjusts the contribution of each data sample to the local objective during optimization given knowledge of the distribution, mitigating the instability brought by data heterogeneity across all clients. We conduct extensive experiments on four publicly available image datasets with different types of non-IID data distributions. Our results show that FedSLD achieves better convergence performance than the compared leading FL optimization algorithms, increasing the test accuracy by up to 5.50 percentage points.