FedSLD: Federated Learning with Shared Label Distribution for Medical Image Classification
This work addresses the challenge of poor model generalizability due to non-IID data distributions in federated learning for medical centers, representing an incremental improvement in optimization techniques.
The paper tackles the problem of data heterogeneity in federated learning for medical image classification by proposing FedSLD, which uses shared label distribution to adjust sample contributions, resulting in up to a 5.50 percentage point increase in test accuracy compared to leading methods.
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.