Debunking Optimization Myths in Federated Learning for Medical Image Classification
This work addresses robustness issues in Federated Learning for medical imaging, providing insights for practitioners, but it is incremental as it revisits and clarifies existing optimization myths rather than introducing new methods.
The study tackled the problem of sensitivity to local factors like optimizers and learning rates in Federated Learning for medical image classification, finding that edge device configurations have a greater impact on performance than the specific FL method, with concrete numerical evidence on colorectal pathology and blood cell classification tasks.
Federated Learning (FL) is a collaborative learning method that enables decentralized model training while preserving data privacy. Despite its promise in medical imaging, recent FL methods are often sensitive to local factors such as optimizers and learning rates, limiting their robustness in practical deployments. In this work, we revisit vanilla FL to clarify the impact of edge device configurations, benchmarking recent FL methods on colorectal pathology and blood cell classification task. We numerically show that the choice of local optimizer and learning rate has a greater effect on performance than the specific FL method. Moreover, we find that increasing local training epochs can either enhance or impair convergence, depending on the FL method. These findings indicate that appropriate edge-specific configuration is more crucial than algorithmic complexity for achieving effective FL.