Revisit the Stability of Vanilla Federated Learning Under Diverse Conditions
This work provides a practical baseline for resource-constrained hospitals using federated learning, though it is incremental as it reassesses an existing method.
The paper revisits the stability of the vanilla FedAvg algorithm in federated learning, finding that it maintains robust performance across diverse datasets, models, and hyperparameter settings, making it a reliable choice for medical applications.
Federated Learning (FL) is a distributed machine learning paradigm enabling collaborative model training across decentralized clients while preserving data privacy. In this paper, we revisit the stability of the vanilla FedAvg algorithm under diverse conditions. Despite its conceptual simplicity, FedAvg exhibits remarkably stable performance compared to more advanced FL techniques. Our experiments assess the performance of various FL methods on blood cell and skin lesion classification tasks using Vision Transformer (ViT). Additionally, we evaluate the impact of different representative classification models and analyze sensitivity to hyperparameter variations. The results consistently demonstrate that, regardless of dataset, classification model employed, or hyperparameter settings, FedAvg maintains robust performance. Given its stability, robust performance without the need for extensive hyperparameter tuning, FedAvg is a safe and efficient choice for FL deployments in resource-constrained hospitals handling medical data. These findings underscore the enduring value of the vanilla FedAvg approach as a trusted baseline for clinical practice.