Revisit the Stability of Vanilla Federated Learning Under Diverse Conditions

TL;DR

This paper demonstrates that the simple FedAvg algorithm remains remarkably stable and robust across various datasets, models, and hyperparameters, making it a reliable choice for federated learning in medical applications.

Contribution

The study provides comprehensive empirical evidence that vanilla FedAvg maintains stability and performance across diverse conditions, reaffirming its suitability for resource-constrained clinical settings.

Findings

FedAvg shows consistent stability across datasets and models.

Robust performance without extensive hyperparameter tuning.

Suitable for resource-limited hospital environments.

Abstract

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.