FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise

TL;DR

FedGSCA is a robust federated learning framework for medical image classification that effectively handles label noise and data heterogeneity through global sample selection and adaptive client adjustments, improving stability and accuracy.

Contribution

This paper introduces FedGSCA, a novel federated learning framework with a global sample selector and client adaptive adjustment to combat label noise in medical data.

Findings

Outperforms state-of-the-art methods under various noise conditions.

Enhances model stability and generalization in noisy federated learning.

Effectively handles extreme and heterogeneous label noise scenarios.

Abstract

Federated Learning (FL) emerged as a solution for collaborative medical image classification while preserving data privacy. However, label noise, which arises from inter-institutional data variability, can cause training instability and degrade model performance. Existing FL methods struggle with noise heterogeneity and the imbalance in medical data. Motivated by these challenges, we propose FedGSCA, a novel framework for enhancing robustness in noisy medical FL. FedGSCA introduces a Global Sample Selector that aggregates noise knowledge from all clients, effectively addressing noise heterogeneity and improving global model stability. Furthermore, we develop a Client Adaptive Adjustment (CAA) mechanism that combines adaptive threshold pseudo-label generation and Robust Credal Labeling Loss. CAA dynamically adjusts to class distributions, ensuring the inclusion of minority samples and carefully managing noisy labels by considering multiple plausible labels. This dual approach mitigates the impact of noisy data and prevents overfitting during local training, which improves the generalizability of the model. We evaluate FedGSCA on one real-world colon slides dataset and two synthetic medical datasets under various noise conditions, including symmetric, asymmetric, extreme, and heterogeneous types. The results show that FedGSCA outperforms the state-of-the-art methods, excelling in extreme and heterogeneous noise scenarios. Moreover, FedGSCA demonstrates significant advantages in improving model stability and handling complex noise, making it well-suited for real-world medical federated learning scenarios.