<ul><li>Federated learning (FL) offers a solution for collaborative model training while preserving data privacy in decentralized client datasets.</li><li>Challenges like noisy labels, missing classes, and imbalanced distributions affect the effectiveness of FL.</li><li>A new methodology is proposed to address data quality issues in FL by enhancing data integrity through noise cleaning, synthetic data generation, and robust model training.</li><li>Experimental evaluations on MNIST and Fashion-MNIST datasets show improved model performance, especially in noise and class imbalance scenarios, ensuring data privacy and practicality for edge devices.</li></ul>

Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data

Discover more