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

TL;DR

This paper introduces a robust federated learning framework that combines confidence-weighted filtering and GAN-based data completion to effectively handle noisy, incomplete, and imbalanced data across decentralized clients, improving model performance while preserving privacy.

Contribution

It presents a novel federated learning approach that systematically addresses data quality issues using adaptive noise filtering, GAN-based synthetic data generation, and robust training methods.

Findings

Significant performance improvements on MNIST and Fashion-MNIST datasets.

Effective mitigation of noise, class imbalance, and missing labels.

Maintains data privacy and computational efficiency for edge devices.

Abstract

Federated learning (FL) presents an effective solution for collaborative model training while maintaining data privacy across decentralized client datasets. However, data quality issues such as noisy labels, missing classes, and imbalanced distributions significantly challenge its effectiveness. This study proposes a federated learning methodology that systematically addresses data quality issues, including noise, class imbalance, and missing labels. The proposed approach systematically enhances data integrity through adaptive noise cleaning, collaborative conditional GAN-based synthetic data generation, and robust federated model training. Experimental evaluations conducted on benchmark datasets (MNIST and Fashion-MNIST) demonstrate significant improvements in federated model performance, particularly macro-F1 Score, under varying noise and class imbalance conditions. Additionally, the proposed framework carefully balances computational feasibility and substantial performance gains, ensuring practicality for resource constrained edge devices while rigorously maintaining data privacy. Our results indicate that this method effectively mitigates common data quality challenges, providing a robust, scalable, and privacy compliant solution suitable for diverse real-world federated learning scenarios.