Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909611169153024 |
|---|---|
| author | Gokcen, Alpaslan Boyaci, Ali |
| author_facet | Gokcen, Alpaslan Boyaci, Ali |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09733 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data Gokcen, Alpaslan Boyaci, Ali Machine Learning Artificial Intelligence Cryptography and Security 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. |
| title | Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data |
| topic | Machine Learning Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2505.09733 |