Meta-FL: A Novel Meta-Learning Framework for Optimizing Heterogeneous Model Aggregation in Federated Learning
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910499500720128 |
|---|---|
| author | Alsulaimawi, Zahir |
| author_facet | Alsulaimawi, Zahir |
| contents | Federated Learning (FL) enables collaborative model training across diverse entities while safeguarding data privacy. However, FL faces challenges such as data heterogeneity and model diversity. The Meta-Federated Learning (Meta-FL) framework has been introduced to tackle these challenges. Meta-FL employs an optimization-based Meta-Aggregator to navigate the complexities of heterogeneous model updates. The Meta-Aggregator enhances the global model's performance by leveraging meta-features, ensuring a tailored aggregation that accounts for each local model's accuracy. Empirical evaluation across four healthcare-related datasets demonstrates the Meta-FL framework's adaptability, efficiency, scalability, and robustness, outperforming conventional FL approaches. Furthermore, Meta-FL's remarkable efficiency and scalability are evident in its achievement of superior accuracy with fewer communication rounds and its capacity to manage expanding federated networks without compromising performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_16035 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Meta-FL: A Novel Meta-Learning Framework for Optimizing Heterogeneous Model Aggregation in Federated Learning Alsulaimawi, Zahir Machine Learning Cryptography and Security Federated Learning (FL) enables collaborative model training across diverse entities while safeguarding data privacy. However, FL faces challenges such as data heterogeneity and model diversity. The Meta-Federated Learning (Meta-FL) framework has been introduced to tackle these challenges. Meta-FL employs an optimization-based Meta-Aggregator to navigate the complexities of heterogeneous model updates. The Meta-Aggregator enhances the global model's performance by leveraging meta-features, ensuring a tailored aggregation that accounts for each local model's accuracy. Empirical evaluation across four healthcare-related datasets demonstrates the Meta-FL framework's adaptability, efficiency, scalability, and robustness, outperforming conventional FL approaches. Furthermore, Meta-FL's remarkable efficiency and scalability are evident in its achievement of superior accuracy with fewer communication rounds and its capacity to manage expanding federated networks without compromising performance. |
| title | Meta-FL: A Novel Meta-Learning Framework for Optimizing Heterogeneous Model Aggregation in Federated Learning |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2406.16035 |