Meta-FL: A Novel Meta-Learning Framework for Optimizing Heterogeneous Model Aggregation in Federated Learning
It addresses challenges in federated learning for healthcare applications, but appears incremental as it builds on existing FL methods with a novel aggregation technique.
The paper tackles the problem of data heterogeneity and model diversity in federated learning by introducing the Meta-FL framework, which uses a Meta-Aggregator to optimize model aggregation, resulting in superior accuracy with fewer communication rounds across four healthcare datasets.
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.