Meta-FL: A Novel Meta-Learning Framework for Optimizing Heterogeneous Model Aggregation in Federated Learning

TL;DR

Meta-FL introduces a meta-learning framework for federated learning that effectively manages model heterogeneity and improves global model performance through a specialized meta-aggregator, demonstrating superior results in healthcare datasets.

Contribution

The paper presents Meta-FL, a novel meta-learning framework with a meta-aggregator that enhances federated learning by addressing data and model heterogeneity.

Findings

Outperforms traditional FL methods in accuracy.

Requires fewer communication rounds for convergence.

Maintains robustness and scalability in large networks.

Abstract

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.