FedGiA: An Efficient Hybrid Algorithm for Federated Learning
This work addresses efficiency and convergence issues in federated learning, which is crucial for distributed machine learning applications, but it appears incremental as it builds on existing methods.
The authors tackled the challenges of communication and computational efficiency in federated learning by proposing FedGiA, a hybrid algorithm combining gradient descent and inexact alternating direction method of multipliers, which achieves better efficiency than state-of-the-art methods and guarantees global convergence under mild conditions.
Federated learning has shown its advances recently but is still facing many challenges, such as how algorithms save communication resources and reduce computational costs, and whether they converge. To address these critical issues, we propose a hybrid federated learning algorithm (FedGiA) that combines the gradient descent and the inexact alternating direction method of multipliers. The proposed algorithm is more communication- and computation-efficient than several state-of-the-art algorithms theoretically and numerically. Moreover, it also converges globally under mild conditions.