FedGiA: An Efficient Hybrid Algorithm for Federated Learning

Abstract

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.

arXiv admin note: substantial text overlap with arXiv:2110.15318; text overlap with arXiv:2204.10607

References in corpus (6)

• Mobile Edge Computing: A Survey on Architecture and Computation Offloading
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Distributed Reinforcement Learning for Privacy-Preserving Dynamic Edge Caching
• Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning
• Differentially Private Federated Learning via Inexact ADMM with Multiple Local Updates
• Federated Nonconvex Sparse Learning