Learning to Transmit with Provable Guarantees in Wireless Federated Learning

Abstract

We propose a novel data-driven approach to allocate transmit power for federated learning (FL) over interference-limited wireless networks. The proposed method is useful in challenging scenarios where the wireless channel is changing during the FL training process and when the training data are not independent and identically distributed (non-i.i.d.) on the local devices. Intuitively, the power policy is designed to optimize the information received at the server end during the FL process under communication constraints. Ultimately, our goal is to improve the accuracy and efficiency of the global FL model being trained. The proposed power allocation policy is parameterized using graph convolutional networks (GCNs), and the associated constrained optimization problem is solved through a primal-dual (PD) algorithm. Theoretically, we show that the formulated problem has a zero duality gap and, once the power policy is parameterized, optimality depends on how expressive this parameterization is. Numerically, we demonstrate that the proposed method outperforms existing baselines under different wireless channel settings and varying degrees of data heterogeneity.

References in corpus (17)

• Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networks
• Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
• Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
• Multi-Armed Bandit Based Client Scheduling for Federated Learning
• Learning Optimal Resource Allocations in Wireless Systems
• Super-resolution channel estimation for mmWave massive MIMO with hybrid precoding
• A Unified Successive Pseudo-Convex Approximation Framework
• A Globally Optimal Energy-Efficient Power Control Framework and its Efficient Implementation in Wireless Interference Networks
• Parallel Successive Convex Approximation for Nonsmooth Nonconvex Optimization
• Communication Efficiency in Federated Learning: Achievements and Challenges
• Link Scheduling using Graph Neural Networks
• Optimal Joint Subcarrier and Power Allocation in NOMA is Strongly NP-Hard
• Graph-based Algorithm Unfolding for Energy-aware Power Allocation in Wireless Networks
• Federated Learning for Internet of Things: Applications, Challenges, and Opportunities
• Communication-Efficient Robust Federated Learning Over Heterogeneous Datasets
• Optimization of Weighted Individual Energy Efficiencies in Interference Network
• Power Allocation for Wireless Federated Learning using Graph Neural Networks