Power Allocation for Wireless Federated Learning using Graph Neural Networks

TL;DR

This paper introduces a graph neural network-based power allocation strategy for wireless federated learning, enhancing transmission success and model accuracy under interference constraints.

Contribution

It presents a novel data-driven power allocation method using graph neural networks and primal-dual optimization for federated learning over wireless networks.

Findings

Outperforms baseline methods in transmission success rate

Improves global model accuracy and efficiency

Demonstrates effectiveness through numerical experiments

Abstract

We propose a data-driven approach for power allocation in the context of federated learning (FL) over interference-limited wireless networks. The power policy is designed to maximize the transmitted information during the FL process under communication constraints, with the ultimate objective of improving the accuracy and efficiency of the global FL model being trained. The proposed power allocation policy is parameterized using a graph convolutional network and the associated constrained optimization problem is solved through a primal-dual algorithm. Numerical experiments show that the proposed method outperforms three baseline methods in both transmission success rate and FL global performance.