Power Allocation for Wireless Federated Learning Using Graph Neural Networks
Boning Li, Ananthram Swami, Santiago Segarra
2022ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)15 citationsDOI
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.
Topics & Concepts
Computer scienceParameterized complexityWireless networkGraphWirelessContext (archaeology)Dual (grammatical number)Power (physics)Baseline (sea)Mathematical optimizationArtificial intelligenceDistributed computingTheoretical computer scienceAlgorithmTelecommunicationsMathematicsBiologyOceanographyLiteraturePhysicsPaleontologyGeologyArtQuantum mechanicsPrivacy-Preserving Technologies in DataCooperative Communication and Network CodingWireless Networks and Protocols