Research

Paper

TESTING March 10, 2026

A Graph-Based Approach to Spectrum Demand Prediction Using Hierarchical Attention Networks

Authors

Mohamad Alkadamani, Halim Yanikomeroglu, Amir Ghasemi

Abstract

The surge in wireless connectivity demand, coupled with the finite nature of spectrum resources, compels the development of efficient spectrum management approaches. Spectrum sharing presents a promising avenue, although it demands precise characterization of spectrum demand for informed policy-making. This paper introduces HR-GAT, a hierarchical resolution graph attention network model, designed to predict spectrum demand using geospatial data. HR-GAT adeptly handles complex spatial demand patterns and resolves issues of spatial autocorrelation that usually challenge standard machine learning models, often resulting in poor generalization. Tested across five major Canadian cities, HR-GAT improves predictive accuracy of spectrum demand by 21% over eight baseline models, underscoring its superior performance and reliability.

Metadata

arXiv ID: 2603.09859
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09859v1</id>\n    <title>A Graph-Based Approach to Spectrum Demand Prediction Using Hierarchical Attention Networks</title>\n    <updated>2026-03-10T16:20:51Z</updated>\n    <link href='https://arxiv.org/abs/2603.09859v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09859v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>The surge in wireless connectivity demand, coupled with the finite nature of spectrum resources, compels the development of efficient spectrum management approaches. Spectrum sharing presents a promising avenue, although it demands precise characterization of spectrum demand for informed policy-making. This paper introduces HR-GAT, a hierarchical resolution graph attention network model, designed to predict spectrum demand using geospatial data. HR-GAT adeptly handles complex spatial demand patterns and resolves issues of spatial autocorrelation that usually challenge standard machine learning models, often resulting in poor generalization. Tested across five major Canadian cities, HR-GAT improves predictive accuracy of spectrum demand by 21% over eight baseline models, underscoring its superior performance and reliability.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.NI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.SY'/>\n    <published>2026-03-10T16:20:51Z</published>\n    <arxiv:comment>7 pages, 6 figures. Presented at IEEE GLOBECOM 2025, Taiwan. To appear in the conference proceedings</arxiv:comment>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Mohamad Alkadamani</name>\n    </author>\n    <author>\n      <name>Halim Yanikomeroglu</name>\n    </author>\n    <author>\n      <name>Amir Ghasemi</name>\n    </author>\n  </entry>"
}