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

arXiv: https://arxiv.org/abs/2603.09859 · HTML: https://mlsanity.com/paper/2603.09859/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 20 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 3 of 3)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Graph Construction with Flexible Nodes for Traffic Demand Prediction](https://mlsanity.com/paper/2403.00276/) (2024)
- [Systematic Literature Review of AI-enabled Spectrum Management in 6G and Future Networks](https://mlsanity.com/paper/2407.10981/) (2024)

## Built on by (most cited first, 1 of 1)

- [TD-STGT: A Spatio-Temporal Graph Transformer for Mobile Traffic Demand Forecasting](https://mlsanity.com/paper/2609.06636/) (2026)

## Abstract (arXiv)

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.