Unsupervised Graph-based Learning Method for Sub-band Allocation in 6G Subnetworks

Daniel Abode, Ramoni Adeogun, Lou Salaün, Renato Abreu, Thomas Jacobsen +1 more
12/13/2023
cs.NIcs.LGeess.SY

No official code found. Best implementation: abodedaniel/Unsupervised-Graph-Coloring-using-Gated-Graph-Neural-Network (0 stars, last commit 2025-01-02).

Abstract

In this paper, we present an unsupervised approach for frequency sub-band allocation in wireless networks using graph-based learning. We consider a dense deployment of subnetworks in the factory environment with a limited number of sub-bands which must be optimally allocated to coordinate inter-subnetwork interference. We model the subnetwork deployment as a conflict graph and propose an unsupervised learning approach inspired by the graph colouring heuristic and the Potts model to optimize the sub-band allocation using graph neural networks. The numerical evaluation shows that the proposed method achieves close performance to the centralized greedy colouring sub-band allocation heuristic with lower computational time complexity. In addition, it incurs reduced signalling overhead compared to iterative optimization heuristics that require all the mutual interfering channel information. We further demonstrate that the method is robust to different network settings.

View on arXivView PDF

Code Implementations(1)

abodedaniel/Unsupervised-Graph-Coloring-using-Gated-Graph-Neural-NetworkCommunity100%

In this repo, we show an unsupervised graph coloring method using gated graph neural network. The graph coloring problem is formulated as a multi-class node classification problem. The graph neural models are based on pytorch geometric library.

00Python, Jupyter NotebookDec 16, 20241 years ago

Similar Papers

GNN-Based Joint Channel and Power Allocation in Heterogeneous Wireless Networks

81% match1 repo42024

Graph Neural Networks for Power Allocation in Wireless Networks with Full Duplex Nodes

80% match2023

Graph Neural Networks-Based User Pairing in Wireless Communication Systems

80% match1 repo122023

Distributed Link Sparsification for Scalable Scheduling Using Graph Neural Networks (Journal Version)

80% match2025

Graph Neural Network-Based Bandwidth Allocation for Secure Wireless Communications

80% match2023

Multi-Agent Reinforcement Learning for Multi-Cell Spectrum and Power Allocation

80% match2023

Cite this paper

@article{abode2023unsupervised,
  title  = {Unsupervised Graph-based Learning Method for Sub-band Allocation in 6G Subnetworks},
  author = {Daniel Abode and Ramoni Adeogun and Lou Salaün and Renato Abreu and Thomas Jacobsen and Gilberto Berardinelli},
  year   = {2023},
  eprint = {2401.00950},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2401.00950v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2401.00950.svg)](https://codeofpaper.com/paper/2401.00950)

Discussion