Saved in:
Bibliographic Details
Main Authors: Lyu, Qing, Vu, Mai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.05241
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913878475014144
author Lyu, Qing
Vu, Mai
author_facet Lyu, Qing
Vu, Mai
contents Machine learning (ML) models can effectively optimize a multi-cell wireless network by designing the beamforming vectors and association decisions. Existing ML designs, however, often needs to approximate the integer association variables with a probability distribution output. We propose a novel graph neural network (GNN) structure that jointly optimize beamforming vectors and user association while guaranteeing association output as integers. The integer association constraints are satisfied using the Gumbel-Softmax (GS) reparameterization, without increasing computational complexity. Simulation results demonstrate that our proposed GS-based GNN consistently achieves integer association decisions and yields a higher sum-rate, especially when generalized to larger networks, compared to all other fractional association methods.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05241
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Joint Beamforming and Integer User Association using a GNN with Gumbel-Softmax Reparameterizations
Lyu, Qing
Vu, Mai
Signal Processing
Machine learning (ML) models can effectively optimize a multi-cell wireless network by designing the beamforming vectors and association decisions. Existing ML designs, however, often needs to approximate the integer association variables with a probability distribution output. We propose a novel graph neural network (GNN) structure that jointly optimize beamforming vectors and user association while guaranteeing association output as integers. The integer association constraints are satisfied using the Gumbel-Softmax (GS) reparameterization, without increasing computational complexity. Simulation results demonstrate that our proposed GS-based GNN consistently achieves integer association decisions and yields a higher sum-rate, especially when generalized to larger networks, compared to all other fractional association methods.
title Joint Beamforming and Integer User Association using a GNN with Gumbel-Softmax Reparameterizations
topic Signal Processing
url https://arxiv.org/abs/2506.05241