Joint Beamforming and Integer User Association using a GNN with Gumbel-Softmax Reparameterizations

2025/06/05 by Qing Lyu, Lyu, Qing, Mai Vu +1 · 1 citation
Engineering · Computer Science · #Advanced MIMO Systems Optimization #Millimeter-Wave Propagation and Modeling #Wireless Signal Modulation Classification

paper · pdf · doi:10.48550/arxiv.2506.05241

Abstract

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.

Citations

• Graph Neural Network Based Beamforming and RIS Reflection Design in A Multi-RIS Assisted Wireless Network
• Soft Actor-Critic With Integer Actions
• GBLinks: GNN-Based Beam Selection and Link Activation for Ultra-dense D2D mmWave Networks
• Deep Learning Optimized Sparse Antenna Activation for Reconfigurable Intelligent Surface Assisted Communication
• Relational inductive biases, deep learning, and graph networks
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Millimeter Wave Channel Modeling and Cellular Capacity Evaluation
• User Association for Load Balancing in Heterogeneous Cellular Networks
• An Iteratively Weighted MMSE Approach to Distributed Sum-Utility Maximization for a MIMO Interfering Broadcast Channel

Cited by

• A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints

Related

• GNN-Based Beamforming for Sum-Rate Maximization in MU-MISO Networks
• Multimodal Visual Image Based User Association and Beamforming Using Graph Neural Networks
• Learning Cooperative Beamforming with Edge-Update Empowered Graph Neural Networks
• Model-Based GNN Enabled Energy-Efficient Beamforming for Ultra-Dense Wireless Networks
• Beamforming Design and Association Scheme for Multi-RIS Multi-User mmWave Systems Through Graph Neural Networks