# GNN-Based Beamforming for Sum-Rate Maximization in MU-MISO Networks

arXiv: https://arxiv.org/abs/2311.03659 · HTML: https://mlsanity.com/paper/2311.03659/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2023.

## Built on by (most cited first, 7 of 7)

- [A Semi-amortized Lifted Learning-to-Optimize Masked (SALLO-M) Transformer Model for Scalable and Generalizable Beamforming](https://mlsanity.com/paper/2510.13077/) (2025)
- [BERT4beam: Large AI Model Enabled Generalized Beamforming Optimization](https://mlsanity.com/paper/2509.11056/) (2025)
- [RIS-Assisted Downlink Pinching-Antenna Systems: GNN-Enabled Optimization Approaches](https://mlsanity.com/paper/2511.20305/) (2025)
- [GNN-Enabled Robust Hybrid Beamforming with Score-Based CSI Generation and Denoising](https://mlsanity.com/paper/2511.06663/) (2025)
- [Association-Aware GNN for Precoder Learning in Cell-Free Systems](https://mlsanity.com/paper/2603.13035/) (2026)
- [Spectral- and Energy-efficient Multi-BS Multi-RIS Pinching-antenna Systems: A GNN-based Approach](https://mlsanity.com/paper/2605.01307/) (2026)
- [Self-Evolving In-Context Learning for Direct Pilot-to-Beamformer Design in MU-MISO Systems](https://mlsanity.com/paper/2607.11970/) (2026)

## Abstract (arXiv)

The advantages of graph neural networks (GNNs) in leveraging the graph topology of wireless networks have drawn increasing attentions. This paper studies the GNN-based learning approach for the sum-rate maximization in multiple-user multiple-input single-output (MU-MISO) networks subject to the users' individual data rate requirements and the power budget of the base station. By modeling the MU-MISO network as a graph, a GNN-based architecture named CRGAT is proposed to directly map the channel state information to the beamforming vectors. The attention-enabled aggregation and the residual-assisted combination are adopted to enhance the learning capability and avoid the oversmoothing issue. Furthermore, a novel activation function is proposed for the constraint due to the limited power budget at the base station. The CRGAT is trained in an unsupervised learning manner with two proposed loss functions. An evaluation method is proposed for the learning-based approach, based on which the effectiveness of the proposed CRGAT is validated in comparison with several convex optimization and learning based approaches. Numerical results are provided to reveal the advantages of the CRGAT including the millisecond-level response with limited optimality performance loss, the scalability to different number of users and power budgets, and the adaptability to different system settings.