Anamika Sharma; Jagrati Nagdiya; Jagdish Chandra Patni; Om Prakash Pal

Graph Neural Network Representation for Low-Complexity Antenna Selection in RIS-Assisted MIMO Systems

PDF (779KB), PP.413-426

Views: 0 Downloads: 0

Author(s)

Anamika Sharma ^1,* Jagrati Nagdiya ² Jagdish Chandra Patni ³ Om Prakash Pal ⁴

1. Graphic Era Deemed to be University, Dehradun, 248002, India

2. Shri Vaishnav Vidyapeeth Vishwavidyalaya, Indore, 453111, India

3. Chandigarh University, Mohali, 140413, India

4. Graphic Era Deemed to be University Dehradun, 248002, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijwmt.2026.04.24

Received: 24 Mar. 2026 / Revised: 25 May 2026 / Accepted: 15 Jul. 2026 / Published: 8 Aug. 2026

Index Terms

Graph neural networks, reconfigurable intelligent surfaces, antenna selection, MIMO systems low-complexity, optimisation, deep learning for wireless communications

Abstract

Antenna selection in reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output (MIMO) systems presents has significant computational challenges. The contribution of each transmit antenna is determined by the combined effects of direct and RIS-reflected channels. To address the complexity of combinatorial search a graph neural network (GNN)-based antenna selection framework is proposed. In this framework transmit antennas are represented as graph nodes with channel-correlation information forming. The graph edges and magnitude-phase channel statistics serve as node features. A three-layer feedforward GNN is trained using greedy-selection labels generated from 1000 channel realizations and evaluated on 200 independent test realizations. For a 16×8 MIMO system assisted by a 64-element RIS at 28 GHz the proposed method achieves a spectral efficiency of 63.41 bits/s/Hz and corresponding to 94.5% of the greedy baseline performance of 67.09 bits/s/Hz. While reducing the average selection time from 0.441 ms to 0.025 ms. These results determine that graph-structured learning enables near-greedy antenna selection with considerably lower inference complexity. The current study is limited to simulated settings with fixed system dimensions and idealized channel assumptions; future work will address broader channel models and larger-scale configurations.

Cite This Paper

Anamika Sharma, Jagrati Nagdiya, Jagdish Chandra Patni, Om Prakash Pal, "Graph Neural Network Representation for Low-Complexity Antenna Selection in RIS-Assisted MIMO Systems", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.16, No.4, pp. 413-426, 2026. DOI:10.5815/ijwmt.2026.04.24

Reference

[1]L. Sui, Z. Lin, P. Xiao, and B. Vucetic, “Performance Analysis for Reconfigurable Intelligent Surface Assisted MIMO Systems,” IEEE Trans. Wirel. Commun., vol. 23, no. 1, 2024. doi: 10.1109/TWC.2023.3277887.
[2]A. Makarfi et al., “Reconfigurable Intelligent Surface-Enabled Vehicular Networks: A Physical Layer Security Perspective,” IEEE Open Journal of the Communications Society, vol. 7, 2026. doi: 10.1109/OJCOMS.2025.3642889.
[3]J. Qian and L. Sang, “RIS-Assisted Communications: A Comprehensive Study for Far- and Near-Field Scenarios,” IEEE Trans. Cogn. Commun. Netw., vol. 12, 2026. doi: 10.1109/TCCN.2025.3598097.
[4]M. M. Kamal, I. Khan, M. A. Al-Khasawneh, and A. K. J. Saudagar, “Hybrid optimization-based deep learning for energy efficiency resource allocation in MIMO-enabled wireless networks,” Sci. Rep., vol. 15, no. 1, 2025. doi: 10.1038/s41598-025-16571-8.
[5]Z. Chen, J. Sun, Z. Huan, and Z. Zhang, “Research on Vehicle Joint Radar Communication Resource Optimization Method Based on GNN-DRL,” Computers, Materials and Continua, vol. 86, no. 2, 2026. doi: 10.32604/cmc.2025.071182.
[6]Y. Tian et al., “An Optimized Deep Learning Framework for Energy-Efficient Resource Allocation in UAV-Assisted Wireless Networks,” IEEE Access, vol. 13, 2025. doi: 10.1109/ACCESS.2025.3546225.
[7]Y. Cao, W. Cheng, J. Wang, and W. Zhang, “Active Reconfigurable Intelligent Surface Assisted MIMO: Electromagnetic-Compliant Modeling With Mutual Coupling,” IEEE Trans. Wirel. Commun., vol. 25, 2026. doi: 10.1109/TWC.2025.3610859.
[8]Z. Yigit, E. Basar, and I. Altunbas, “Low complexity adaptation for reconfigurable intelligent surface-based mimo systems,” IEEE Communications Letters, vol. 24, no. 12, 2020. doi: 10.1109/LCOMM.2020.3014820.
[9]M. Soleymani, A. Zappone, E. Jorswieck, M. Di Renzo, and I. Santamaria, “Spectral-Energy Efficiency Tradeoff of Nearly-Passive RIS in MIMO URLLC Downlink: Diagonal Versus beyond Diagonal,” IEEE Wireless Communications Letters, vol. 15, 2026. doi: 10.1109/LWC.2025.3641845.
[10]S. Asaad, H. Tabassum, C. Ouyang, and P. Wang, “Joint Antenna Selection and Beamforming for Massive MIMO-Enabled Over-the-Air Federated Learning,” IEEE Trans. Wirel. Commun., vol. 23, no. 8, 2024. doi: 10.1109/TWC.2024.3352504.
[11]S. Sanayei and A. Nosratinia, “Antenna selection in MIMO systems,” IEEE Communications Magazine, vol. 42, no. 10, pp. 68–73, Oct. 2004. Doi: 10.1109/MCOM.2004.1341263
[12]A. F. Molisch, M. Z. Win, Y.-S. Choi, and J. H. Winters, “Capacity of MIMO systems with antenna selection,” IEEE Transactions on Wireless Communications, vol. 4, no. 4, pp. 1759–1772, Jul. 2005. Doi: 10.1109/TWC.2005.850307
[13]Y. Shen, Y. Shi, J. Zhang, and K. B. Letaief, “Graph neural networks for scalable radio resource management: Architecture design and theoretical analysis,” IEEE Journal on Selected Areas in Communications, vol. 39, no. 1, pp. 101–115, Jan. 2021. Doi: 10.1109/JSAC.2020.3036965
[14]L. Zhao, H. Wang, J. Chen, and X. Meng, “Multi-Array Visible-Light Optical Generalized Spatial Multiplexing–Multiple Input Multiple-Output System with Pearson Coefficient-Based Antenna Selection,” Photonics, vol. 11, no. 1, 2024. doi: 10.3390/photonics11010067.
[15]A. Khaleel and E. Basar, “Reconfigurable Intelligent Surface-Empowered MIMO Systems,” IEEE Syst. J., vol. 15, no. 3, 2021. doi: 10.1109/JSYST.2020.3011987.
[16]R. K. Fotock, A. Lucky Imoize, A. Zappone, M. Di Renzo, and R. Garello, “Secrecy Energy Efficiency Maximization in RIS-Aided Networks: Active or Nearly-Passive RIS?,” IEEE Transactions on Information Forensics and Security, vol. 21, 2026. doi: 10.1109/TIFS.2025.3620227.
[17]M. Raeisi, H. Chen, H. Wymeersch, and E. Basar, “Modern Base Station Architecture: Enabling Passive Beamforming With Beyond Diagonal RISs,” IEEE Trans. Wirel. Commun., vol. 25, 2026. doi: 10.1109/TWC.2025.3641612.
[18]Y. Lu et al., “Agentic Graph Neural Networks for Wireless Communications and Networking Towards Edge General Intelligence: A Survey,” IEEE Communications Surveys & Tutorials, 2026. doi: 10.1109/comst.2026.3651990.
[19]T. Ahmad and E. Basar, “RIS-Based Dual-Mode Receive Spatial Modulation for Low-Complexity Wireless Access Points,” IEEE Trans. Wirel. Commun., vol. 25, 2026. doi: 10.1109/TWC.2025.3625994.
[20]J. A. Alzubi, M. G. Dhandapani, A. Aiyappan, S. Damodaran, J. Shreyas, and T. P. Priyanka, “Adaptive Residual Recurrent Neural Network with Heuristic Optimization for Spectral Energy Balancing in 6G Massive MIMO Systems,” International Journal of Computational Intelligence Systems, vol. 19, no. 1, 2026. doi: 10.1007/s44196-025-01106-w.
[21]M. Balachandran and N. M. Vali Mohamad, “Joint Design of Antenna Selection and Resource Allocation in Massive MIMO-Based Ultra Dense Heterogeneous Networks,” Journal of Electrical and Computer Engineering, vol. 2024, 2024, doi: 10.1155/2024/3809470.
[22]M. Lee, G. Yu, and H. Dai, “Decentralized Inference With Graph Neural Networks in Wireless Communication Systems,” IEEE Trans. Mob. Comput., vol. 22, no. 5, 2023. doi: 10.1109/TMC.2021.3125793.
[23]Y. Shen, J. Zhang, S. H. Song, and K. B. Letaief, “Graph Neural Networks for Wireless Communications: From Theory to Practice,” IEEE Trans. Wirel. Commun., vol. 22, no. 5, 2023. doi: 10.1109/TWC.2022.3219840.
[24]J. Suarez-Varela et al., “Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities,” IEEE Netw., vol. 37, no. 3, 2023. doi: 10.1109/MNET.123.2100773.
[25]L. Liang, H. Ye, G. Yu, and G. Y. Li, “Deep-Learning-Based Wireless Resource Allocation with Application to Vehicular Networks,” Proceedings of the IEEE, vol. 108, no. 2, 2020. doi: 10.1109/JPROC.2019.2957798.
[26]N. Xuan Tung et al., “Graph Neural Networks for Next-Generation-IoT: Recent Advances and Open Challenges,” IEEE Communications Surveys and Tutorials, vol. 28, 2026. doi: 10.1109/COMST.2025.3613845.
[27]X. Liu and C. Fischione, “Coordinated Beamforming for Multi-Cell ISAC Using Graph Neural Networks,” IEEE Trans. Wirel. Commun., vol. 25, 2026. doi: 10.1109/TWC.2025.3621437.
[28]J. He, K. Yu, Y. Shi, Y. Zhou, and W. Chen, “Reconfigurable intelligent surface assisted massive MIMO with antenna selection,” IEEE Transactions on Wireless Communications, 2021. doi: 10.1109/TWC.2021.3133272

International Journal of Wireless and Microwave Technologies (IJWMT)