1.
Linfu, Zou; Zhiwen, Pan; El-Hajjar, Mohammed
Graph Neural Network Aided Beamforming for Holographic Millimeter Wave MIMO Systems Journal Article
In: IEEE Transactions on Vehicular Technology, vol. 74, no. 7, pp. 10582–10595, 2025, ISSN: 1939-9359.
Abstract | Links | BibTeX | Tags: Accuracy, Array signal processing, Beamforming, Channel estimation, Downlink, Estimation, graph neural network, Graph neural networks, holographic MIMO, millimeter wave, Millimeter wave communication, OFDM, Optimization, Training
@article{linfu_graph_2025,
title = {Graph Neural Network Aided Beamforming for Holographic Millimeter Wave MIMO Systems},
author = {Zou Linfu and Pan Zhiwen and Mohammed El-Hajjar},
url = {https://ieeexplore.ieee.org/document/10896848},
doi = {10.1109/TVT.2025.3544063},
issn = {1939-9359},
year = {2025},
date = {2025-07-01},
urldate = {2025-10-08},
journal = {IEEE Transactions on Vehicular Technology},
volume = {74},
number = {7},
pages = {10582–10595},
abstract = {Holographic multiple-input multiple-output (HMIMO) systems are considered as one of the potential techniques to meet the demands of next-generation communications by replacing costly and power-hungry devices with sub-half-wavelength antenna elements. However, optimizing the beamforming matrix in the base station (BS) for HMIMO systems is challenging, given the prohibitive overhead of directly estimating the channels between the BS and the user equipment. Instead of following the traditional method of channel estimation and beamforming optimization, in this paper we employ a deep-learning technique to optimize the beamformers at the BS based on a loss function. Specifically, in this paper we introduce a graph neural network (GNN) designed to map the received pilot signals to optimized beamforming matrices and to model interactions among user equipment within the network. The simulation results show that our deep-learning method effectively maximizes the sum-rate objective while using reduced number of pilots than traditional channel estimation and beamforming optimization techniques.},
keywords = {Accuracy, Array signal processing, Beamforming, Channel estimation, Downlink, Estimation, graph neural network, Graph neural networks, holographic MIMO, millimeter wave, Millimeter wave communication, OFDM, Optimization, Training},
pubstate = {published},
tppubtype = {article}
}
Holographic multiple-input multiple-output (HMIMO) systems are considered as one of the potential techniques to meet the demands of next-generation communications by replacing costly and power-hungry devices with sub-half-wavelength antenna elements. However, optimizing the beamforming matrix in the base station (BS) for HMIMO systems is challenging, given the prohibitive overhead of directly estimating the channels between the BS and the user equipment. Instead of following the traditional method of channel estimation and beamforming optimization, in this paper we employ a deep-learning technique to optimize the beamformers at the BS based on a loss function. Specifically, in this paper we introduce a graph neural network (GNN) designed to map the received pilot signals to optimized beamforming matrices and to model interactions among user equipment within the network. The simulation results show that our deep-learning method effectively maximizes the sum-rate objective while using reduced number of pilots than traditional channel estimation and beamforming optimization techniques.
2.
Feng, Xinyu; El-Hajjar, Mohammed; Xu, Chao; Hanzo, Lajos
Graph Neural Network Aided Detection for the Multi-User Multi-Dimensional Index Modulated Uplink Journal Article
In: IEEE Open Journal of Vehicular Technology, vol. 6, pp. 1593–1612, 2025, ISSN: 2644-1330.
Abstract | Links | BibTeX | Tags: Artificial neural networks, Detectors, graph factor, graph neural network (GNN), Graph neural networks, Index modulation (IM), Indexes, machine learning, Message passing, message passing (MP), multi-user, Next generation networking, Peak to average power ratio, Symbols, Uplink, Vectors
@article{feng_graph_2025,
title = {Graph Neural Network Aided Detection for the Multi-User Multi-Dimensional Index Modulated Uplink},
author = {Xinyu Feng and Mohammed El-Hajjar and Chao Xu and Lajos Hanzo},
url = {https://ieeexplore.ieee.org/document/11017516},
doi = {10.1109/OJVT.2025.3574934},
issn = {2644-1330},
year = {2025},
date = {2025-01-01},
urldate = {2025-10-08},
journal = {IEEE Open Journal of Vehicular Technology},
volume = {6},
pages = {1593–1612},
abstract = {The concept of Compressed Sensing-aided Space-Frequency Index Modulation (CS-SFIM) is conceived for the Large-Scale Multi-User Multiple-Input Multiple-Output Uplink (LS-MU-MIMO-UL) of Next-Generation (NG) networks. Explicitly, in CS-SFIM, the information bits are mapped to both spatial- and frequency-domain indices, where we treat the activation patterns of the transmit antennas and of the subcarriers separately. Serving a large number of users in an MU-MIMO-UL system leads to substantial Multi-User Interference (MUI). Hence, we design the Space-Frequency (SF) domain matrix as a joint factor graph, where the Approximate Message Passing (AMP) and Expectation Propagation (EP) based MU detectors can be utilized. In the LS-MU-MIMO-UL scenario considered, the proposed system uses optimal Maximum Likelihood (ML) and Minimum Mean Square Error (MMSE) detectors as benchmarks for comparison with the proposed MP-based detectors. These MP-based detectors significantly reduce the detection complexity compared to ML detection, making the design eminently suitable for LS-MU scenarios. To further reduce the detection complexity and improve the detection performance, we propose a pair of Graph Neural Network (GNN) based detectors, which rely on the orthogonal AMP (OAMP) and on the EP algorithm, which we refer to as the GNN-AMP and GEPNet detectors, respectively. The GEPNet detector maximizes the detection performance, while the GNN-AMP detector strikes a performance versus complexity trade-off. The GNN is trained for a single system configuration and yet it can be used for any number of users in the system. The simulation results show that the GNN-based detector approaches the ML performance in various configurations.},
keywords = {Artificial neural networks, Detectors, graph factor, graph neural network (GNN), Graph neural networks, Index modulation (IM), Indexes, machine learning, Message passing, message passing (MP), multi-user, Next generation networking, Peak to average power ratio, Symbols, Uplink, Vectors},
pubstate = {published},
tppubtype = {article}
}
The concept of Compressed Sensing-aided Space-Frequency Index Modulation (CS-SFIM) is conceived for the Large-Scale Multi-User Multiple-Input Multiple-Output Uplink (LS-MU-MIMO-UL) of Next-Generation (NG) networks. Explicitly, in CS-SFIM, the information bits are mapped to both spatial- and frequency-domain indices, where we treat the activation patterns of the transmit antennas and of the subcarriers separately. Serving a large number of users in an MU-MIMO-UL system leads to substantial Multi-User Interference (MUI). Hence, we design the Space-Frequency (SF) domain matrix as a joint factor graph, where the Approximate Message Passing (AMP) and Expectation Propagation (EP) based MU detectors can be utilized. In the LS-MU-MIMO-UL scenario considered, the proposed system uses optimal Maximum Likelihood (ML) and Minimum Mean Square Error (MMSE) detectors as benchmarks for comparison with the proposed MP-based detectors. These MP-based detectors significantly reduce the detection complexity compared to ML detection, making the design eminently suitable for LS-MU scenarios. To further reduce the detection complexity and improve the detection performance, we propose a pair of Graph Neural Network (GNN) based detectors, which rely on the orthogonal AMP (OAMP) and on the EP algorithm, which we refer to as the GNN-AMP and GEPNet detectors, respectively. The GEPNet detector maximizes the detection performance, while the GNN-AMP detector strikes a performance versus complexity trade-off. The GNN is trained for a single system configuration and yet it can be used for any number of users in the system. The simulation results show that the GNN-based detector approaches the ML performance in various configurations.