Beamforming has significance for enhancing spectral efficiency and mitigating interference in multi-antenna wireless systems, facilitating spatial multiplexing and diversity in dense and high mobility scenarios. Traditional beamforming techniques such as zero-forcing beamforming (ZFBF) and minimum mean square error (MMSE) beamforming experience performance deterioration under adverse channel conditions. Deep learning-based beamforming offers an alternative with nonlinear mappings from channel state information (CSI) to beamforming weights by improving robustness against dynamic channel environments. Transformer-based models are particularly effective due to their ability to model long-range dependencies across time and frequency. However, their quadratic attention complexity limits scalability in large OFDM grids. Recent studies address this issue through sparse attention mechanisms that reduce complexity while maintaining expressiveness, yet often employ patterns that disregard channel dynamics, as they are not specifically designed for wireless communication scenarios. In this work, we propose a Doppler-aware Sparse Neural Network Beamforming (Doppler-aware Sparse NNBF) model that incorporates a channel-adaptive sparse attention mechanism in a multi-user single-input multiple-output (MU-SIMO) setting. The proposed sparsity structure is configurable along 2D time-frequency axes based on channel dynamics and is theoretically proven to ensure full connectivity within p hops, where p is the number of attention heads. Simulation results under urban macro (UMa) channel conditions show that Doppler-aware Sparse NNBF significantly outperforms both a fixed-pattern baseline, referred to as Standard Sparse NNBF, and conventional beamforming techniques ZFBF and MMSE beamforming in high mobility scenarios, while maintaining structured sparsity with a controlled number of attended keys per query.

The literature is abundant with methodologies focusing on using transformer architectures due to their prominence in wireless signal processing and their capability to capture long-range dependencies via attention mechanisms. In particular, separable convolutions enhance parameter efficiency for the process of high-dimensional data characteristics of MIMO systems. In this work, we introduce a novel unsupervised deep learning framework that integrates separable convolutions and transformers to generate beamforming weights under imperfect channel state information (CSI) for a multi-user single-input multiple-output (MU-SIMO) system in dense urban environments. The primary goal is to enhance throughput by maximizing sum-rate while ensuring reliable communication. Spectral efficiency and block error rate (BLER) are considered as performance metrics. Experiments are carried out under various conditions to compare the performance of the proposed NNBF framework against baseline methods zero-forcing beamforming (ZFBF) and minimum mean square error (MMSE) beamforming. Experimental results demonstrate the superiority of the proposed framework over the baseline techniques.

In this paper, we consider the importance of channel measurement data from specific sites and its impact on air interface optimization and test. Currently, a range of statistical channel models including 3GPP 38.901 tapped delay line (TDL), clustered delay line (CDL), urban microcells (UMi) and urban macrocells (UMa) type channels are widely used for air interface performance testing and simulation. However, there remains a gap in the realism of these models for air interface testing and optimization when compared with real world measurement based channels. To address this gap, we compare the performance impacts of training neural receivers with 1) statistical 3GPP TDL models, and 2) measured macro-cell channel impulse response (CIR) data. We leverage our OmniPHY-5G neural receiver for NR PUSCH uplink simulation, with a training procedure that uses statistical TDL channel models for pre-training, and fine-tuning based on measured site specific MIMO CIR data. The proposed fine-tuning method achieves a 10% block error rate (BLER) at a 1.85 dB lower signal-to-noise ratio (SNR) compared to pre-training only on simulated TDL channels, illustrating a rough magnitude of the gap that can be closed by site-specific training, and gives the first answer to the question "how much can fine-tuning the RAN for site-specific channels help?"

Using a deep autoencoder (DAE) for end-to-end communication in multiple-input multiple-output (MIMO) systems is a novel concept with significant potential. DAE-aided MIMO has been shown to outperform singular-value decomposition (SVD)-based precoded MIMO in terms of bit error rate (BER). This paper proposes embedding left- and right-singular vectors of the channel matrix into DAE encoder and decoder to further improve the performance of the MIMO DAE. SVD-embedded DAE largely outperforms theoretic linear precoding in terms of BER. This is remarkable since it demonstrates that DAEs have significant potential to exceed the limits of current system design by treating the communication system as a single, end-to-end optimization block. Based on the simulation results, at SNR=10dB, the proposed SVD-embedded design can achieve a BER of about 10−5and reduce the BER at least 10 times compared with existing DAE without SVD, and up to 18 times compared with theoretical linear precoding. We attribute this to the fact that the proposed DAE can match the input and output as an adaptive modulation structure with finite alphabet input. We also observe that adding residual connections to the DAE further improves the performance.

Anomaly detection is a ubiquitous and challenging task, relevant across many disciplines. With the vital role communication networks play in our daily lives, the security of these networks is imperative for the smooth functioning of society. To this end, we propose a novel self-supervised deep learning framework CAAD for anomaly detection in wireless communication systems. Specifically, CAAD employs contrastive learning in an adversarial setup to learn effective representations of normal and anomalous behavior in wireless networks. We conduct rigorous performance comparisons of CAAD with several state-of-the-art anomaly detection techniques and verify that CAAD yields a mean performance improvement of 92.84%. Additionally, to adapt to the dynamic shifts in benign and anomalous data distributions, we also augment CAAD enabling it to systematically incorporate expert feedback through a novel contrastive learning feedback loop to improve the learned representations and thereby reduce prediction uncertainty (CAAD-EF). We view CAADEF as a novel, holistic, and widely applicable solution to anomaly detection. Our source code and data are available online1

Signal anomaly detection is commonly used to detect rogue or unexpected signals. It has many applications in interference mitigation, wireless security, optimized spectrum allocation, and radio coordination. Our work proposes a new method for anomaly detection on signal detection metadata using generative adversarial network output processed by a long short term memory recurrent neural network. We provide a performance analysis and comparison to baseline methods, and demonstrate that through the usage of metadata for analytics, we can provide robust detection, while also minimizing computation and bandwidth, and generalizing to numerous effects which differs from many prior works that focus on A.D. based signal processing on the raw RF sample data.

End-to-end autoencoder (AE) learning has the potential of exceeding the performance of human-engineered transceivers and encoding schemes, without a priori knowledge of communication-theoretic principles. In this work, we aim to understand to what extent and for which scenarios this claim holds true when comparing with fair benchmarks. Our particular focus is on memoryless multiple-input multiple-output (MIMO) and multi-user (MU) systems. Four case studies are considered: two point-to-point (closed-loop and open-loop MIMO) and two MU scenarios (MIMO broadcast and interference channels). For the point-to-point scenarios, we explain some of the performance gains observed in prior work through the selection of improved baseline schemes that include geometric shaping as well as bit and power allocation. For the MIMO broadcast channel, we demonstrate the feasibility of a novel AE method with centralized learning and decentralized execution. Interestingly, the learned scheme performs close to nonlinear vector-perturbation precoding and significantly outperforms conventional zero-forcing. Lastly, we highlight potential pitfalls when interpreting learned communication schemes. In particular, we show that the AE for the considered interference channel learns to avoid interference, albeit in a rotated reference frame. After de-rotating the learned signal constellation of each user, the resulting scheme corresponds to conventional time sharing with geometric shaping.

End-to-end data-driven machine learning (ML) of multiple-input multiple-output (MIMO) systems has been shown to have the potential of exceeding the performance of engineered MIMO transceivers, without any a priori knowledge of communication-theoretic principles. In this work, we aim to understand to what extent and for which scenarios this claim holds true when comparing with fair benchmarks. We study closed-loop MIMO, open-loop MIMO, and multi-user MIMO (MU-MIMO) and show that the gains of ML-based communication in the former two cases can be to a large extent ascribed to implicitly learned geometric shaping and bit and power allocation, not to learning new spatial encoders. For MU-MIMO, we demonstrate the feasibility of a novel method with centralized learning and decentralized executing, outperforming conventional zero-forcing. For each scenario, we provide explicit descriptions as well as open-source implementations of the selected neural-network architectures.

This paper presents a novel physical layer scheme for multiple-input multiple-output (MIMO) communication systems based on unsupervised deep learning (DL) using an autoencoder in an interference channel (IC) environment. Moreover, it extends the single-input single-output (SISO) channel autoencoder to consider fading channel conditions. In both schemes, two physical layer communication system encoders and decoders are jointly optimized in the presence of interference to minimize their symbol error rate (SER). We analyze resulting SER performance for varying signal-to-interference-plus-noise-ratio (SINR) levels. Realistic channel effects; i.e. Rayleigh fading, are used while training the autoencoder system. For SISO systems, the autoencoder system in IC demonstrates significant performance improvement compared to the conventional single-user systems by eliminating interference when there is channel state information (CSI) at the transmitter. The MIMO autoencoder system also shows significant performance improvements compared to the conventional single-user MIMO systems at SINR levels higher than 16dB. MIMO systems with different number of antennas are simulated to analyze the change in the system complexity and scalability. The information required at the transmitter; i.e. CSI from both the intended and interference links, and the autoencoder training time increases with increasing number of antennas for the autoencoder-based MIMO systems.