Searcharxiv⌕ Search

arXiv subjects

Shenghui Song

Publications and source records attributed to Shenghui Song.

At least 91 records · Page 5Linked to original sources
arXiv2023

Message Passing Meets Graph Neural Networks: A New Paradigm for Massive MIMO Systems

As one of the core technologies for 5G systems, massive multiple-input multiple-output (MIMO) introduces dramatic capacity improvements along with very high beamforming and spatial multiplexing gains. When developing efficient physical layer algorithms for massive MIMO systems, message passing is one promising candidate owing to the superior performance. However, as their computational complexity increases dramatically with the problem size, the state-of-the-art message passing algorithms cannot be directly applied to future 6G systems, where an exceedingly large number of antennas are expected to be deployed. To address this issue, we propose a model-driven deep learning (DL) framework, namely the AMP-GNN for massive MIMO transceiver design, by considering the low complexity of the AMP algorithm and adaptability of GNNs. Specifically, the structure of the AMP-GNN network is customized by unfolding the approximate message passing (AMP) algorithm and introducing a graph neural network (GNN) module into it. The permutation equivariance property of AMP-GNN is proved, which enables the AMP-GNN to learn more efficiently and to adapt to different numbers of users. We also reveal the underlying reason why GNNs improve the AMP algorithm from the perspective of expectation propagation, which motivates us to amalgamate various GNNs with different message passing algorithms. In the simulation, we take the massive MIMO detection to exemplify that the proposed AMP-GNN significantly improves the performance of the AMP detector, achieves comparable performance as the state-of-the-art DL-based MIMO detectors, and presents strong robustness to various mismatches.

cs.IT↗
arXiv2023

Multi-objective Optimization of Space-Air-Ground Integrated Network Slicing Relying on a Pair of Central and Distributed Learning Algorithms

As an attractive enabling technology for next-generation wireless communications, network slicing supports diverse customized services in the global space-air-ground integrated network (SAGIN) with diverse resource constraints. In this paper, we dynamically consider three typical classes of radio access network (RAN) slices, namely high-throughput slices, low-delay slices and wide-coverage slices, under the same underlying physical SAGIN. The throughput, the service delay and the coverage area of these three classes of RAN slices are jointly optimized in a non-scalar form by considering the distinct channel features and service advantages of the terrestrial, aerial and satellite components of SAGINs. A joint central and distributed multi-agent deep deterministic policy gradient (CDMADDPG) algorithm is proposed for solving the above problem to obtain the Pareto optimal solutions. The algorithm first determines the optimal virtual unmanned aerial vehicle (vUAV) positions and the inter-slice sub-channel and power sharing by relying on a centralized unit. Then it optimizes the intra-slice sub-channel and power allocation, and the virtual base station (vBS)/vUAV/virtual low earth orbit (vLEO) satellite deployment in support of three classes of slices by three separate distributed units. Simulation results verify that the proposed method approaches the Pareto-optimal exploitation of multiple RAN slices, and outperforms the benchmarkers.

cs.NI↗
arXiv2023

Binary Federated Learning with Client-Level Differential Privacy

Federated learning (FL) is a privacy-preserving collaborative learning framework, and differential privacy can be applied to further enhance its privacy protection. Existing FL systems typically adopt Federated Average (FedAvg) as the training algorithm and implement differential privacy with a Gaussian mechanism. However, the inherent privacy-utility trade-off in these systems severely degrades the training performance if a tight privacy budget is enforced. Besides, the Gaussian mechanism requires model weights to be of high-precision. To improve communication efficiency and achieve a better privacy-utility trade-off, we propose a communication-efficient FL training algorithm with differential privacy guarantee. Specifically, we propose to adopt binary neural networks (BNNs) and introduce discrete noise in the FL setting. Binary model parameters are uploaded for higher communication efficiency and discrete noise is added to achieve the client-level differential privacy protection. The achieved performance guarantee is rigorously proved, and it is shown to depend on the level of discrete noise. Experimental results based on MNIST and Fashion-MNIST datasets will demonstrate that the proposed training algorithm achieves client-level privacy protection with performance gain while enjoying the benefits of low communication overhead from binary model updates.

cs.LG↗
arXiv2023

Power Allocation for Device-to-Device Interference Channel Using Truncated Graph Transformers

Power control for the device-to-device interference channel with single-antenna transceivers has been widely analyzed with both model-based methods and learning-based approaches. Although the learning-based approaches, i.e., datadriven and model-driven, offer performance improvement, the widely adopted graph neural network suffers from learning the heterophilous power distribution of the interference channel. In this paper, we propose a deep learning architecture in the family of graph transformers to circumvent the issue. Experiment results show that the proposed methods achieve the state-of-theart performance across a wide range of untrained network configurations. Furthermore, we show there is a trade-off between model complexity and generality.

eess.SP↗
arXiv2023

An Adaptive and Robust Deep Learning Framework for THz Ultra-Massive MIMO Channel Estimation

Terahertz ultra-massive MIMO (THz UM-MIMO) is envisioned as one of the key enablers of 6G wireless networks, for which channel estimation is highly challenging. Traditional analytical estimation methods are no longer effective, as the enlarged array aperture and the small wavelength result in a mixture of far-field and near-field paths, constituting a hybrid-field channel. Deep learning (DL)-based methods, despite the competitive performance, generally lack theoretical guarantees and scale poorly with the size of the array. In this paper, we propose a general DL framework for THz UM-MIMO channel estimation, which leverages existing iterative channel estimators and is with provable guarantees. Each iteration is implemented by a fixed point network (FPN), consisting of a closed-form linear estimator and a DL-based non-linear estimator. The proposed method perfectly matches the THz UM-MIMO channel estimation due to several unique advantages. First, the complexity is low and adaptive. It enjoys provable linear convergence with a low per-iteration cost and monotonically increasing accuracy, which enables an adaptive accuracy-complexity tradeoff. Second, it is robust to practical distribution shifts and can directly generalize to a variety of heavily out-of-distribution scenarios with almost no performance loss, which is suitable for the complicated THz channel conditions. For practical usage, the proposed framework is further extended to wideband THz UM-MIMO systems with beam squint effect. Theoretical analysis and extensive simulation results are provided to illustrate the advantages over the state-of-the-art methods in estimation accuracy, convergence rate, complexity, and robustness.

eess.SP↗
arXiv2023

Lightweight and Flexible Deep Equilibrium Learning for CSI Feedback in FDD Massive MIMO

In frequency-division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems, downlink channel state information (CSI) needs to be sent back to the base station (BS) by the users, which causes prohibitive feedback overhead. In this paper, we propose a lightweight and flexible deep learning-based CSI feedback approach by capitalizing on deep equilibrium models. Different from existing deep learning-based methods that stack multiple explicit layers, we propose an implicit equilibrium block to mimic the behavior of an infinite-depth neural network. In particular, the implicit equilibrium block is defined by a fixed-point iteration and the trainable parameters in different iterations are shared, which results in a lightweight model. Furthermore, the number of forward iterations can be adjusted according to users' computation capability, enabling a flexible accuracy-efficiency trade-off. Simulation results will show that the proposed design obtains a comparable performance as the benchmarks but with much-reduced complexity and permits an accuracy-efficiency trade-off at runtime.

cs.IT↗
arXiv2023

Local SGD Accelerates Convergence by Exploiting Second Order Information of the Loss Function

With multiple iterations of updates, local statistical gradient descent (L-SGD) has been proven to be very effective in distributed machine learning schemes such as federated learning. In fact, many innovative works have shown that L-SGD with independent and identically distributed (IID) data can even outperform SGD. As a result, extensive efforts have been made to unveil the power of L-SGD. However, existing analysis failed to explain why the multiple local updates with small mini-batches of data (L-SGD) can not be replaced by the update with one big batch of data and a larger learning rate (SGD). In this paper, we offer a new perspective to understand the strength of L-SGD. We theoretically prove that, with IID data, L-SGD can effectively explore the second order information of the loss function. In particular, compared with SGD, the updates of L-SGD have much larger projection on the eigenvectors of the Hessian matrix with small eigenvalues, which leads to faster convergence. Under certain conditions, L-SGD can even approach the Newton method. Experiment results over two popular datasets validate the theoretical results.

cs.LG↗
arXiv2023

Integrated Sensing and Communication in Coordinated Cellular Networks

Integrated sensing and communication (ISAC) is a promising technique to provide sensing services in future wireless networks. Numerous existing works have adopted a monostatic radar architecture to realize ISAC, i.e., employing the same base station (BS) to transmit the ISAC signal and receive the echo. Yet, the concurrent information transmission causes unavoidable self-interference (SI) to the radar echo at the BS. To overcome this difficulty, we propose a coordinated cellular network-supported multistatic radar architecture to implement ISAC, which allows us to spatially separate the ISAC signal transmission and radar echo reception, intrinsically circumventing the problem of SI. To this end, we jointly optimize the transmit and receive beamforming policy to minimize the sensing beam pattern mismatch error subject to ISAC quality-of-service requirements. The resulting non-convex optimization problem is tackled by an alternating optimization-based suboptimal algorithm. Simulation results showed that the proposed scheme outperforms the two baseline schemes adopting conventional designs.

cs.IT↗
arXiv2023

Active IRS-Aided MIMO Systems: How Much Gain Can We Get?

Intelligent reflecting surfaces (IRSs) have emerged as a promising technology to improve the efficiency of wireless communication systems. However, passive IRSs suffer from the ``multiplicative fading" effect, because the transmit signal will go through two fading hops. With the ability to amplify and reflect signals, active IRSs offer a potential way to tackle this issue, where the amplification energy only experiences the second hop. However, the fundamental limit and system design for active IRSs have not been fully understood, especially for multiple-input multiple-output (MIMO) systems. In this work, we consider the analysis and design for the large-scale active IRS-aided MIMO system assuming only statistical channel state information (CSI) at the transmitter and the IRS. The evaluation of the fundamental limit, i.e., ergodic rate, turns out to be a very difficult problem. To this end, we leverage random matrix theory (RMT) to derive the deterministic approximation (DA) for the ergodic rate, and then design an algorithm to jointly optimize the transmit covariance matrix at the transmitter and the reflection matrix at the active IRS. Numerical results demonstrate the accuracy of the derived DA and the effectiveness of the proposed optimization algorithm. The results in this work reveal interesting physical insights with respect to the advantage of active IRSs over their passive counterparts.

cs.IT↗
arXiv2023

Joint BS Selection, User Association, and Beamforming Design for Network Integrated Sensing and Communication

Different from conventional radar, the cellular network in the integrated sensing and communication (ISAC) system enables collaborative sensing by multiple sensing nodes, e.g., base stations (BSs). However, existing works normally assume designated BSs as the sensing nodes, and thus can't fully exploit the macro-diversity gain. In the paper, we propose a joint BS selection, user association, and beamforming design to tackle this problem. The total transmit power is minimized while guaranteeing the communication and sensing performance measured by the signal-to-interference-plus-noise ratio (SINR) for the communication users and the Cramer-Rao lower bound (CRLB) for location estimation, respectively. An alternating optimization (AO)-based algorithm is developed to solve the non-convex problem. Simulation results validate the effectiveness of the proposed algorithm and unveil the benefits brought by collaborative sensing and BS selection.

eess.SP↗
arXiv2023

Networked Sensing with AI-Empowered Interference Management: Exploiting Macro-Diversity and Array Gain in Perceptive Mobile Networks

Sensing will be an important service of future wireless networks to assist innovative applications such as autonomous driving and environment monitoring. Perceptive mobile networks (PMNs) were proposed to add sensing capability to current cellular networks. Different from traditional radar, the cellular structure of PMNs offers multiple perspectives to sense the same target, but the inherent interference between sensing and communication along with the joint processing among distributed sensing nodes (SNs) also cause big challenges for the design of PMNs. In this paper, we first propose a two-stage protocol to tackle the interference between two sub-systems. Specifically, the echoes created by communication signals, i.e., interference for sensing, are first estimated in the clutter estimation (CE) stage and then utilized for interference management in the target sensing (TS) stage. A networked sensing detector is then derived to exploit the perspectives provided by multiple SNs for sensing the same target. The macro-diversity from multiple SNs together with the array gain and the higher angular resolution from multiple receive antennas of each SN are investigated to reveal the benefit of networked sensing. Furthermore, we derive the sufficient condition to guarantee one SN's contribution is positive, based on which a SN selection algorithm is proposed. To reduce the communication workload, we propose a distributed model-driven deep-learning algorithm that utilizes partially-sampled data for CE. Simulation results confirm the benefits of networked sensing and validate the higher efficiency of the proposed CE algorithm than existing methods.

cs.IT↗
arXiv2023

Blind Performance Prediction for Deep Learning Based Ultra-Massive MIMO Channel Estimation

Reliability is of paramount importance for the physical layer of wireless systems due to its decisive impact on end-to-end performance. However, the uncertainty of prevailing deep learning (DL)-based physical layer algorithms is hard to quantify due to the black-box nature of neural networks. This limitation is a major obstacle that hinders their practical deployment. In this paper, we attempt to quantify the uncertainty of an important category of DL-based channel estimators. An efficient statistical method is proposed to make blind predictions for the mean squared error of the DL-estimated channel solely based on received pilots, without knowledge of the ground-truth channel, the prior distribution of the channel, or the noise statistics. The complexity of the blind performance prediction is low and scales only linearly with the number of antennas. Simulation results for ultra-massive multiple-input multiple-output (UM-MIMO) channel estimation with a mixture of far-field and near-field paths are provided to verify the accuracy and efficiency of the proposed method.

eess.SP↗
arXiv2023

Asymptotic Mutual Information Analysis for Double-scattering MIMO Channels: A New Approach by Gaussian Tools

The asymptotic mutual information (MI) analysis for multiple-input multiple-output (MIMO) systems over double-scattering channels has achieved engaging results, but the convergence rates of the mean, variance, and the distribution of the MI are not yet available in the literature. In this paper, by utilizing the large random matrix theory (RMT), we give a central limit theory (CLT) for the MI and derive the closed-form approximation for the mean and the variance by a new approach -- Gaussian tools. The convergence rates of the mean, variance, and the characteristic function are proved to be O(1/N) for the first time, where N is the number of transmit antennas. Furthermore, the impact of the number of effective scatterers on the mean and variance was investigated in the moderate-to-high SNR regime with some interesting physical insights. The proposed evaluation framework can be utilized for the asymptotic performance analysis of other systems over double-scattering channels.

cs.IT↗
arXiv2023

Hierarchical Federated Learning with Quantization: Convergence Analysis and System Design

Federated learning (FL) is a powerful distributed machine learning framework where a server aggregates models trained by different clients without accessing their private data. Hierarchical FL, with a client-edge-cloud aggregation hierarchy, can effectively leverage both the cloud server's access to many clients' data and the edge servers' closeness to the clients to achieve a high communication efficiency. Neural network quantization can further reduce the communication overhead during model uploading. To fully exploit the advantages of hierarchical FL, an accurate convergence analysis with respect to the key system parameters is needed. Unfortunately, existing analysis is loose and does not consider model quantization. In this paper, we derive a tighter convergence bound for hierarchical FL with quantization. The convergence result leads to practical guidelines for important design problems such as the client-edge aggregation and edge-client association strategies. Based on the obtained analytical results, we optimize the two aggregation intervals and show that the client-edge aggregation interval should slowly decay while the edge-cloud aggregation interval needs to adapt to the ratio of the client-edge and edge-cloud propagation delay. Simulation results shall verify the design guidelines and demonstrate the effectiveness of the proposed aggregation strategy.

cs.LG↗
arXiv2022

FedDQ: Communication-Efficient Federated Learning with Descending Quantization

Federated learning (FL) is an emerging learning paradigm without violating users' privacy. However, large model size and frequent model aggregation cause serious communication bottleneck for FL. To reduce the communication volume, techniques such as model compression and quantization have been proposed. Besides the fixed-bit quantization, existing adaptive quantization schemes use ascending-trend quantization, where the quantization level increases with the training stages. In this paper, we first investigate the impact of quantization on model convergence, and show that the optimal quantization level is directly related to the range of the model updates. Given the model is supposed to converge with the progress of the training, the range of the model updates will gradually shrink, indicating that the quantization level should decrease with the training stages. Based on the theoretical analysis, a descending quantization scheme named FedDQ is proposed. Experimental results show that the proposed descending quantization scheme can save up to 65.2% of the communicated bit volume and up to 68% of the communication rounds, when compared with existing schemes.

cs.LG↗
arXiv2022

Secrecy Analysis for IRS-aided Wiretap MIMO Communications: Fundamental Limits and System Design

In order to meet the demands of future innovative applications, many efforts have been made to exceed the limits predicted by Shannon's Theory. Besides the investigation of beyond-Shannon metrics such as security, latency, and semantics, another direction is to jointly design the transceiver and the environment by utilizing the intelligent reflecting surface (IRS). In this paper, we consider the analysis and design of IRS-aided multiple-input multiple-output (MIMO) secure communications, which has attracted much research attention but still in its infancy. For example, despite their importance, the fundamental limits of IRS-aided wiretap MIMO communications are not yet available in the literature. In this paper, we will investigate these fundamental limits by determining the ergodic secrecy rate (ESR) and secrecy outage probability (SOP). For that purpose, the central limit theorem (CLT) for the joint distributions of the mutual information (MI) statistics over the IRS-aided MIMO secure communication channel is derived by utilizing the random matrix theory (RMT). The derived CLT is then used to obtain the closed form expressions for the ESR and SOP, which are also extended to the scenario with multiple multi-antenna eavesdroppers. Based on the theoretical results, algorithms for maximizing the artificial noise (AN) aided ESR and minimizing the SOP are proposed. Numerical results validate the accuracy of the theoretical results and effectiveness of the proposed optimization algorithms.

cs.IT↗
arXiv2022

Iterative Sparse Recovery based Passive Localization in Perceptive Mobile Networks

Perceptive mobile networks (PMNs) were proposed to integrate sensing capability into current cellular networks where multiple sensing nodes (SNs) can collaboratively sense the same targets. Besides the active sensing in traditional radar systems, passive sensing based on the uplink communication signals from mobile user equipment may play a more important role in PMNs, especially for targets with weak electromagnetic wave reflection, e.g., pedestrians. However, without the properly designed active sensing waveform, passive sensing normally suffers from low signal to noise power ratio (SNR). As a result, most existing methods require a large number of data samples to achieve an accurate estimate of the covariance matrix for the received signals, based on which a power spectrum is constructed for localization purposes. Such a requirement will create heavy communication workload for PMNs because the data samples need to be transferred over the network for collaborative sensing. To tackle this issue, in this paper we leverage the sparse structure of the localization problem to reduce the searching space and propose an iterative sparse recovery (ISR) algorithm that estimates the covariance matrix and the power spectrum in an iterative manner. Experiment results show that, with very few samples in the low SNR regime, the ISR algorithm can achieve much better localization performance than existing methods.

eess.SP↗
arXiv2022

SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another dimension reduction method, adaptive sampling weights and processes regions that are relevant to the task, and is thus able to better preserve useful information. However, the use of adaptive sampling has been limited to certain layers. In this paper, we show that using adaptive sampling in the building blocks of a deep neural network can improve its efficiency. In particular, we propose SSBNet which is built by inserting sampling layers repeatedly into existing networks like ResNet. Experiment results show that the proposed SSBNet can achieve competitive image classification and object detection performance on ImageNet and COCO datasets. For example, the SSB-ResNet-RS-200 achieved 82.6% accuracy on ImageNet dataset, which is 0.6% higher than the baseline ResNet-RS-152 with a similar complexity. Visualization shows the advantage of SSBNet in allowing different layers to focus on different positions, and ablation studies further validate the advantage of adaptive sampling over uniform methods.

cs.CV↗