To exploit unprecedented data generation in mobile edge networks, federated learning (FL) has emerged as a promising alternative to the conventional centralized machine learning (ML). However, there are some critical challenges for FL deployment. One major challenge called straggler issue severely limits FL's coverage where the device with the weakest channel condition becomes the bottleneck of the model aggregation performance. Besides, the huge uplink communication overhead compromises the effectiveness of FL, which is particularly pronounced in large-scale systems. To address the straggler issue, we propose the integration of an unmanned aerial vehicle (UAV) as the parameter server (UAV-PS) to coordinate the FL implementation. We further employ over-the-air computation technique that leverages the superposition property of wireless channels for efficient uplink communication. Specifically, in this paper, we develop a novel UAV-enabled over-the-air asynchronous FL (UAV-AFL) framework which supports the UAV-PS in updating the model continuously to enhance the learning performance. Moreover, we conduct a convergence analysis to quantitatively capture the impact of model asynchrony, device selection and communication errors on the UAV-AFL learning performance. Based on this, a unified communication-learning problem is formulated to maximize asymptotical learning performance by optimizing the UAV-PS trajectory, device selection and over-the-air transceiver design. Simulation results demonstrate that the proposed scheme achieves substantially learning efficiency improvement compared with the state-of-the-art approaches.
In this paper, we propose a new message passing algorithm that utilizes hybrid vector message passing (HVMP) to solve the generalized bilinear factorization (GBF) problem. The proposed GBF-HVMP algorithm integrates expectation propagation (EP) and variational message passing (VMP) via variational free energy minimization, yielding tractable Gaussian messages. Furthermore, GBF-HVMP enables vector/matrix variables rather than scalar ones in message passing, resulting in a loop-free Bayesian network that improves convergence. Numerical results show that GBF-HVMP significantly outperforms state-of-the-art methods in terms of NMSE performance and computational complexity.
Existing near-field localization algorithms generally face a scalability issue when the number of antennas at the sensor array goes large. To address this issue, this paper studies a passive localization system, where an extremely large-scale antenna array (ELAA) is deployed at the base station (BS) to locate a user that transmits signals. The user is considered to be in the near-field (Fresnel) region of the BS array. We propose a novel algorithm, named array partitioning based location estimation (APLE), for scalable near-field localization. The APLE algorithm is developed based on the basic assumption that, by partitioning the ELAA into multiple subarrays, the user can be approximated as in the far-field region of each subarray. The APLE algorithm determines the user's location by exploiting the differences in the angles of arrival (AoAs) of the subarrays. Specifically, we establish a probability model of the received signal based on the geometric constraints of the user's location and the observed AoAs. Then, a message-passing algorithm, i.e., the proposed APLE algorithm, is designed for user localization. APLE exhibits linear computational complexity with the number of BS antennas, leading to a significant reduction in complexity compared to the existing methods. Besides, numerical results demonstrate that the proposed APLE algorithm outperforms the existing baselines in terms of localization accuracy.
Satellite Internet of Things (IoT) is to use satellites as the access points for IoT devices to achieve the global coverage of future IoT systems, and is expected to support burgeoning IoT applications, including communication, sensing, and computing. However, the complex and dynamic satellite environments and limited network resources raise new challenges in the design of satellite IoT systems. In this article, we focus on the joint design of communication, sensing, and computing to improve the performance of satellite IoT, which is quite different from the case of terrestrial IoT systems. We describe how the integration of the three functions can enhance system capabilities, and summarize the state-of-the-art solutions. Furthermore, we discuss the main challenges of integrating communication, sensing, and computing in satellite IoT to be solved with pressing interest.
Decentralized federated learning (DFL), inherited from distributed optimization, is an emerging paradigm to leverage the explosively growing data from wireless devices in a fully distributed manner.DFL enables joint training of machine learning model under device to device (D2D) communication fashion without the coordination of a parameter server. However, the deployment of wireless DFL is facing some pivotal challenges. Communication is a critical bottleneck due to the required extensive message exchange between neighbor devices to share the learned model. Besides, consensus becomes increasingly difficult as the number of devices grows because there is no available central server to perform coordination. To overcome these difficulties, this paper proposes employing over-the-air computation (Aircomp) to improve communication efficiency by exploiting the superposition property of analog waveform in multi-access channels, and introduce the mixing matrix mechanism to promote consensus using the spectral property of symmetric doubly stochastic matrix. Specifically, we develop a novel multiple-input multiple-output over-the-air DFL (MIMO OA-DFL) framework to study over-the-air DFL problem over MIMO multiple access channels. We conduct a general convergence analysis to quantitatively capture the influence of aggregation weight and communication error on the MIMO OA-DFL performance in \emph{ad hoc} networks. The result shows that the communication error together with the spectral gap of mixing matrix has a significant impact on the learning performance. Based on this, a joint communication-learning optimization problem is formulated to optimize transceiver beamformers and mixing matrix. Extensive numerical experiments are performed to reveal the characteristics of different topologies and demonstrate the substantial learning performance enhancement of our proposed algorithm.
Task-oriented communication offers ample opportunities to alleviate the communication burden in next-generation wireless networks. Most existing work designed the physical-layer communication modules and learning-based codecs with distinct objectives: learning is targeted at accurate execution of specific tasks, while communication aims at optimizing conventional communication metrics, such as throughput maximization, delay minimization, or bit error rate minimization. The inconsistency between the design objectives may hinder the exploitation of the full benefits of task-oriented communications. In this paper, we consider a specific task-oriented communication system for multi-device edge inference over a multiple-input multiple-output (MIMO) multiple-access channel, where the learning (i.e., feature encoding and classification) and communication (i.e., precoding) modules are designed with the same goal of inference accuracy maximization. Instead of end-to-end learning which involves both the task dataset and wireless channel during training, we advocate a separate design of learning and communication to achieve the consistent goal. Specifically, we leverage the maximal coding rate reduction (MCR2) objective as a surrogate to represent the inference accuracy, which allows us to explicitly formulate the precoding optimization problem. We cast valuable insights into this formulation and develop a block coordinate descent (BCD) solution algorithm. Moreover, the MCR2 objective also serves the loss function of the feature encoding network, based on which we characterize the received features as a Gaussian mixture (GM) model, facilitating a maximum a posteriori (MAP) classifier to infer the result. Simulation results on both the synthetic and real-world datasets demonstrate the superior performance of the proposed method compared to various baselines.
In this paper, we develop a new method to automatically convert 2D line drawings from three orthographic views into 3D CAD models. Existing methods for this problem reconstruct 3D models by back-projecting the 2D observations into 3D space while maintaining explicit correspondence between the input and output. Such methods are sensitive to errors and noises in the input, thus often fail in practice where the input drawings created by human designers are imperfect. To overcome this difficulty, we leverage the attention mechanism in a Transformer-based sequence generation model to learn flexible mappings between the input and output. Further, we design shape programs which are suitable for generating the objects of interest to boost the reconstruction accuracy and facilitate CAD modeling applications. Experiments on a new benchmark dataset show that our method significantly outperforms existing ones when the inputs are noisy or incomplete.
To address the limitations of traditional over-the-air federated learning (OA-FL) such as limited server coverage and low resource utilization, we propose an OA-FL in MIMO cloud radio access network (MIMO Cloud-RAN) framework, where edge devices upload (or download) model parameters to the cloud server (CS) through access points (APs). Specifically, in every training round, there are three stages: edge aggregation; global aggregation; and model updating and broadcasting. To better utilize the correlation among APs, called inter-AP correlation, we propose modeling the global aggregation stage as a lossy distributed source coding (L-DSC) problem to make analysis from the perspective of rate-distortion theory. We further analyze the performance of the proposed OA-FL in MIMO Cloud-RAN framework. Based on the analysis, we formulate a communication-learning optimization problem to improve the system performance by considering the inter-AP correlation. To solve this problem, we develop an algorithm by using alternating optimization (AO) and majorization-minimization (MM), which effectively improves the FL learning performance. Furthermore, we propose a practical design that demonstrates the utilization of inter-AP correlation. The numerical results show that the proposed practical design effectively leverages inter-AP correlation, and outperforms other baseline schemes.
Reconfigurable intelligent surface (RIS) has attracted enormous interest for its potential advantages in assisting both wireless communication and environmental sensing. In this paper, we study a challenging multiuser tracking problem in the multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) system aided by multiple RISs. In particular, we assume that a multi-antenna base station (BS) receives the OFDM symbols from single-antenna users reflected by multiple RISs and tracks the positions of these users. Considering the users' mobility and the blockage of light-of-sight (LoS) paths, we establish a probability transition model to characterize the tracking process, where the geometric constraints between channel parameters and multiuser positions are utilized. We further develop an online message passing algorithm, termed the Bayesian multiuser tracking (BMT) algorithm, to estimate the multiuser positions, the angles-of-arrivals (AoAs) at multiple RISs, and the time delay and the blockage of the LoS path. The Bayesian Cramer Rao bound (BCRB) is derived as the fundamental performance limit of the considered tracking problem. Based on the BCRB, we optimize the passive beamforming (PBF) of the multiple RISs to improve the tracking performance. Simulation results show that the proposed PBF design significantly outperforms the counterpart schemes, and our BMT algorithm can achieve up to centimeter-level tracking accuracy.
This paper investigates the problem of activity detection and channel estimation in cooperative multi-cell massive access systems with temporally correlated activity, where all access points (APs) are connected to a central unit via fronthaul links. We propose to perform user-centric AP cooperation for computation burden alleviation and introduce a generalized sliding-window detection strategy for fully exploiting the temporal correlation in activity. By establishing the probabilistic model associated with the factor graph representation, we propose a scalable Dynamic Compressed Sensing-based Multiple Measurement Vector Generalized Approximate Message Passing (DCS-MMV-GAMP) algorithm from the perspective of Bayesian inference. Therein, the activity likelihood is refined by performing standard message passing among the activities in the spatial-temporal domain and GAMP is employed for efficient channel estimation. Furthermore, we develop two schemes of quantize-and-forward (QF) and detect-and-forward (DF) based on DCS-MMV-GAMP for the finite-fronthaul-capacity scenario, which are extensively evaluated under various system limits. Numerical results verify the significant superiority of the proposed approach over the benchmarks. Moreover, it is revealed that QF can usually realize superior performance when the antenna number is small, whereas DF shifts to be preferable with limited fronthaul capacity if the large-scale antenna arrays are equipped.