Existing semantic communication schemes primarily focus on single-hop scenarios, overlooking the challenges of multi-hop wireless image transmission. As semantic communication is inherently lossy, distortion accumulates over multiple hops, leading to significant performance degradation. To address this, we propose the multi-hop parallel image semantic communication (MHPSC) framework, which introduces a parallel residual compensation link at each hop against distortion accumulation. To minimize the associated transmission bandwidth overhead, a coarse-to-fine residual compression scheme is designed. A deep learning-based residual compressor first condenses the residuals, followed by the adaptive arithmetic coding (AAC) for further compression. A residual distribution estimation module predicts the prior distribution for the AAC to achieve fine compression performances. This approach ensures robust multi-hop image transmission with only a minor increase in transmission bandwidth. Experimental results confirm that MHPSC outperforms both existing semantic communication and traditional separated coding schemes.

Existing wireless video transmission schemes directly conduct video coding in pixel level, while neglecting the inner semantics contained in videos. In this paper, we propose a wireless video semantic communication framework, abbreviated as WVSC, which integrates the idea of semantic communication into wireless video transmission scenarios. WVSC first encodes original video frames as semantic frames and then conducts video coding based on such compact representations, enabling the video coding in semantic level rather than pixel level. Moreover, to further reduce the communication overhead, a reference semantic frame is introduced to substitute motion vectors of each frame in common video coding methods. At the receiver, multi-frame compensation (MFC) is proposed to produce compensated current semantic frame with a multi-frame fusion attention module. With both the reference frame transmission and MFC, the bandwidth efficiency improves with satisfying video transmission performance. Experimental results verify the performance gain of WVSC over other DL-based methods e.g. DVSC about 1 dB and traditional schemes about 2 dB in terms of PSNR.

This paper investigates the joint optimization of unmanned aerial vehicle-mounted base station (UAV-BS) movement and user association for multiple UAV-BSs providing emergency services to indoor users. Specifically, we focus on optimizing associations between UAV-BSs and indoor users within an outdoor-to-indoor path loss model that accounts for floor penetration. The primary objective is to determine the optimal associations between UAV-BSs and indoor users, while also addressing how multiple UAV-BSs should move to establish these associations quickly. To solve this problem, we propose a novel multi-agent reinforcement learning (MARL) architecture featuring three key innovations: a dual-action structure that decouples the complex decision-making process into separate movement and association actions, a multi-agent double deep Q-network (MADDQN) to learn optimal policies, and prioritized experience replay (PER) to improve learning efficiency. Simulation results demonstrate that the proposed algorithm significantly outperforms baseline methods—including a multi-agent deep Q-network (MADQN), multi-agent independent actor-critic (MAIAC), multi-agent deep deterministic policy gradient (MADDPG), and a consensus-based bundle algorithm (CBBA)—across all metrics. Furthermore, a series of rigorous ablation studies systematically validates the contribution of each component. Overall, the simulation results validate the superiority and robustness of our proposed algorithm in dynamic and challenging indoor environments.

Neural network-based medium access control (MAC) protocol models (NPMs) improve goodput through site-specific operations but are vulnerable to shifts from their training network environments, such as changes in the number of user equipments (UEs) severely degrading goodput. To enhance resilience against such environmental shifts, we propose three novel token-based MAC protocol frameworks empowered by large language models (LLMs). First, we introduce a token-based protocol model (TPM), where an LLM generates MAC signaling messages. By editing LLM instruction prompts, TPM enables instant adaptation, which can be further enhanced by TextGrad, an LLM-based automated prompt optimizer. TPM inference is fast but coarse due to the lack of real interactions with the changed environment, and computationally intensive due to the large size of the LLM. To improve goodput and computation efficiency, we develop T2NPM, which transfers and augments TPM knowledge into an NPM via knowledge distillation (KD). Integrating TPM and T2NPM, we propose T3NPM, which employs TPM in the early phase and switches to T2NPM at a later stage. To optimize this phase switching, we design a novel metric of meta-resilience, which quantifies resilience to unknown target goodput after environmental shifts. Simulations corroborate that T3NPM achieves 20.56% higher meta-resilience than NPM with 19.8× lower computation cost than TPM in FLOPs.

Tokens are fundamental processing units of generative AI (GenAI) and large language models (LLMs), and token communication (TC) is essential for enabling remote AI-generate content (AIGC) and wireless LLM applications. Unlike traditional bits, each of which is independently treated, the semantics of each token depends on its surrounding context tokens. This inter-token dependency makes TC vulnerable to outage channels, where the loss of a single token can significantly distort the original message semantics. Motivated by this, this paper focuses on optimizing token packetization to maximize the average token similarity (ATS) between the original and received token messages under outage channels. Due to inter-token dependency, this token grouping problem is combinatorial, with complexity growing exponentially with message length. To address this, we propose a novel framework of semantic packet aggregation with lookahead search (SemPA-Look), built on two core ideas. First, it introduces the residual semantic score (RSS) as a token-level surrogate for the message-level ATS, allowing robust semantic preservation even when a certain token packet is lost. Second, instead of full search, SemPA-Look applies a lookahead search-inspired algorithm that samples intra-packet token candidates without replacement (fixed depth), conditioned on inter-packet token candidates sampled with replacement (fixed width), thereby achieving linear complexity. Experiments on a remote AIGC task with the MS-COCO dataset (text captioned images) demonstrate that SemPA-Look achieves high ATS and LPIPS scores comparable to exhaustive search, while reducing computational complexity by up to 40$\times$. Compared to other linear-complexity algorithms such as the genetic algorithm (GA), SemPA-Look achieves 10$\times$ lower complexity, demonstrating its practicality for remote AIGC and other TC applications.

To support emerging language-based applications using dispersed and heterogeneous computing resources, the hybrid language model (HLM) offers a promising architecture, where an on-device small language model (SLM) generates draft tokens that are validated and corrected by a remote large language model (LLM). However, the original HLM suffers from substantial communication overhead, as the LLM requires the SLM to upload the full vocabulary distribution for each token. Moreover, both communication and computation resources are wasted when the LLM validates tokens that are highly likely to be accepted. To overcome these limitations, we proposecommunication-efficient and uncertainty-aware HLM (CU-HLM). In CU-HLM, the SLM transmits truncated vocabulary distributions only when its output uncertainty is high. We validate the feasibility of this opportunistic transmission by discovering a strong correlation between SLM’s uncertainty and LLM’s rejection probability. Furthermore, we theoretically derive optimal uncertainty thresholds and optimal vocabulary truncation strategies. Simulation results show that, compared to standard HLM, CU-HLM achieves up to 206× higher token throughput by skipping 74.8% transmissions with 97.4% vocabulary compression, while maintaining 97.4% accuracy.

Existing wireless video transmission schemes directly conduct video coding in pixel level, while neglecting the inner semantics contained in videos. In this paper, we propose a wireless video semantic communication framework with decoupled diffusion multi-frame compensation (DDMFC), abbreviated as WVSC-D, which integrates the idea of semantic communication into wireless video transmission scenarios. WVSC-D first encodes original video frames as semantic frames and then conducts video coding based on such compact representations, enabling the video coding in semantic level rather than pixel level. Moreover, to further reduce the communication overhead, a reference semantic frame is introduced to substitute motion vectors of each frame in common video coding methods. At the receiver, DDMFC is proposed to generate compensated current semantic frame by a two-stage conditional diffusion process. With both the reference frame transmission and DDMFC frame compensation, the bandwidth efficiency improves with satisfying video transmission performance. Experimental results verify the performance gain of WVSC-D over other DL-based methods e.g. DVSC about 1.8 dB in terms of PSNR.

Wi-Fi 7 introduces the restricted target wake time (RTWT) mechanism, which is vital for Industrial IoT (IIoT) applications requiring periodic, reliable, and low-latency communication. RTWT enables deterministic channel access by assigning scheduled transmission slots to stations (STAs), minimizing contention and interference. However, determining efficient RTWT slot assignments remains challenging in dense networks, where conventional interference graph-based models lack flexibility and scalability. To overcome this, we propose a scalable interference graph learning (IGL) framework that learns optimal interference graph representations for graph coloring-based RTWT scheduling. The IGL leverages an evolution strategy (ES) to train a neural network (NN) using a single network-wide reward, avoiding costly edge-wise feedback. Furthermore, a deep hashing function (DHF) groups interfering STAs, limiting training and inference to relevant subsets and greatly reducing complexity. Simulation results demonstrate that the proposed IGL improves slot efficiency by up to 25%, reduces packet losses by up to 30% in dynamic environments. Thanks to DHF, it also reduces the training and inference time of IGL by 4 and 8 times, respectively, and the online slot assignment time by 3 times in large networks.

Wireless time-sensitive networking (WTSN) is essential for Industrial Internet of Things. We address the problem of minimizing time slots needed for WTSN transmissions while ensuring reliability subject to interference constraints—an NP-hard task. Existing semidefinite programming (SDP) methods can relax and solve the problem but suffer from high polynomial complexity. We propose a sparse interference graph-aided SDP (SIG-SDP) framework that exploits the interference’s sparsity arising from attenuated signals between distant user pairs. First, the framework utilizes the sparsity to establish the upper and lower bounds of the minimum number of slots and uses binary search to locate the minimum within the bounds. Here, for each searched slot number, the framework optimizes a positive semidefinite (PSD) matrix indicating how likely user pairs share the same slot, and the constraint feasibility with the optimized PSD matrix further refines the slot search range. Second, the framework designs a matrix multiplicative weights (MMW) algorithm that accelerates the optimization, achieved by only sparsely adjusting interfering user pairs’ elements in the PSD matrix while skipping the non-interfering pairs. We also design an online architecture to deploy the framework to adjust slot assignments based on real-time interference measurements. Simulations show that the SIG-SDP framework converges in near-linear complexity and is highly scalable to large networks. The framework minimizes the number of slots with up to 10 times faster computation and up to 100 times lower packet loss rates than compared methods. The online architecture demonstrates how the algorithm complexity impacts dynamic networks’ performance.

Semantic communication (SemCom) has recently emerged as a promising paradigm for next-generation wireless systems. Empowered by advanced artificial intelligence (AI) technologies, SemCom has achieved significant improvements in transmission quality and efficiency. However, existing SemCom systems either rely on training over large datasets and specific channel conditions or suffer from performance degradation under channel noise when operating in a training-free manner. To address these issues, we explore the use of generative diffusion models (GDMs) as training-free SemCom systems. Specifically, we design a semantic encoding and decoding method based on the inversion and sampling process of the denoising diffusion implicit model (DDIM), which introduces a two-stage forward diffusion process, split between the transmitter and receiver to enhance robustness against channel noise. Moreover, we optimize sampling steps to compensate for the increased noise level caused by channel noise. We also conduct a brief analysis to provide insights about this design. Simulations on the Kodak dataset validate that the proposed system outperforms the existing baseline SemCom systems across various metrics.

Real-world graph signals are inherently time-varying and evolve smoothly, making the characterization of such data challenging. We propose a novel approach for reconstructing missing time-varying graph data by leveraging the assumption that the latent variable responsible for generating this data evolves according to nonlinear dynamics. To learn these dynamics, we employ a Koopman autoencoder, and apply graph embedding techniques to map the graph data into a latent space. While existing approaches require known time-invariant Laplacian matrices, our proposed approach can perform reconstruction without needing these matrices, which can also be time-varying. Simulation results show that our method surpasses baseline approaches, achieving a reduction in reconstruction error by 47% to 61% compared to alternative methods, while effectively reconstructing time-varying graphs with dynamic structures.

Text-based communication is expected to be prevalent in 6G applications such as wireless AI-generated content (AIGC). Motivated by this, this paper addresses the challenges of transmitting text prompts over erasure channels for a text-to-image AIGC task by developing the semantic segmentation and repeated transmission (SMART) algorithm. SMART groups words in text prompts into packets, prioritizing the task-specific significance of semantics within these packets, and optimizes the number of repeated transmissions. Simulation results show that SMART achieves higher similarities in received texts and generated images compared to a character-level packetization baseline, while reducing computing latency by orders of magnitude compared to an exhaustive search baseline.

Six-dimensional movable antenna (6DMA) is an innovative and transformative technology to improve wireless network capacity by adjusting the 3D positions and 3D rotations of antennas/surfaces (sub-arrays) based on the channel spatial distribution. For optimization of the antenna positions and rotations, the acquisition of statistical channel state information (CSI) is essential for 6DMA systems. In this paper, we unveil for the first time a new directional sparsity property of the 6DMA channels between the base station (BS) and the distributed users, where each user has significant channel gains only with a (small) subset of 6DMA position-rotation pairs, which can receive direct/reflected signals from the user. By exploiting this property, a covariance-based algorithm is proposed for estimating the statistical CSI in terms of the average channel power at a small number of 6DMA positions and rotations. Based on such limited channel power estimation, the average channel powers for all possible 6DMA positions and rotations in the BS movement region are reconstructed by further estimating the multi-path average power and direction-of-arrival (DOA) vectors of all users. Simulation results show that the proposed directional sparsitybased algorithm can achieve higher channel power estimation accuracy than existing benchmark schemes, while requiring a lower pilot overhead.

The application of machine learning (ML) to communication systems is expected to play a pivotal role in future artificial intelligence (AI)-based next-generation wireless networks. While most existing works focus on ML techniques for static wireless environments, they often face limitations when applied to highly dynamic environments, such as flying ad hoc networks (FANETs). This paper explores the use of data-driven Koopman approaches to address these challenges. Specifically, we investigate how these approaches can model UAV trajectory dynamics within FANETs, enabling more accurate predictions and improved network performance. By leveraging Koopman operator theory, we propose two possible approaches—centralized and distributed—to efficiently address the challenges posed by the constantly changing topology of FANETs. To demonstrate this, we consider a FANET performing surveillance with UAVs following predetermined trajectories and predict signal-to-interference-plus-noise ratios (SINRs) to ensure reliable communication between UAVs. Our results show that these approaches can accurately predict connectivity and isolation events that lead to modelled communication outages. This capability could help UAVs schedule their transmissions based on these predictions.

We introduce CSI-Inpainter, a novel approach for obstacle removal using Wi-Fi CSI. This method harnesses CSI data to reconstruct obscured visual elements, regardless of lighting conditions. Extensive empirical evaluation in both office and industrial settings demonstrates the effectiveness of CSI-Inpainter’s exceptional ability to identify and reconstruct occluded segments, outperforming traditional baselines and our received signal strength indicator (RSSI)-based work, RF-Inpainter in terms of visual quality. Our findings emphasize the superiority of CSI data over RSSI for providing richer visual information and underscore the critical role of optimal sensor placement and data fusion from multiple CSI sensors in enhancing the performance. CSI-Inpainter represents a significant advancement in obstacle removal for various applications like surveillance, offering new insights into the integration of wireless sensing and visual scene recovery, expanding the potential applications of Computer Vision in real-world environments.

According to the advances in quantum computing and distributed learning, quantum federated learning (QFL) has recently become an emerging field of study. In QFL, each quantum computer or device locally trains its quantum neural network (QNN) with trainable gates, and communicates only these gate parameters over classical channels, without costly quantum communications. To successfully opeate QFL under various and dynamic channel conditions in Internet of Things (IoT) environments, this article develops a novel depth-controllable architecture of entangled slimmable QNNs (eSQNNs), and thus, proposes an entangled slimmable QFL (eSQFL) that communicates the superposition-coded parameters of eSQNNs. Even though the proposed eSQNN-based eSQFL is superior, training the depth-controllable eSQNN architecture is challenging due to high-entanglement entropy and interdepth interference. Therefore, the proposed method in this article mitigates the interference using entanglement controlled universal (CU) gates and an inplace fidelity distillation (IPFD) regularizer penalizing interdepth quantum state differences, respectively. Furthermore, the proposed method optimizes the superposition coding power allocation by deriving and minimizing the convergence bound of eSQFL. The novelty of this work is evaluated via extensive simulations in terms of prediction accuracy, fidelity, and entropy compared to Vanilla QFL as well as under different channel conditions and various data distributions.

Semantic encoders and decoders for digital semantic communication (SC) often struggle to adapt to variations in unpredictable channel environments and diverse system designs. To address these challenges, this paper proposes a novel framework for training semantic encoders and decoders to enable channel-adaptive digital SC. The core idea is to use binary symmetric channel (BSC) as a universal representation of generic digital communications, eliminating the need to specify channel environments or system designs. Based on this idea, our framework employs parallel BSCs to equivalently model the relationship between the encoder’s output and the decoder’s input. The bit-flip probabilities of these BSCs are treated as trainable parameters during end-to-end training, with varying levels of regularization applied to address diverse requirements in practical systems. The advantage of our framework is justified by developing a training-aware communication strategy for the inference stage. This strategy makes communication bit errors align with the pre-trained bit-flip probabilities by adaptively selecting power and modulation levels based on practical requirements and channel conditions. Simulation results demonstrate that the proposed framework outperforms existing training approaches in terms of both task performance and power consumption.

Due to the emergence of various wireless sensing technologies, numerous positioning algorithms have been introduced in the literature, categorized intogeometry-driven positioning(GP) anddata-driven positioning(DP). These approaches have respective limitations, e.g., a non-line-of-sight issue for GP and the lack of a high-dimensional and labeled dataset for DP, which could be complemented by integrating both methods. To this end, this paper aims to introduce a novel principle calledcombinatorial data augmentation(CDA), a catalyst for the two approaches’ seamless integration. Specifically, GP-based data samples augmented from different positioning element combinations are calledpreliminary estimated locations(PELs), which can be used as high-dimensional inputs for DP. We confirm the CDA’s effectiveness from field experiments based on WiFiround-trip times(RTTs) andinertial measurement units(IMUs) by designing several CDA-based positioning algorithms. First, we show that CDA offers various metrics quantifying each PEL’s reliability, thereby extracting important PELs for WiFi RTT positioning. Second, CDA helps compute the observation error covariance matrix of a Kalman filter for fusing two position estimates derived by WiFi RTTs and IMUs. Third, we use the important PELs and the above position estimate as the corresponding input feature and the real-time label for fingerprint-based positioning as a representative DP algorithm. It provides accurate and reliable positioning results, with an average positioning error of 1.58 (m) and a standard deviation of 0.90 (m).

Cell-free multiple-input-multiple-output (MIMO) is poised to enable scalable next-generation cellular networks. To this end, it is crucial to optimize the cell-free MIMO link configuration, including user associations, data stream allocation, and beamforming (BF). However, the scalability of link configuration optimization is significantly challenged as signaling and computational costs increase with the number of base stations (BSs) and user equipments (UEs). To address this scalability issue, this paper proposes a distributed multi-agent deep reinforcement learning (MADRL)-based cell-free MIMO link configuration framework that leverages interference approximation to minimize signaling overhead required for channel state information (CSI) exchange. Our proposed framework reduces the solution search space suitable for distributed MADRL, by decomposing the original sum rate maximization problem into BS-specific tasks. Simulation results show that our proposed method achieves scalability, as the sum rate increases with the number of BSs and UEs.

By integrating recent advances in large language models (LLMs) and generative models into the emerging semantic communication (SC) paradigm, in this article we put forward to a novel framework of language-oriented semantic communication (LSC). In LSC, machines communicate using human language messages that can be interpreted and manipulated via natural language processing (NLP) techniques for SC efficiency. To demonstrate LSC’s potential, we introduce three innovative algorithms: 1) semantic source coding (SSC) which compresses a text prompt into its key head words capturing the prompt’s syntactic essence while maintaining their appearance order to keep the prompt’s context; 2) semantic channel coding (SCC) that improves robustness against errors by substituting head words with their lenghthier synonyms; and 3) semantic knowledge distillation (SKD) that produces listener-customized prompts via in-context learning the listener’s language style. In a communication task for progressive text-to-image generation, the proposed methods achieve higher perceptual similarities with fewer transmissions while enhancing robustness in noisy communication channels.

In this work, we compare emergent communication (EC) built upon multi-agent deep reinforcement learning (MADRL) and language-oriented semantic communication (LSC) empowered by a pre-trained large language model (LLM) using human language. In a multi-agent remote navigation task, with multimodal input data comprising location and channel maps, it is shown that EC incurs high training cost and struggles when using multimodal data, whereas LSC yields high inference computing cost due to the LLM's large size. To address their respective bottlenecks, we propose a novel framework of language-guided EC (LEC) by guiding the EC training using LSC via knowledge distillation (KD). Simulations corroborate that LEC achieves faster travel time while avoiding areas with poor channel conditions, as well as speeding up the MADRL training convergence by up to 61.8% compared to EC.

In this paper, we address a radio resource allocation challenge for multiple unmanned aerial vehicles (UAVs) connected to low Earth orbit (LEO) satellites, supporting ground users through store-and-forward transmission. Unlike existing integrated systems assuming seamless fusion of LEOs and UAVs, our practical approach treats UAVs and LEOs as nodes of distinct systems. UAVs act as relay nodes, receiving and forwarding data packets to LEO with possibly decapsulation and encapsulation. Our proposed resource allocation minimizes maximum transmission delays or buffer lengths of UAVs, formulated as a convex optimization problem. Given unknown arrival rates and channel conditions, we explore reinforcement learning for learning these critical parameters in resource allocation.

Semantic communication, emerging as a promising paradigm for data transmission, offers an innovative departure from the constraints of Shannon theory, heralding significant advancements in future communication technologies. Despite the proliferation of proposed approaches, there are still numerous challenges. In this paper, we review current semantic communication methodologies and shed light on pivotal issues and addressing certain discrepancies that exist within the field. By elucidating both dos and don'ts, we aim to provide valuable insights into the emerging landscape of semantic communication.

Low Probability of Detection (LPD) communication aims to obscure the very presence of radio frequency (RF) signals, going beyond just hiding the content of the communication. However, the use of Unmanned Aerial Vehicles (UAVs) introduces a challenge, as UAVs can detect RF signals from the ground by hovering over specific areas of interest. With the growing utilization of UAVs in modern surveillance, there is a crucial need for a thorough understanding of their unknown nonlinear dynamic trajectories to effectively implement LPD communication. Unfortunately, this critical information is often not readily available, posing a significant hurdle in LPD communication. To address this issue, we consider a case-study for enabling terrestrial LPD communication in the presence of multiple UAVs that are engaged in surveillance. We introduce a novel framework that combines graph neural networks (GNN) with Koopman theory to predict the trajectories of multiple fixed-wing UAVs over an extended prediction horizon. Using the predicted UAV locations, we enable LPD communication in a terrestrial ad-hoc network by controlling nodes' transmit powers to keep the received power at UAVs' predicted locations minimized. Our extensive simulations validate the efficacy of the proposed framework in accurately predicting the trajectories of multiple UAVs, thereby effectively establishing LPD communication.

In this study, we delve into the intricacies of semantic communication-control codesign (CoCoCo) for wireless mixed logical dynamical (MLD) systems operating under signal temporal logic (STL) specifications. Our novel contribution, the MLD-Koopman autoencoder (AE), emerges as a method to linearize the progression of system states within a feature space. This linearization effectively mitigates the communication and computation costs associated with MLD system control. To surmount the challenges posed by multiple correlated MLD systems that possess distinct logical control rules while sharing baseline dynamics, we present the compositional logical dynamical (CLD)-Koopman AE as a remedy to the scalability limitations of the MLD-Koopman AE. This innovative approach incorporates two pivotal models—the dynamics semantic Koopman (DSK) model, capturing semantic correlations among MLD systems, and the logical semantic Koopman (LSK) model, encoding logical control rules. These models portray the linear evolution of baseline dynamics and control rules within a feature space, facilitating predictions of future states for multiple MLD systems with constrained communication. Validation comes from simulations on large-scale inverted cart-pole systems, demonstrating the prowess of the CLD-Koopman AE in achieving an average state prediction performance 82.77% higher than other predictive benchmarks, particularly evident at a signal-to-noise ratio (SNR) of 10 dB.

In recent years, split learning (SL) has emerged as a promising distributed learning framework that can utilize big data in parallel without privacy leakage while reducing client-side computing resources. In the initial implementation of SL, however, the server serves multiple clients sequentially incurring high latency. Parallel implementation of SL can alleviate this latency problem, but existing Parallel SL algorithms compromise scalability due to its fundamental structural problem. To this end, our previous works have proposed two scalable Parallel SL algorithms, dubbed SGLR and LocFedMix-SL, by solving the aforementioned fundamental problem of the Parallel SL structure. In this article, we propose a novel Parallel SL framework, coined Mix2SFL, that can ameliorate both accuracy and communication-efficiency while still ensuring scalability. Mix2SFL first supplies more samples to the server through a manifold mixup between the smashed data uploaded to the server as in SmashMix of LocFedMix-SL, and then averages the split-layer gradient as in GradMix of SGLR, followed by local model aggregation as in SFL. Numerical evaluation corroborates that Mix2SFL achieves improved performance in both accuracy and latency compared to the state-of-the-art SL algorithm with scalability guarantees. Moreover, its convergence speed as well as privacy guarantee are validated through the experimental results.

Although quantum supremacy is yet to come, there has recently been an increasing interest in identifying the potential of quantum machine learning (QML) in the looming era of practical quantum computing. Motivated by this, in this article we re-design multi-agent reinforcement learning (MARL) based on the unique characteristics of quantum neural networks (QNNs) having two separate dimensions of trainable parameters: angle parameters affecting the output qubit states, and pole parameters associated with the output measurement basis. Exploiting this dyadic trainability as meta-learning capability, we propose quantum meta MARL (QM2ARL) that first applies angle training for meta-QNN learning, followed by pole training for few-shot or local-QNN training. To avoid overfitting, we develop an angle-to-pole regularization technique injecting noise into the pole domain during angle training. Furthermore, by exploiting the pole as the memory address of each trained QNN, we introduce the concept of pole memory allowing one to save and load trained QNNs using only two-parameter pole values. We theoretically prove the convergence of angle training under the angle-to-pole regularization, and by simulation corroborate the effectiveness of QM2ARL in achieving high reward and fast convergence, as well as of the pole memory in fast adaptation to a time-varying environment.

This paper presents a wireless data collection frame-work that employs an unmanned aerial vehicle (UAV) to efficiently gather data from distributed IoT sensors deployed in a large area. Our approach takes into account the non-zero communication ranges of the sensors to optimize the flight path of the UAV, resulting in a variation of the Traveling Salesman Problem (TSP). We prove mathematically that the optimal waypoints for this TSP-variant problem are restricted to the boundaries of the sensor communication ranges, greatly reducing the solution space. Building on this finding, we develop a low-complexity UAV-assisted sensor data collection algorithm, and demonstrate its effectiveness in a selected use case where we minimize the total energy consumption of the UAV and sensors by jointly optimizing the UAV's travel distance and the sensors' communication ranges.

Vector Quantized Variational Autoencoder (VQ-VAE) has shown promise in representing diverse and complex data distributions in deep learning, making it a potential solution for various applications including wireless communications. In this paper, we propose a joint source-channel coding scheme based on VQ-VAE for point-to-point wireless communication. Our approach leverages the dependence of the encoder and decoder on a given dataset and channel conditions to develop efficient encoding and decoding schemes, leading to improved reliability and efficiency even in the presence of noisy wireless channels. We demonstrate the effectiveness of our proposed approach through extensive simulations in handling realistic wireless communication scenarios. In addition, we discuss potential connections to semantic communication and highlight the secure and energy-efficient nature of our approach.

This paper proposes new framework of communication system leveraging promising generation capabilities of multimodal generative models. Regarding nowadays’ smart applications, successful communication can be made by conveying the perceptual meaning, which we set as text prompt. Text serves as a suitable semantic representation of image data as it has evolved to instruct an image or generate image through mutli-modal techniques, by being interpreted in a manner similar to human cogitation. Utilizing text can also reduce the overload compared to transmitting the intact data itself. The transmitter converts objective image to text through multi-model generation process and the receiver reconstructs the image using reverse process. Each word in the text sentence has each syntactic role, responsible for particular piece of information the text contains. For further efficiency in communication load, the transmitter sequentially sends words in priority of carrying the most information until reaches successful communication. Therefore, our primary focus is on the promising design of a communication system based on image-to-text transformation and the proposed schemes for sequentially transmitting word tokens. Our work is expected to pave a new road of utilizing state-of-the-art generative models to real communication systems.

Metaverse over wireless networks is an emerging use case of the sixth generation (6G) wireless systems, posing unprecedented challenges in terms of its multi-modal data transmissions with stringent latency and reliability requirements. Towards enabling this wireless metaverse, in this article we propose a novel semantic communication (SC) framework by decomposing the metaverse into human/machine agent-specific semantic multiverses (SMs). An SM stored at each agent comprises a semantic encoder and a generator, leveraging recent advances in generative artificial intelligence (AI). To improve communication efficiency, the encoder learns the semantic representations (SRs) of multi-modal data, while the generator learns how to manipulate them for locally rendering scenes and interactions in the metaverse. Since these learned SMs are biased towards local environments, their success hinges on synchronizing heterogeneous SMs in the background while communicating SRs in the foreground, turning the wireless metaverse problem into the problem of semantic multiverse communication (SMC). Based on this SMC architecture, we propose several promising algorithmic and analytic tools for modeling and designing SMC, ranging from distributed learning and multi-agent reinforcement learning (MARL) to signaling games and symbolic AI.

In this paper, we suggest a method to transform a communication protocol based on deep neural network (NN) into a semantic communication protocol. We need such transformation to alleviate the issues posed by NN's lack of interpretability and redundant parameters due to overparametrization. However, transformation process is challenging because it is difficult to disambiguate the semantics while reducing the protocol's complexity. We solve the challenge by employing NN's activation patterns and probabilistic logic. Lastly, we validate our method by transforming an NN trained for a medium access control (MAC) protocol and verifying its contention performance compared to ALOHA based protocols.

Integrated sensing and communication (ISAC) is a promising technology for next-generation communication systems, allowing concurrent data communication and positioning. However, in the presence of blockages, ISAC does not guarantee accurate positioning due to the lack of echo signals from targets. To address this issue, we study a downlink ISAC system with an unmanned aerial vehicle (UAV) relay that decode-and-forward data signals while securing blockage-free paths. In this UAV-assisted downlink ISAC system, we aim to maximize the sum rate while ensuring a target positioning accuracy by optimizing transmit power allocation. With moving target objects in a three-dimensional (3D) environment, this optimization problem becomes non-trivial due to complicated object positioning state transitions. To relax this complexity, we derive an approximated state transition model of 3D object and thereby formulate a strictly convex optimization problem that guarantees a unique power allocation solution. Numerical results corroborate that the proposed power allocation outperforms the baseline with feedback-based beam training in terms of the achievable sum rate.

Classical medium access control (MAC) protocols are interpretable, yet their task-agnostic control signaling messages (CMs) are ill-suited for emerging mission-critical applications. By contrast, neural network (NN) based protocol models (NPMs) learn to generate task-specific CMs, but their rationale and impact lack interpretability. To fill this void, in this article we propose, for the first time, a semantic protocol model (SPM) constructed by transforming an NPM into an interpretable symbolic graph written in the probabilistic logic programming language (ProbLog). This transformation is viable by extracting and merging common CMs and their connections, while treating the NPM as a CM generator. By extensive simulations, we corroborate that the SPM tightly approximates its original NPM while occupying only 0.02% memory. By leveraging its interpretability and memory-efficiency, we demonstrate several SPM-enabled applications such as SPM reconfiguration for collision-avoidance, as well as comparing different SPMs via semantic entropy calculation and storing multiple SPMs to cope with non-stationary environments.

Federated learning (FL) is a key enabler for efficient communication and computing, leveraging devices’ distributed computing capabilities. However, applying FL in practice is challenging due to the local devices’ heterogeneous energy, wireless channel conditions, and non-independently and identically distributed (non-IID) data distributions. To cope with these issues, this paper proposes a novel learning framework by integrating FL and width-adjustable slimmable neural networks (SNN). Integrating FL with SNNs is challenging due to time-varying channel conditions and data distributions. In addition, existing multi-width SNN training algorithms are sensitive to the data distributions across devices, which makes SNN ill-suited for FL. Motivated by this, we propose a communication and energy-efficient SNN-based FL (namedSlimFL) that jointly utilizessuperposition coding (SC)for global model aggregation andsuperposition training (ST)for updating local models. By applying SC, SlimFL exchanges the superposition of multiple-width configurations decoded as many times as possible for a given communication throughput. Leveraging ST, SlimFL aligns the forward propagation of different width configurations while avoiding inter-width interference during backpropagation. We formally prove the convergence of SlimFL. The result reveals that SlimFL is not only communication-efficient but also deals with non-IID data distributions and poor channel conditions, which is also corroborated by data-intensive simulations.

A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. LEO SAT networks exhibit extremely long link distances of many users under time-varying SAT network topology. This makes existing multiple access protocols, such as random access channel (RACH) based cellular protocol designed for fixed terrestrial network topology, ill-suited. To overcome this issue, in this paper, we propose a novel contention-based random access solution for LEO SAT networks, dubbed emergent random access channel protocol (eRACH). In stark contrast to existing model-based and standardized protocols, eRACH is a model-free approach that emerges through interaction with the non-stationary network environment, using multi-agent deep reinforcement learning (MADRL). Furthermore, by exploiting known SAT orbiting patterns, eRACH does not require central coordination or additional communication across users, while training convergence is stabilized through the regular orbiting patterns. Compared to RACH, we show from various simulations that our proposed eRACH yields 54.6% higher average network throughput with around two times lower average access delay while achieving 0.989 Jain’s fairness index.

In recent years, quantum computing (QC) has been getting a lot of attention from industry and academia. Especially, among various QC research topics, variational quantum circuit (VQC) enables quantum deep reinforcement learning (QRL). Many studies of QRL have shown that the QRL is superior to the classical reinforcement learning (RL) methods under the constraints of the number of training parameters. This paper extends and demonstrates the QRL to quantum multi-agent RL (QMARL). However, the extension of QRL to QMARL is not straightforward due to the challenge of the noise intermediate-scale quantum (NISQ) and the non-stationary properties in classical multi-agent RL (MARL). Therefore, this paper proposes the centralized training and decentralized execution (CTDE) QMARL framework by designing novel VQCs for the framework to cope with these issues. To corroborate the QMARL framework, this paper conducts the QMARL demonstration in a single-hop environment where edge agents offload packets to clouds. The extensive demonstration shows that the proposed QMARL framework enhances 57.7% of total reward than classical frameworks.

This paper aims to integrate two synergetic technologies, federated learning (FL) and width-adjustable slimmable neural network (SNN) architectures. FL preserves data privacy by exchanging the locally trained models of mobile devices. By adopting SNNs as local models, FL can flexibly cope with the time-varying energy capacities of mobile devices. Combining FL and SNNs is however non-trivial, particularly under wireless connections with time-varying channel conditions. Furthermore, existing multi-width SNN training algorithms are sensitive to the data distributions across devices, so are ill-suited to FL. Motivated by this, we propose a communication and energy efficient SNN-based FL (named SlimFL) that jointly utilizes superposition coding (SC) for global model aggregation and superposition training (ST) for updating local models. By applying SC, SlimFL exchanges the superposition of multiple width configurations that are decoded as many as possible for a given communication throughput. Leveraging ST, SlimFL aligns the forward propagation of different width configurations, while avoiding the inter-width interference during back propagation. We formally prove the convergence of SlimFL. The result reveals that SlimFL is not only communication-efficient but also can counteract non-IID data distributions and poor channel conditions, which is also corroborated by simulations.

Semantic communication (SC) goes beyond technical communication in which a given sequence of bits or symbols, often referred to as information, is be transmitted reliably over a noisy channel, regardless of its meaning. In SC, conveying the meaning of information becomes important, which requires some sort of agreement between a sender and a receiver through their knowledge bases. In this sense, SC is closely related to a signaling game where a sender takes an action to send a signal that conveys information to a receiver, while the receiver can interpret the signal and choose a response accordingly. Based on the signaling game, we can build a SC model and characterize the performance in terms of mutual information in this paper. In addition, we show that the conditional mutual information between the instances of the knowledge bases of communicating parties plays a crucial role in improving the performance of SC.

A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. However, such wide coverage rather makes it difficult to apply existing multiple access protocols, such as random access channel (RACH). To overcome this issue, in this paper, we propose a novel random access solution for LEO SAT networks, called as S-RACH. In contrast to existing standardized protocols, S-RACH is a model-free approach using deep reinforcement learning (DRL). Compared to RACH, we show from various simulations that our proposed S-RACH yields around 2x lower average access delay.

Precise positioning has become one core topic in wireless communications by facilitating candidate techniques of beyond 5G and 6G. Nevertheless, most existing positioning algorithms, categorized into geometry-driven and data-driven approaches, fail to simultaneously fulfill diversified requirements for practical use, e.g., accuracy, real-time operation, scalability, maintenance, etc. This article aims at introducing a new principle, called combinatorial data augmentation (CDA), a catalyst for tightly integrating geometry and data-driven approaches. We first explain the concept of CDA and its critical advantages over the two standalone approaches, followed by validating its effectiveness by field experiments with WiFi round-trip time and inertial measurement units.

Split learning (SL) is a promising distributed learning framework that enables to utilize the huge data and parallel computing resources of mobile devices. SL is built upon a model-split architecture, wherein a server stores an upper model segment that is shared by different mobile clients storing its lower model segments. Without exchanging raw data, SL achieves high accuracy and fast convergence by only uploading smashed data from clients and downloading global gradients from the server. Nonetheless, the original implementation of SL sequentially serves multiple clients, incurring high latency with many clients. A parallel implementation of SL has great potential in reducing latency, yet existing parallel SL algorithms resort to compromising scalability and/or convergence speed. Motivated by this, the goal of this article is to develop a scalable parallel SL algorithm with fast convergence and low latency. As a first step, we identify that the fundamental bottleneck of existing parallel SL comes from the model-split and parallel computing architectures, under which the server-client model updates are often imbalanced, and the client models are prone to detach from the server’s model. To fix this problem, by carefully integrating local parallelism, federated learning, and mixup augmentation techniques, we propose a novel parallel SL framework, coined LocFedMix-SL. Simulation results corroborate that LocFedMix-SL achieves improved scalability, convergence speed, and latency, compared to sequential SL as well as the state-of-the-art parallel SL algorithms such as SplitFed and LocSplitFed.

Real-time remote control over wireless is an important yet challenging application in fifth-generation and beyond due to its mission-critical nature under limited communication resources. Current solutions hinge on not only utilizing ultrareliable and low-latency communication (URLLC) links but also predicting future states, which may consume enormous communication resources and struggle with a short prediction time horizon. To fill this void, in this article we propose a novel two-way Koopman autoencoder (AE) approach wherein: 1) a sensing Koopman AE learns to understand the temporal state dynamics and predicts missing packets from a sensor to its remote controller and 2) a controlling Koopman AE learns to understand the temporal action dynamics and predicts missing packets from the controller to an actuator co-located with the sensor. Specifically, each Koopman AE aims to learn the Koopman operator in the hidden layers while the encoder of the AE aims to project the nonlinear dynamics onto a lifted subspace, which is reverted into the original nonlinear dynamics by the decoder of the AE. The Koopman operator describes the linearized temporal dynamics, enabling long-term future prediction and coping with missing packets and closed-form optimal control in the lifted subspace. Simulation results corroborate that the proposed approach achieves a$38\times $lower mean squared control error at 0-dBm signal-to-noise ratio (SNR) than the nonpredictive baseline.

In this paper, we propose a communication-efficiently decentralized machine learning framework that solves a consensus optimization problem defined over a network of inter-connected workers. The proposed algorithm, Censored and Quantized Generalized GADMM (CQ-GGADMM), leverages the worker grouping and decentralized learning ideas of Group Alternating Direction Method of Multipliers (GADMM), and pushes the frontier in communication efficiency by extending its applicability to generalized network topologies, while incorporating link censoring for negligible updates after quantization. We theoretically prove that CQ-GGADMM achieves the linear convergence rate when the local objective functions are strongly convex under some mild assumptions. Numerical simulations corroborate that CQ-GGADMM exhibits higher communication efficiency in terms of the number of communication rounds and transmit energy consumption without compromising the accuracy and convergence speed, compared to the censored decentralized ADMM, and the worker grouping method of GADMM.

Wireless channels can be inherently privacy preserving by distorting the received signals due to channel noise, and superpositioning multiple signals over-the-air. By harnessing these natural distortions and superpositions by wireless channels, we propose a novel privacy-preserving machine learning (ML) framework at the network edge, coined over-the-air mixup ML (AirMixML). In AirMixML, multiple workers transmit analog-modulated signals of their private data samples to an edge server who trains an ML model using the received noisy-and-superpositioned samples. AirMixML coincides with model training using mixup data augmentation achieving comparable accuracy to that with raw data samples. From a privacy perspective, AirMixML is a differentially private (DP) mechanism limiting the disclosure of each worker's private sample information at the server, while the worker's transmit power determines the privacy disclosure level. To this end, we develop a fractional channel-inversion power control (PC) method, a-Dirichlet mixup PC (DirMix(a)-PC), wherein for a given global power scaling factor after channel inversion, each worker's local power contribution to the superpositioned signal is controlled by the Dirichlet dispersion ratio a. Mathematically, we derive a closed-form expression clarifying the relationship between the local and global PC factors to guarantee a target DP level. By simulations, we provide DirMix(α)-PC design guidelines to improve accuracy, privacy, and energy-efficiency. Finally, AirMixML with DirMix(a)-PC is shown to achieve reasonable accuracy compared to a privacy-violating baseline with neither superposition nor PC.

Knowledge distillation (KD) has enabled remarkable progress in model compression and knowledge transfer. However, KD requires a large volume of original data or their representation statistics that are not usually available in practice. Data-free KD has recently been proposed to resolve this problem, wherein teacher and student models are fed by a synthetic sample generator trained from the teacher. Nonetheless, existing data-free KD methods rely on fine-tuning of weights to balance multiple losses, and ignore the diversity of generated samples, resulting in limited accuracy and robustness. To overcome this challenge, we propose robustness and diversity seeking data-free KD (RDSKD) in this paper. The generator loss function is crafted to produce samples with high authenticity, class diversity, and inter-sample diversity. Without real data, the objectives of seeking high sample authenticity and class diversity often conflict with each other, causing frequent loss fluctuations. We mitigate this by exponentially penalizing loss increments. With MNIST, CIFAR-10, and SVHN datasets, our experiments show that RDSKD achieves higher accuracy with more robustness over different hyperparameter settings, compared to other data-free KD methods such as DAFL, MSKD, ZSKD, and DeepInversion.

Remote state monitoring over wireless is envisaged to play a pivotal role in enabling beyond 5G applications ranging from remote drone control to remote surgery. One key challenge is to identify the system dynamics that is non-linear with a large dimensional state. To obviate this issue, in this article we propose to train an autoencoder whose encoder and decoder are split and stored at a state sensor and its remote observer, respectively. This autoencoder not only decreases the remote monitoring payload size by reducing the state representation dimension but also learns the system dynamics by lifting it via a Koopman operator, thereby allowing the observer to locally predict future states after training convergence. Numerical results under a non-linear cart-pole environment demonstrate that the proposed split learning of a Koopman autoencoder can locally predict future states, and the prediction accuracy increases with the representation dimension and transmission power.

Designing distributed, fast, and reliable wireless consensus protocols is instrumental in enabling mission-critical decentralized systems, such as robotic networks in the Industrial Internet of Things (IIoT), drone swarms in rescue missions, and so forth. However, chasing both low-latency and reliability of consensus protocols is a challenging task. The problem is aggravated under wireless connectivity that may be slower and less reliable, compared to wired connections. To tackle this issue, we investigate fundamental relationships between consensus latency and reliability through the lens of wireless connectivity, and co-design communication and consensus protocols for low-latency and reliable decentralized systems. Specifically, we propose a novel communication-efficient distributed consensus protocol, termed random representative consensus (R2C), and show its effectiveness under gossip and broadcast communication protocols. To this end, we derive a closed-form end-to-end (E2E) latency expression of the R2C that guarantees target reliability, and compare it with a baseline consensus protocol, referred to as referendum consensus (RC). The result shows that the R2C is faster compared to the RC and more reliable compared when co-designed with the broadcast protocol compared to that with the gossip protocol.

Machine learning (ML) is a promising enabler for the fifth-generation (5G) communication systems and beyond. By imbuing intelligence into the network edge, edge nodes can proactively carry out decision-making and, thereby, react to local environmental changes and disturbances while experiencing zero communication latency. To achieve this goal, it is essential to cater for high ML inference accuracy at scale under the time-varying channel and network dynamics, by continuously exchanging fresh data and ML model updates in a distributed way. Taming this new kind of data traffic boils down to improving the communication efficiency of distributed learning by optimizing communication payload types, transmission techniques, and scheduling, as well as ML architectures, algorithms, and data processing methods. To this end, this article aims to provide a holistic overview of relevant communication and ML principles and, thereby, present communication-efficient and distributed learning frameworks with selected use cases.

In this article, we propose a communication-efficient decentralized machine learning (ML) algorithm, coined quantized group ADMM (Q-GADMM). To reduce the number of communication links, every worker in Q-GADMM communicates only with two neighbors, while updating its model via the group alternating direction method of multipliers (GADMM). Moreover, each worker transmits the quantized difference between its current model and its previously quantized model, thereby decreasing the communication payload size. However, due to the lack of centralized entity in decentralized ML, the spatial sparsity and payload compression may incur error propagation, hindering model training convergence. To overcome this, we develop a novel stochastic quantization method to adaptively adjust model quantization levels and their probabilities, while proving the convergence of Q-GADMM for convex objective functions. Furthermore, to demonstrate the feasibility of Q-GADMM for non-convex and stochastic problems, we propose quantized stochastic GADMM (Q-SGADMM) that incorporates deep neural network architectures and stochastic sampling. Simulation results corroborate that Q-GADMM significantly outperforms GADMM in terms of communication efficiency while achieving the same accuracy and convergence speed for a linear regression task. Similarly, for an image classification task using DNN, Q-SGADMM achieves significantly less total communication cost with identical accuracy and convergence speed compared to its counterpart without quantization, i.e., stochastic GADMM (SGADMM).

Wireless connectivity is instrumental in enabling scalable federated learning (FL), yet wireless channels bring challenges for model training, in which channel randomness perturbs each worker’s model update while multiple workers’ updates incur significant interference under limited bandwidth. To address these challenges, in this work we formulate a novel constrained optimization problem, and propose an FL framework harnessing wireless channel perturbations and interference for improving privacy, bandwidth-efficiency, and scalability. The resultant algorithm is coinedanalog federated ADMM (A-FADMM)based on analog transmissions and the alternating direction method of multipliers (ADMM). In A-FADMM, all workers upload their model updates to the parameter server (PS) using a single channel via analog transmissions, during which all models are perturbed and aggregated over-the-air. This not only saves communication bandwidth, but also hides each worker’s exact model update trajectory from any eavesdropper including the honest-but-curious PS, thereby preserving data privacy against model inversion attacks. We formally prove the convergence and privacy guarantees of A-FADMM for convex functions under time-varying channels, and numerically show the effectiveness of A-FADMM under noisy channels and stochastic non-convex functions, in terms of convergence speed and scalability, as well as communication bandwidth and energy efficiency.

This article studies the joint problem of uplink-downlink scheduling and power allocation for controlling a large number of control systems that upload their states to remote controllers and download control actions over wireless links. To overcome the lack of wireless resources, we propose a machine learning-based solution, where only one control system is controlled, while the rest of the control systems are actuated by locally predicting the missing state and/or action information using the previous uplink and/or downlink receptions via a Gaussian process regression (GPR). This GPR prediction credibility is determined using the age-of-information (AoI) of the latest reception. Moreover, the successful reception is affected by the transmission power, mandating a co-design of the communication and control operations. To this end, we formulate a network-wide minimization problem of the average AoI and transmission power under communication reliability and control stability constraints. To solve the problem, we propose a dynamic control algorithm using the Lyapunov drift-plus-penalty optimization framework. Numerical results corroborate that the proposed algorithm can stably control$2\times$more number of actuators compared to an event-triggered scheduling baseline with Kalman filtering and frequency division multiple access, which is$18\times$larger than a round-robin scheduling baseline.

A mega-constellation of low-earth orbit (LEO) satellites has the potential to enable long-range communication with low latency. Integrating this with burgeoning unmanned aerial vehicle (UAV) assisted non-terrestrial networks will be a disruptive solution for beyond 5G systems provisioning large-scale three-dimensional connectivity. In this article, we study the problem of forwarding packets between two faraway ground terminals, through an LEO satellite selected from an orbiting constellation and a mobile high-altitude platform (HAP) such as a fixed-wing UAV. To maximize the end-to-end data rate, the satellite association and HAP location should be optimized, which is challenging due to a huge number of orbiting satellites and the resulting time-varying network topology. We tackle this problem using deep reinforcement learning (DRL) with a novel action dimension reduction technique. Simulation results corroborate that our proposed method achieves up to 5.74x higher average data rate compared to a direct communication baseline without SAT and HAP.

In this paper, we propose a communication-efficient decen-tralized machine learning (ML) algorithm, coined quantized group ADMM (Q-GADMM). Every worker in Q-GADMM communicates only with two neighbors, and updates its model via the group alternating direct method of multiplier (GADMM), thereby ensuring fast convergence while reducing the number of communication rounds. Furthermore, each worker quantizes its model updates before transmissions, thereby decreasing the communication payload sizes. We prove that Q-GADMM converges to the optimal solution for convex loss functions, and numerically show that Q-GADMM yields 7x less communication cost while achieving almost the same accuracy and convergence speed compared to GADMM without quantization.

This article proposes a communication-efficient decentralized deep learning algorithm, coined layer-wise federated group ADMM (L-FGADMM). To minimize an empirical risk, every worker in L-FGADMM periodically communicates with two neighbors, in which the periods are separately adjusted for different layers of its deep neural network. A constrained optimization problem for this setting is formulated and solved using the stochastic version of GADMM proposed in our prior work. Numerical evaluations show that by less frequently exchanging the largest layer, L-FGADMM can significantly reduce the communication cost, without compromising the convergence speed. Surprisingly, despite less exchanged information and decentralized operations, intermittently skipping the largest layer consensus in L-FGADMM creates a regularizing effect, thereby achieving the test accuracy as high as federated learning (FL), a baseline method with the entire layer consensus by the aid of a central entity.

When the data is distributed across multiple servers, lowering the communication cost between the servers (or workers) while solving the distributed learning problem is an important problem and is the focus of this paper. In particular, we propose a fast, and communication-efficient decentralized framework to solve the distributed machine learning (DML) problem. The proposed algorithm, Group Alternating Direction Method of Multipliers (GADMM) is based on the Alternating Direction Method of Multipliers (ADMM) framework. The key novelty in GADMM is that it solves the problem in a decentralized topology where at most half of the workers are competing for the limited communication resources at any given time. Moreover, each worker exchanges the locally trained model only with two neighboring workers, thereby training a global model with a lower amount of communication overhead in each exchange. We prove that GADMM converges to the optimal solution for convex loss functions, and numerically show that it converges faster and more communication-efficient than the state-of-the-art communication-efficient algorithms such as the Lazily Aggregated Gradient (LAG) and dual averaging, in linear and logistic regression tasks on synthetic and real datasets. Furthermore, we propose Dynamic GADMM (D-GADMM), a variant of GADMM, and prove its convergence under the time-varying network topology of the workers.

This paper investigates the control of a massive population of UAVs such as drones. The straightforward method of control of UAVs by considering the interactions among them to make a flock requires a huge inter-UAV communication which is impossible to implement in real-time applications. One method of control is to apply the mean field game (MFG) framework which substantially reduces communications among the UAVs. However, to realize this framework, powerful processors are required to obtain the control laws at different UAVs. This requirement limits the usage of the MFG framework for real-time applications such as massive UAV control. Thus, a function approximator based on neural networks (NN) is utilized to approximate the solutions of Hamilton-Jacobi-Bellman (HJB) and Fokker-Planck-Kolmogorov (FPK) equations. Nevertheless, using an approximate solution can violate the conditions for convergence of the MFG framework. Therefore, the federated learning (FL) approach which can share the model parameters of NNs at drones, is proposed with NN based MFG to satisfy the required conditions. The stability analysis of the NN based MFG approach is presented and the performance of the proposed FL-MFG is elaborated by the simulations.

This paper investigates the autonomous control of massive unmanned aerial vehicles (UAVs) for mission-critical applications (e.g., dispatching many UAVs from a source to a destination for firefighting). Achieving their fast travel and low motion energy without inter-UAV collision under wind perturbation is a daunting control task, which incurs huge communication energy for exchanging UAV states in real time. We tackle this problem by exploiting a mean-field game (MFG) theoretic control method that requires the UAV state exchanges only once at the initial source. Afterwards, each UAV can control its acceleration by locally solving two partial differential equations (PDEs), known as the Hamilton-Jacobi- Bellman (HJB) and Fokker-Planck-Kolmogorov (FPK) equations. This approach, however, brings about huge computation energy for solving the PDEs, particularly under multi-dimensional UAV states. We address this issue by utilizing a machine learning (ML) method where two separate ML models approximate the solutions of the HJB and FPK equations. These ML models are trained and exploited using an online gradient descent method with low computational complexity. Numerical evaluations validate that the proposed ML aided MFG theoretic algorithm, referred to as \emph{MFG learning control}, is effective in collision avoidance with low communication energy and acceptable computation energy.

Edge computing is an emerging concept based on distributed computing, storage, and control services closer to end network nodes. Edge computing lies at the heart of the fifth-generation (5G) wireless systems and beyond. While the current state-of-the-art networks communicate, compute, and process data in a centralized manner (at the cloud), for latency and compute-centric applications, both radio access and computational resources must be brought closer to the edge, harnessing the availability of computing and storage-enabled small cell base stations in proximity to the end devices. Furthermore, the network infrastructure must enable a distributed edge decision-making service that learns to adapt to the network dynamics with minimal latency and optimize network deployment and operation accordingly. This paper will provide a fresh look to the concept of edge computing by first discussing the applications that the network edge must provide, with a special emphasis on the ensuing challenges in enabling ultrareliable and low-latency edge computing services for mission-critical applications such as virtual reality (VR), vehicle-to-everything (V2X), edge artificial intelligence (AI), and so on. Furthermore, several case studies where the edge is key are explored followed by insights and prospect for future work.

Fueled by the availability of more data and computing power, recent breakthroughs in cloud-based machine learning (ML) have transformed every aspect of our lives from face recognition and medical diagnosis to natural language processing. However, classical ML exerts severe demands in terms of energy, memory, and computing resources, limiting their adoption for resource-constrained edge devices. The new breed of intelligent devices and high-stake applications (drones, augmented/virtual reality, autonomous systems, and so on) requires a novel paradigm change calling for distributed, low-latency and reliable ML at the wireless network edge (referred to as edge ML). In edge ML, training data are unevenly distributed over a large number of edge nodes, which have access to a tiny fraction of the data. Moreover, training and inference are carried out collectively over wireless links, where edge devices communicate and exchange their learned models (not their private data). In a first of its kind, this article explores the key building blocks of edge ML, different neural network architectural splits and their inherent tradeoffs, as well as theoretical and technical enablers stemming from a wide range of mathematical disciplines. Finally, several case studies pertaining to various high-stake applications are presented to demonstrate the effectiveness of edge ML in unlocking the full potential of 5G and beyond.

The month’s regular papers issue covers machine learning at the wireless network edge, soft-informationbased localization techniques, and Antenna-in-Package technology.

Millimeter-wave (mmWave) bands will play an important role in 5G wireless systems. The system performance can be assessed by using models from stochastic geometry that cater for the directivity in the desired signal transmissions as well as the interference, and by calculating the signal-to-interference-plus-noise ratio (SINR) coverage. Nonetheless, the accuracy of the existing coverage expressions derived through stochastic geometry may be questioned, as it is not clear whether they would capture the impact of the detailed mmWave channel and antenna features. In this paper, we propose an SINR coverage analysis framework that includes realistic channel model and antenna element radiation patterns. We introduce and estimate two parameters, aligned gain and misaligned gain, associated with the desired signal beam and the interfering signal beam, respectively. The distributions of these gains are used to determine the distribution of the SINR which is compared with the corresponding SINR coverage, calculated through the system-level simulations. The results show that both aligned and misaligned gains can be modeled as exponential-logarithmically distributed random variables with the highest accuracy, and can further be approximated as exponentially distributed random variables with reasonable accuracy. These approximations can be used as a tool to evaluate the system-level performance of various 5G connectivity scenarios in the mmWave band.

Virtual reality (VR) enables mobile wireless users to experience multimodal perceptions in a virtual space. In this paper we investigate the problem of concurrent support of visual and haptic perceptions over wireless cellular networks, with a focus on the downlink transmission phase. While the visual perception requires moderate reliability and maximized rate, the haptic perception requires fixed rate and high reliability. Hence, the visuo-haptic VR traffic necessitates the use of two different network slices: enhanced mobile broadband (eMBB) for visual perception and ultra-reliable and low latency communication (URLLC) for haptic perception. We investigate two methods by which these two slices share the downlink resources orthogonally and non-orthogonally, respectively. We compare these methods in terms of the just-noticeable difference (JND), an established measure in psychophysics, and show that non- orthogonal slicing becomes preferable under a higher target integrated-perceptual resolution and/or a higher target rate for haptic perceptions.

Millimeter-wave (mmWave) bands have been attracting growing attention as a possible candidate for next- generation cellular networks, since the available spectrum is orders of magnitude larger than in current cellular allocations. To precisely design mmWave systems, it is important to examine mmWave interference and SIR coverage under large-scale deployments. For this purpose, we apply an accurate mmWave channel model, derived from experiments, into an analytical framework based on stochastic geometry. In this way we obtain an analytical expression for the SIR coverage probability in mmWave cellular networks.

This paper investigates a cellular edge caching design under an extremely large number of small base stations (SBSs) and users. In this ultra-dense edge caching network (UDCN), SBS-user distances shrink, and each user can request a cached content from multiple SBSs. Unfortunately, the complexity of existing caching controls' mechanisms increases with the number of SBSs, making them inapphcable for solving the fundamental caching problem: How to maximize local caching gain while minimizing the replicated content caching? Furthermore, spatial dynamics of interference is no longer negligible in UDCNs due to the surge in interference. In addition, the caching control should consider temporal dynamics of user demands. To overcome such difficulties, we propose a novel caching algorithm weaving together notions of mean-field game theory and stochastic geometry. These enable our caching algorithm to become independent of the number of SBSs and users, while incorporating spatial interference dynamics as well as temporal dynamics of content popularity and storage constraints. Numerical evaluation validates the fact that the proposed algorithm reduces not only the long run average cost by at least 24% but also the number of replicated content by 56% compared to a popularity-based algorithm.

Massive multiple-input multiple-output (massive MIMO) and small cell densification are complementary key 5G enablers. Given a fixed number of the entire basestation antennas per unit area, this paper fairly compares (i) to deploy few base stations (BSs) and concentrate many antennas on each of them, i.e. massive MIMO, and (ii) to deploy more BSs equipped with few antennas, i.e. small cell densification. We observe that small cell densification always outperforms for both signal-to-interference ratio (SIR) coverage and energy efficiency (EE), when each BS serves multiple users via L number of sub-bands (multicarrier transmission). Moreover, we also observe that larger L increases SIR coverage while decreasing EE, thus urging the necessity of optimal 5G network design. These two observations are based on our novel closed-form SIR coverage probability derivation using stochastic geometry, also validated via numerical simulations.

One of the goals of 5G wireless systems stated by the NGMN alliance is to provide moderate rates (50+ Mbps) everywhere and with very high reliability. We term this service Ultra-Reliable Ubiquitous-Rate Communication (UR2C). This paper investigates the role of frequency reuse in supporting UR2C in the downlink. To this end, two frequency reuse schemes are considered: user-specific frequency reuse (FRu) and BS-specific frequency reuse (FRb). For a given unit frequency channel, FRureduces the number of serving user equipments (UEs), whereas FRb directly decreases the number of interfering base stations (BSs). This increases the distance from the interfering BSs and the signal-to-interference ratio (SIR) attains ultra-reliability, e.g. 99% SIR coverage at a randomly picked UE. The ultra-reliability is, however, achieved at the cost of the reduced frequency allocation, which may degrade overall downlink rate. To fairly capture this reliability-rate tradeoff, we propose ubiquitous rate defined as the maximum downlink rate whose required SIR can be achieved with ultra-reliability. By using stochastic geometry, we derive closed-form ubiquitous rate as well as the optimal frequency reuse rules for UR2C.

This article investigates the mobility management of an ultra dense cellular network (UDN) from an energy-efficiency (EE) point of view. Many dormant base stations (BSs) in a UDN do not transmit signals, and thus a received power based handover (HO) approach as in traditional cellular networks is hardly applicable. In addition, the limited front/backhaul capacity compared to a huge number of BSs makes it difficult to implement a centralized HO and power control. For these reasons, a novel user-centric association rule is proposed, which jointly optimizes HO and power control for maximizing EE. The proposed mobility management is able to cope not only with the spatial randomness of user movement but also with temporally correlated wireless channels. The proposed approach is implemented over a HO time window and tractable power con- trol policy by exploiting mean-field game (MFG) and stochastic geometry (SG). Compared to a baseline with a fixed HO interval and transmit power, the proposed approach achieves the 1.2 times higher long-term average EE at a typical active BS.

This article investigates the performance of an ultra-dense network (UDN) from an energy-efficiency (EE) standpoint leveraging the interplay between stochastic geometry (SG) and mean-field game (MFG) theory. In this setting, base stations (BSs) (resp. users) are uniformly distributed over a two-dimensional plane as two independent homogeneous Poisson point processes (PPPs), where users associate to their nearest BSs. The goal of every BS is to maximize its own energy efficiency subject to channel uncertainty, random BS location, and interference levels. Due to the coupling in interference, the problem is solved in the mean-field (MF) regime where each BS interacts with the whole BS population via time- varying MF interference. As a main contribution, the asymptotic convergence of MF interference to zero is rigorously proved in a UDN with multiple transmit antennas. It allows us to derive a closed-form EE representation, yielding a tractable EE optimal power control policy. This proposed power control achieves more than 1.5 times higher EE compared to a fixed power baseline.

A strong motivation of charging depleted battery can be an enabler for network capacity increase. In this light we propose a spatial attraction cellular network (SAN) consisting of macro cells overlaid with small cell base stations that wirelessly charge user batteries. Such a network makes battery depleting users move toward the vicinity of small cell base stations. With a fine adjustment of charging power, this user spatial attraction (SA) improves in spectral efficiency as well as load balancing. We jointly optimize both enhancements thanks to SA, and derive the corresponding optimal charging power in a closed form by using a stochastic geometric approach.

The forthcoming 5G cellular network is expected to overlay millimeter-wave (mmW) transmissions with the incumbent micro-wave (μW) architecture. The overall mm-μW resource management should, therefore, harmonize with each other. This paper aims at maximizing the overall downlink (DL) rate with a minimum uplink (UL) rate constraint, and concludes: mmW tends to focus more on DL transmissions while μW has high priority for complementing UL, under time-division duplex (TDD) mmW operations. Such UL dedication of μW results from the limited use of mmW UL bandwidth due to excessive power consumption and/or high peak-to-average power ratio (PAPR) at mobile users. To further relieve this UL bottleneck, we propose mmW UL decoupling that allows each legacy μW base station (BS) to receive mmW signals. Its impact on mm-μW resource management is provided in a tractable way by virtue of a novel closed-form mm-μW spectral efficiency (SE) derivation. In an ultra-dense cellular network (UDN), our derivation verifies mmW (or μW) SE is a logarithmic function of BS-to-user density ratio. This strikingly simple yet practically valid analysis is enabled by exploiting stochastic geometry in conjunction with real three-dimensional (3-D) building blockage statistics in Seoul, South Korea.

This paper investigates the relationship between base station (BS) density and average spectral efficiency (SE) in the downlink of a cellular network. This relationship has been well known for sparse deployment, i.e. when the number of BSs is small compared to the number of users. In this case the SE is independent of BS density. As BS density grows, on the other hand, it has previously been shown that increasing the BS density increases the SE, but no tractable form for the SE-BS density relationship has yet been derived. In this paper we derive such a closed-form result that reveals the SE is asymptotically a logarithmic function of BS density as the density grows. Further, we study the impact of this result on the network operator's profit when user demand varies, and derive the profit maximizing BS density and the optimal amount of spectrum to be utilized in closed forms. In addition, we provide deployment planning guidelines that will aid the operator in his decision if he should invest in densifying his network or in acquiring more spectrum.

The Long Term Evolution (LTE) broadcast is a promising solution to cope with exponentially increasing user traffic by broadcasting common user requests over the same frequency channels. In this paper, we propose a novel network framework provisioning broadcast and unicast services simultaneously. For each serving file to users, a cellular base station determines either to broadcast or unicast the file based on user demand prediction examining the file's content specific characteristics such as: file size, delay tolerance, price sensitivity. In a network operator's revenue maximization perspective while not inflicting any user payoff degradation, we jointly optimize resource allocation, pricing, and file scheduling. In accordance with the state of the art LTE specifications, the proposed network demonstrates up to 32% increase in revenue for a single cell and more than a 7-fold increase for a 7 cell coordinated LTE broadcast network, compared to the conventional unicast cellular networks.