Search

This paper proposes a novel digital deep joint source-channel coding (DeepJSCC) framework that achieves robust performance across diverse communication environments without requiring extensive retraining and prior knowledge of communication environments. Traditional digital DeepJSCC techniques often face challenges in adapting to various communication environments, as they require significant training overhead and large amounts of communication data to develop either multiple specialized models or a single generalized model, in pre-defined communication environments. To address this challenge, in our framework, an error-adaptive blind training strategy is devised, which eliminates the need for prior knowledge of communication environments. This is achieved by modeling the relationship between the encoder's output and the decoder's input using binary symmetric channels, and optimizing bit-flip probabilities by treating them as trainable parameters. In our framework, a training-aware communication strategy is also presented, which dynamically selects the optimal encoder-decoder pair and transmission parameters based on current channel conditions. In particular, in this strategy, an adaptive power and modulation control method is developed to minimize the total transmission power, while maintaining high task performance. Simulation results demonstrate that our framework outperforms existing DeepJSCC methods, achieving higher peak signal-to-noise ratio, lower power consumption, and requiring significantly fewer encoder-decoder pairs for adaptation.

This paper studies a hybrid language model (HLM) architecture that integrates a small language model (SLM) operating on a mobile device with a large language model (LLM) hosted at the base station (BS) of a wireless network. The HLM token generation process follows the speculative inference principle: the SLM's vocabulary distribution is uploaded to the LLM, which either accepts or rejects it, with rejected tokens being resampled by the LLM. While this approach ensures alignment between the vocabulary distributions of the SLM and LLM, it suffers from low token throughput due to uplink transmission and the computation costs of running both language models. To address this, we propose a novel HLM structure coined Uncertainty-aware opportunistic HLM (U-HLM), wherein the SLM locally measures its output uncertainty and skips both uplink transmissions and LLM operations for tokens that are likely to be accepted. This opportunistic skipping is enabled by our empirical finding of a linear correlation between the SLM's uncertainty and the LLM's rejection probability. We analytically derive the uncertainty threshold and evaluate its expected risk of rejection. Simulations show that U-HLM reduces uplink transmissions and LLM computations by 45.93%, while achieving up to 97.54% of the LLM's inference accuracy and 2.54$\times$ faster token throughput than HLM without skipping., Comment: 6 pages, 6 figures; This work has been submitted to the IEEE for possible publication

Six-dimensional movable antenna (6DMA) is an innovative technology to improve wireless network capacity by adjusting 3D positions and 3D rotations of antenna surfaces based on channel spatial distribution. However, the existing works on 6DMA have assumed a central processing unit (CPU) to jointly process the signals of all 6DMA surfaces to execute various tasks. This inevitably incurs prohibitively high processing cost for channel estimation. Therefore, we propose a distributed 6DMA processing architecture to reduce processing complexity of CPU by equipping each 6DMA surface with a local processing unit (LPU). In particular, we unveil for the first time a new \textbf{\textit{directional sparsity}} property of 6DMA channels, where each user has significant channel gains only for a (small) subset of 6DMA position-rotation pairs, which can receive direct/reflected signals from users. In addition, we propose a practical three-stage protocol for the 6DMA-equipped base station (BS) to conduct statistical CSI acquisition for all 6DMA candidate positions/rotations, 6DMA position/rotation optimization, and instantaneous channel estimation for user data transmission with optimized 6DMA positions/rotations. Specifically, the directional sparsity is leveraged to develop distributed algorithms for joint sparsity detection and channel power estimation, as well as for directional sparsity-aided instantaneous channel estimation. Using the estimated channel power, we develop a channel power-based optimization algorithm to maximize the ergodic sum rate of the users by optimizing the antenna positions/rotations. Simulation results show that our channel estimation algorithms are more accurate than benchmarks with lower pilot overhead, and our optimization outperforms fluid/movable antennas optimized only in two dimensions (2D), even when the latter have perfect instantaneous CSI., Comment: 16 pages, double-column

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., Comment: 5 pages, IEEE vehicular technology conference, Spring 2023

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.

The forthcoming 6G systems are expected to address a wide range of non-stationary tasks. This poses challenges to traditional medium access control (MAC) protocols that are static and predefined. In response, data-driven MAC protocols have recently emerged, offering ability to tailor their signaling messages for specific tasks. This article presents a novel categorization of these data-driven MAC protocols into three levels: Level 1 MAC. task-oriented neural protocols constructed using multi-agent deep reinforcement learning (MADRL); Level 2 MAC. neural network-oriented symbolic protocols developed by converting Level 1 MAC outputs into explicit symbols; and Level 3 MAC. language-oriented semantic protocols harnessing large language models (LLMs) and generative models. With this categorization, we aim to explore the opportunities and challenges of each level by delving into their foundational techniques. Drawing from information theory and associated principles as well as selected case studies, this study provides insights into the trajectory of data-driven MAC protocols and sheds light on future research directions., Comment: 11 pages, 13 figures, submitted to IEEE BITS the Information Theory Magazine

Recent studies on semantic communication commonly rely on neural network (NN) based transceivers such as deep joint source and channel coding (DeepJSCC). Unlike traditional transceivers, these neural transceivers are trainable using actual source data and channels, enabling them to extract and communicate semantics. On the flip side, each neural transceiver is inherently biased towards specific source data and channels, making different transceivers difficult to understand intended semantics, particularly upon their initial encounter. To align semantics over multiple neural transceivers, we propose a distributed learning based solution, which leverages split learning (SL) and partial NN fine-tuning techniques. In this method, referred to as SL with layer freezing (SLF), each encoder downloads a misaligned decoder, and locally fine-tunes a fraction of these encoder-decoder NN layers. By adjusting this fraction, SLF controls computing and communication costs. Simulation results confirm the effectiveness of SLF in aligning semantics under different source data and channel dissimilarities, in terms of classification accuracy, reconstruction errors, and recovery time for comprehending intended semantics from misalignment., Comment: 5 pages, 4 figures, 1 table, submitted to the IEEE for possible publication

Autoencoder (AE) is a neural network (NN) architecture that is trained to reconstruct an input at its output. By measuring the reconstruction errors of new input samples, AE can detect anomalous samples deviated from the trained data distribution. The key to success is to achieve high-fidelity reconstruction (HFR) while restricting AE's capability of generalization beyond training data, which should be balanced commonly via iterative re-training. Alternatively, we propose a novel framework of AE-based anomaly detection, coined HFR-AE, by projecting new inputs into a subspace wherein the trained AE achieves HFR, thereby increasing the gap between normal and anomalous sample reconstruction errors. Simulation results corroborate that HFR-AE improves the area under receiver operating characteristic curve (AUROC) under different AE architectures and settings by up to 13.4% compared to Vanilla AE-based anomaly detection., Comment: 5 pages, submitted to the IEEE for possible publication

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., Comment: 7 pages, 6 figures, submitted to the IEEE for possible publication

Real-time remote control over wireless is an important-yet-challenging application in 5G and beyond due to its mission-critical nature under limited communication resources. Current solutions hinge on not only utilizing ultra-reliable 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 non-linear dynamics onto a lifted subspace, which is reverted into the original non-linear 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 38x lower mean squared control error at 0 dBm signal-to-noise ratio (SNR) than the non-predictive baseline.

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., Comment: 5 pages, 4 figures, VTC Fall 2022 (Workshop of Semantic Communication)

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.

Traditionally, studies on technical communication (TC) are based on stochastic modeling and manipulation. This is not sufficient for semantic communication (SC) where semantic elements are logically connected, rather than stochastically correlated. To fill this void, by leveraging a logical programming language called probabilistic logic (ProbLog), we propose a unified approach to semantic information and communication through the interplay between TC and SC. On top of the well-established existing TC layer, we introduce a SC layer that utilizes knowledge bases of communicating parties for the exchange of semantic information. These knowledge bases are logically described, manipulated, and exploited using ProbLog. To make these SC and TC layers interact, we propose various measures based on the entropy of a clause in a knowledge base. These measures allow us to delineate various technical issues on SC such as a message selection problem for improving the knowledge base at a receiver. Extending this, we showcase selected examples in which SC and TC layers interact with each other while taking into account constraints on physical channels and efficiently utilizing channel resources., Comment: 15 pages, 9 figures. arXiv admin note: substantial text overlap with arXiv:2201.05936

This article aims to provide a unified and technical approach to semantic information, communication, and their interplay through the lens of probabilistic logic. To this end, on top of the existing technical communication (TC) layer, we additionally introduce a semantic communication (SC) layer that exchanges logically meaningful clauses in knowledge bases. To make these SC and TC layers interact, we propose various measures based on the entropy of a clause in a knowledge base. These measures allow us to delineate various technical issues on SC such as a message selection problem for improving the knowledge at a receiver. Extending this, we showcase selected examples in which SC and TC layers interact with each other while taking into account constraints on physical channels., Comment: 6 pages, 3 figures, ICC 2022 (submitted to Workshop on Semantic Communications)

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 grant-free 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.

Spurred by a huge interest in the post-Shannon communication, it has recently been shown that leveraging semantics can significantly improve the communication effectiveness across many tasks. In this article, inspired by human communication, we propose a novel stochastic model of System 1 semantics-native communication (SNC) for generic tasks, where a speaker has an intention of referring to an entity, extracts the semantics, and communicates its symbolic representation to a target listener. To further reach its full potential, we additionally infuse contextual reasoning into SNC such that the speaker locally and iteratively self-communicates with a virtual agent built on the physical listener's unique way of coding its semantics, i.e., communication context. The resultant System 2 SNC allows the speaker to extract the most effective semantics for its listener. Leveraging the proposed stochastic model, we show that the reliability of System 2 SNC increases with the number of meaningful concepts, and derive the expected semantic representation (SR) bit length which quantifies the extracted effective semantics. It is also shown that System 2 SNC significantly reduces the SR length without compromising communication reliability., Comment: 18 pages, 16 figures, in IEEE Transactions on Cognitive Communications and Networking

Due to the emergence of various wireless sensing technologies, numerous positioning algorithms have been introduced in the literature, categorized into \emph{geometry-driven positioning} (GP) and \emph{data-driven positioning} (DP). These approaches have respective limitations, e.g., a non-line-of-sight issue for GP and the lack of a labeled dataset for DP, which can be complemented by integrating both methods. To this end, this paper aims to introduce a novel principle called \emph{combinatorial data augmentation} (CDA), a catalyst for the two approaches' seamless integration. Specifically, GP-based datasets augmented from different combinations of positioning entities, called \emph{preliminary estimate locations} (PELs), can be used as DP's inputs. We confirm the CDA's effectiveness from field experiments based on WiFi \emph{round-trip times} (RTTs) and \emph{inertial measurement units} (IMUs) by designing several CDA-based positioning algorithms. First, we show that CDA offers various metrics quantifying each PEL's reliability, thereby filtering out unreliable PELs for WiFi RTT positioning. Second, CDA helps compute the measurement covariance matrix of a Kalman filter for fusing two position estimates derived by WiFi RTT and IMUs. Third, we use the above position estimate as the corresponding PEL's real-time label for fingerprint-based positioning as a representative DP algorithm. It provides accurate and reliable positioning results, says an average positioning error of $1.51$ (m) with a standard deviation of $0.88$~(m)., Comment: submitted to a possible IEEE journal

The lottery ticket hypothesis (LTH) claims that a deep neural network (i.e., ground network) contains a number of subnetworks (i.e., winning tickets), each of which exhibiting identically accurate inference capability as that of the ground network. Federated learning (FL) has recently been applied in LotteryFL to discover such winning tickets in a distributed way, showing higher accuracy multi-task learning than Vanilla FL. Nonetheless, LotteryFL relies on unicast transmission on the downlink, and ignores mitigating stragglers, questioning scalability. Motivated by this, in this article we propose a personalized and communication-efficient federated lottery ticket learning algorithm, coined CELL, which exploits downlink broadcast for communication efficiency. Furthermore, it utilizes a novel user grouping method, thereby alternating between FL and lottery learning to mitigate stragglers. Numerical simulations validate that CELL achieves up to 3.6% higher personalized task classification accuracy with 4.3x smaller total communication cost until convergence under the CIFAR-10 dataset., Comment: 5 pages, 2 figures, 2 tables

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.

This article studies the joint problem of uplink-downlink scheduling and power allocation for controlling a large number of actuators 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 a fraction of actuators is controlled, while the rest of the actuators 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 $2$x more number of actuators compared to an event-triggered scheduling baseline with Kalman filtering and frequency division multiple access, which is $18$x larger than a round-robin scheduling baseline.

In this book chapter, we study a problem of distributed content caching in an ultra-dense edge caching network (UDCN), in which a large number of small base stations (SBSs) prefetch popular files to cope with the ever-growing user demand in 5G and beyond. In a UDCN, even a small misprediction of user demand may render a large amount of prefetched data obsolete. Furtherproacmore, the interference variance is high due to the short inter-SBS distances, making it difficult to quantify data downloading rates. Lastly, since the caching decision of each SBS interacts with those of all other SBSs, the problem complexity of exponentially increases with the number of SBSs, which is unfit for UDCNs. To resolve such challenging issues while reflecting time-varying and location-dependent user demand, we leverage mean-field game (MFG) theory through which each SBS interacts only with a single virtual SBS whose state is drawn from the state distribution of the entire SBS population, i.e., mean-field (MF) distribution. This MF approximation asymptotically guarantees achieving the epsilon Nash equilibrium as the number of SBSs approaches infinity. To describe such an MFG-theoretic caching framework, this chapter aims to provide a brief review of MFG, and demonstrate its effectiveness for UDCNs., Comment: 26 pages, 9 figures; This chapter is written for the forthcoming book, Edge Caching for Mobile Networks (IET), edited by W. Chen and H. V. Poor. arXiv admin note: substantial text overlap with arXiv:1801.07367

Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under limited communication resources, however, such a method becomes extremely costly particularly for modern deep neural networks having a huge number of model parameters. In this regard, federated distillation (FD) is a compelling distributed learning solution that only exchanges the model outputs whose dimensions are commonly much smaller than the model sizes (e.g., 10 labels in the MNIST dataset). The goal of this chapter is to provide a deep understanding of FD while demonstrating its communication efficiency and applicability to a variety of tasks. To this end, towards demystifying the operational principle of FD, the first part of this chapter provides a novel asymptotic analysis for two foundational algorithms of FD, namely knowledge distillation (KD) and co-distillation (CD), by exploiting the theory of neural tangent kernel (NTK). Next, the second part elaborates on a baseline implementation of FD for a classification task, and illustrates its performance in terms of accuracy and communication efficiency compared to FL. Lastly, to demonstrate the applicability of FD to various distributed learning tasks and environments, the third part presents two selected applications, namely FD over asymmetric uplink-and-downlink wireless channels and FD for reinforcement learning., Comment: 30 pages, 12 figures, 2 tables; This chapter is written for the forthcoming book, Machine Learning and Wireless Communications (Cambridge University Press), edited by H. V. Poor, D. Gunduz, A. Goldsmith, and Y. Eldar

Improving the data rate of machine-type communication (MTC) is essential in supporting emerging Internet of things (IoT) applications ranging from real-time surveillance to edge machine learning. To this end, in this paper we propose a resource allocation approach for uplink transmissions within a random access procedure in MTC by exploiting multichannel selection diversity, coined explore-before-talk (EBT). Each user in EBT first sends pilot signals through multiple channels that are initially allocated by a base station (BS) for exploration, and then the BS informs a subset of initially allocated channels that are associated with high signal-to-noise ratios (SNRs) for data packet transmission by the user while releasing the rest of the channels for other users. Consequently, EBT exploits a multichannel selection diversity gain during data packet transmission, at the cost of exploration during pilot transmission. We optimize this exploration-exploitation trade-off, by deriving closed-form mean data rate and resource outage probability expressions. Numerical results corroborate that EBT achieves a higher mean data rate while satisfying the same outage constraint, compared to a conventional MTC protocol without exploration., Comment: 10 pages, 11 figures, to appear in J. Communications and Networks

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., Comment: 14 pages, 5 figures

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 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., Comment: 20 pages, 14 figures; This article has been submitted to IEEE for possible publication

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 coined analog 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., Comment: 14 pages, 7 figures; This article has been submitted to IEEE for possible publication

While Remote control over wireless connections is a key enabler for scalable control systems consisting of multiple actuator-sensor pairs, i.e., control systems, it entails two technical challenges. Due to the lack of wireless resources, only a limited number of control systems can be served, making the state observations outdated. Further, even after scheduling, the state observations received through wireless channels are distorted, hampering control stability. To address these issues, in this article we propose a scheduling algorithm that guarantees the age-of-information (AoI) of the last received states. Meanwhile, for non-scheduled sensor-actuator pairs, we propose a machine learning (ML) aided predictive control algorithm, in which states are predicted using a Gaussian process regression (GPR). Since the GPR prediction credibility decreases with the AoI of the input data, both predictive control and AoI-based scheduler should be co-designed. Hence, we formulate a joint scheduling and transmission power optimization via the Lyapunov optimization framework. Numerical simulations corroborate that the proposed co-designed predictive control and AoI based scheduling achieves lower control errors, compared to a benchmark scheme using a round-robin scheduler without state prediction., Comment: 5 pages, 4 figures, submitted to IEEE SPAWC 2020

Notwithstanding the significant traction gained by ultra-reliable and low-latency communication (URLLC) in both academia and 3GPP standardization, fundamentals of URLLC remain elusive. Meanwhile, new immersive and high-stake control applications with much stricter reliability, latency and scalability requirements are posing unprecedented challenges in terms of system design and algorithmic solutions. This article aspires at providing a fresh and in-depth look into URLLC by first examining the limitations of 5G URLLC, and putting forward key research directions for the next generation of URLLC, coined eXtreme ultra-reliable and low-latency communication (xURLLC). xURLLC is underpinned by three core concepts: (1) it leverages recent advances in machine learning (ML) for faster and reliable data-driven predictions; (2) it fuses both radio frequency (RF) and non-RF modalities for modeling and combating rare events without sacrificing spectral efficiency; and (3) it underscores the much needed joint communication and control co-design, as opposed to the communication-centric 5G URLLC. The intent of this article is to spearhead beyond-5G/6G mission-critical applications by laying out a holistic vision of xURLLC, its research challenges and enabling technologies, while providing key insights grounded in selected use cases., Comment: 7 pages, 6 figures; This work has been submitted to the IEEE for possible publication

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)., Comment: 20 pages, 8 figures; to appear in IEEE Transactions on Communications

Massive multiple-input multiple-output (massive MIMO) and small cell densification are complementary key 5G enablers. Given a fixed number of the entire base-station 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 (multi-carrier 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.

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.

Devices at the edge of wireless networks are the last mile data sources for machine learning (ML). As opposed to traditional ready-made public datasets, these user-generated private datasets reflect the freshest local environments in real time. They are thus indispensable for enabling mission-critical intelligent systems, ranging from fog radio access networks (RANs) to driverless cars and e-Health wearables. This article focuses on how to distill high-quality on-device ML models using fog computing, from such user-generated private data dispersed across wirelessly connected devices. To this end, we introduce communication-efficient and privacy-preserving distributed ML frameworks, termed fog ML (FML), wherein on-device ML models are trained by exchanging model parameters, model outputs, and surrogate data. We then present advanced FML frameworks addressing wireless RAN characteristics, limited on-device resources, and imbalanced data distributions. Our study suggests that the full potential of FML can be reached by co-designing communication and distributed ML operations while accounting for heterogeneous hardware specifications, data characteristics, and user requirements., Comment: 7 pages, 6 figures; This work has been submitted to the IEEE for possible publication

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 a 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., Comment: 30 pages, 8 figures, to appear in IEEE Internet of Things Journal

In this paper, a novel framework that uses wireless mobile miners (MMs) for computation purposes in a blockchain system is proposed. In the introduced system, the blockchain ledger is located at the communication nodes (CNs), and the MMs associated with CNs process the blockchain's proof-of-work (PoW) computation to verify the originality of the data. The MM that is the first to finish its PoW will receive a reward by sending its computing result to the CNs that are connected to other MMs. In the considered scenario, a blockchain forking event occurs if the MM having the shortest PoW delay fails to be the first to update its computing result to other MMs. To enable such mobile operations for a blockchain with minimum forking events, it is imperative to maintain low-latency wireless communications between MMs and CNs. To analyze the sensitivity of the system to latency, the probability of occurrence of a forking event is theoretically derived. The system is then designed so as to compute the forked block's PoW again to recover from a forking event. For this case, the average energy consumption of an MM is derived as a function of the system parameters such as the number of MMs and power consumed by the computing, transmission, and mobility processes of the MMs. Simulation results verify the analytical derivations and show that using a larger number of MMs can reduce the energy consumption by up to 94.5% compared to a blockchain system with a single MM.

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, etc.), 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 is unevenly distributed over a large number of edge nodes, which have access to a tiny fraction of the data. Moreover training and inference is 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 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 demonstrating the effectiveness of edge ML in unlocking the full potential of 5G and beyond., Comment: 34 pages, 31 figures, 2 tables; to appear in the Proceedings of the IEEE

By leveraging blockchain, this letter proposes a blockchained federated learning (BlockFL) architecture where local learning model updates are exchanged and verified. This enables on-device machine learning without any centralized training data or coordination by utilizing a consensus mechanism in blockchain. Moreover, we analyze an end-to-end latency model of BlockFL and characterize the optimal block generation rate by considering communication, computation, and consensus delays., Comment: to appear in IEEE Communications Letters

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 correctness of the existing coverage expressions derived through stochastic geometry may be questioned, as it is not clear whether they capture the impact of the detailed mmWave channel and antenna features. In this study, we propose an SINR coverage analysis framework that includes realistic channel model (from NYU) and antenna element radiation patterns (with isotropic/directional radiation). We first introduce two parameters, aligned gain and misaligned gain, associated with the desired signal beam and the interfering signal beam, respectively. We provide the distributions of the aligned and misaligned gains through curve fitting of system-simulation results. The distribution of these gains is used to determine the distribution of the SINR. We compare the obtained analytical SINR coverage with the corresponding SINR coverage calculated via 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 are thus expected to be useful to evaluate the system performance under ultra-reliable and low-latency communication (URLLC) and evolved mobile broadband (eMBB) scenarios, respectively., Comment: Accepted to IEEE Transactions on Communications (TCOM)

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., Comment: 7 pages, 4 figures, submitted to IEEE GLOBECOM'18

This paper proposes a real-time movement control algorithm for massive unmanned aerial vehicles (UAVs) that provide emergency cellular connections in an urban disaster site. While avoiding the inter-UAV collision under temporal wind dynamics, the proposed algorithm minimizes each UAV's energy consumption per unit downlink rate. By means of a mean-field game theoretic flocking approach, the velocity control of each UAV only requires its own location and channel states. Numerical results validate the performance of the algorithm in terms of the number of collisions and energy consumption per data rate, under a realistic 3GPP UAV channel model., Comment: to be presented in the 19th IEEE International Workshop on Signal Processing Advances In Wireless Communications (SPAWC), Kalamata, Greece, 2018

Immersive social interactions of mobile users are soon to be enabled within a virtual space, by means of virtual reality (VR) technologies and wireless cellular systems. In a VR mobile social network, the states of all interacting users should be updated synchronously and with low latency via two-way communications with edge computing servers. The resulting end-to-end latency depends on the relationship between the virtual and physical locations of the wireless VR users and of the edge servers. In this work, the problem of analyzing and optimizing the end-to-end latency is investigated for a simple network topology, yielding important insights into the interplay between physical and virtual geometries., Comment: 4 pages, 3 figures, to appear in IEEE Wireless Communications Letters

This paper investigates a cellular edge caching problem under a very large number of small base stations (SBSs) and users. In this ultra-dense edge caching network (UDCN), conventional caching algorithms are inapplicable as their complexity increases with the number of small base stations (SBSs). Furthermore, the performance of UDCN is highly sensitive to the dynamics of user demand and inter-SBS interference. To overcome such difficulties, we propose a distributed caching algorithm under a stochastic geometric network model, as well as a spatio-temporal user demand model that characterizes the content popularity dynamics. By exploiting mean-field game (MFG) theory, the complexity of the proposed UDCN caching algorithm becomes independent of the number of SBSs. Numerical evaluations validate that the proposed caching algorithm reduces not only the long run average cost of the network but also the redundant cached data respectively by 24% and 42%, compared to a baseline caching algorithm. The simulation results also show that the proposed caching algorithm is robust to imperfect popularity information, while ensuring a low computational complexity., Comment: submitted for suitable IEEE publication

Cloud RAN (C-RAN) is a promising enabler for distributed massive MIMO systems, yet is vulnerable to its fronthaul congestion. To cope with the limited fronthaul capacity, this paper proposes a hybrid analog-digital precoding design that adaptively adjusts fronthaul compression levels and the number of active radio-frequency (RF) chains out of the entire RF chains in a downlink distributed massive MIMO system based on C-RAN architecture. Following this structure, we propose an analog beamformer design in pursuit of maximizing multi-user sum average data rate (sum-rate). Each element of the analog beamformer is constructed based on a weighted sum of spatial channel covariance matrices, while the size of the analog beamformer, i.e. the number of active RF chains, is optimized so as to maximize the large-scale approximated sum-rate. With these analog beamformer and RF chain activation, a regularized zero- forcing (RZF) digital beamformer is jointly optimized based on the instantaneous effective channel information observed through the given analog beamformer. The effectiveness of the proposed hybrid precoding algorithm is validated by simulation, and its design criterion is clarified by analysis., Comment: Submitted to IEEE Journal of Selected Topics in Signal Processing

Ultra-reliable low latency communication (URLLC) is an important new feature brought by 5G, with a potential to support a vast set of applications that rely on mission-critical links. In this article, we first discuss the principles for supporting URLLC from the perspective of the traditional assumptions and models applied in communication/information theory. We then discuss how these principles are applied in various elements of the system design, such as use of various diversity sources, design of packets and access protocols. The important messages are that there is a need to optimize the transmission of signaling information, as well as a need for a lean use of various sources of diversity., Comment: Submitted to IEEE Network; Revised after 1st round of review; Title changed after 2nd review

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 a closed-form SIR coverage probability in large-scale mmWave cellular networks., Comment: 7 pages, 6 figures, submitted to GLOBECOM 2017

Real-time distributed control is a promising application of 5G in which communication links should satisfy certain reliability guarantees. In this letter, we derive closed-form maximum average rate when a device (e.g. industrial machine) downloads a sequence of n operational commands through cellular connection, while guaranteeing a certain signal-to-interference ratio (SIR) coverage for all n messages. The result is based on novel closed-form n-successive SIR coverage bounds. The proposed bounds provide simple approximations that are increasingly accurate in the high reliability region., Comment: 4 pages, 3 figures, submitted to IEEE Wireless Communications Letters

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, FRu reduces 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., Comment: 7 pages, 6 figures, to appear in proc. IEEE WiOpt Wksp. SpaSWiN 2017

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 inapplicable 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., Comment: to be presented in IEEE International Conference on Communications (ICC), Paris, France, 2017

In this paper, we investigate the impact of network densification on the performance in terms of downlink signal-to-interference (SIR) coverage probability and network area spectral efficiency (ASE). A sophisticated bounded dual-slope path loss model and practical user equipment (UE) densities are incorporated in the analysis, which have never been jointly considered before. By using stochastic geometry, we derive an integral expression along with closed-form bounds of the coverage probability and ASE, validated by simulation results. Through these, we provide the asymptotic behavior of ultra-densification. The coverage probability and ASE have non-zero convergence in asymptotic regions unless UE density goes to infinity (full load). Meanwhile, the effect of UE density on the coverage probability is analyzed. The coverage probability will reveal an U-shape for large UE densities due to interference fall into the near-field, but it will keep increasing for low UE densites. Furthermore, our results indicate that the performance is overestimated without applying the bounded dual-slope path loss model. The derived expressions and results in this work pave the way for future network provisioning., Comment: 7 pages, 4 figures, to appear in European Wireless 2017

In an Ultra-dense network (UDN) where there are more base stations (BSs) than active users, it is possible that many BSs are instantaneously left idle. Thus, how to utilize these dormant BSs by means of cooperative transmission is an interesting question. In this paper, we investigate the performance of a UDN with two types of cooperation schemes: non-coherent joint transmission (JT) without channel state information (CSI) and coherent JT with full CSI knowledge. We consider a bounded dual-slope path loss model to describe UDN environments where a user has several BSs in the near-field and the rest in the far-field. Numerical results show that non-coherent JT cannot improve the user spectral efficiency (SE) due to the simultaneous increment in signal and interference powers. For coherent JT, the achievable SE gain depends on the range of near-field, the relative densities of BSs and users, and the CSI accuracy. Finally, we assess the energy efficiency (EE) of cooperation in UDN. Despite costing extra energy consumption, cooperation can still improve EE under certain conditions., Comment: 6 pages, 8 figure, to appear in EuCNC 2017

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., Comment: 7 pages, 3 figures, to appear in proc. IEEE GLOBECOM 2016