In this paper, we propose a novel framework for communication efficient distributed learning, FedBDQB, by employing bidirectional dynamic quantization for model updates and bitmap-based lossless compression, and provide its descending analysis and convergence proof. The performance of FedBDQB is evaluated under two representative use cases of distributed learning, federated learning and blockchain-enabled federated learning, comparing with the classic FedAvg and two state-of-the-art methods FedDQ and TinyOFL across various experimental scenarios using multiple widely-adopted datasets (MNIST, CIFAR-10, and CIFAR-100) with both IID and non-IID data partitioning. Experimental results demonstrate that with the case of legacy federated learning, our proposed FedBDQB can significantly reduce the data communication cost over the baselines, especially when the number of clients or the size of the trained model is enlarged, with a negligible decrease in model accuracy and an acceptable increase in computational time. With the case of resource-consuming blockchain-enabled federated learning, FedBDQB can profoundly decrease the resource consumption including computation, traffic volume and storage and improve the consensus efficiency, which provides a promising solution for the practical applicability of blockchain-based distributed learning systems.

Federated Learning (FL) is a promising paradigm for realizing edge intelligence. However, its practical deployment remains vulnerable to model perturbations, such as communication noise and quantization errors, which can significantly degrade model accuracy. Moreover, this degradation is further amplified in the presence of data heterogeneity. To address the above issues, we propose a novel FL framework, termed Sharpness-aware Minimization-based Robust Federated Learning (SMRFL), which provides intrinsic model robustness against perturbations by leveraging an intriguing geometrical property of the loss landscape: models around a flat minimum tend to exhibit similarly low loss values and thus higher robustness. Specifically, SMRFL encourages model convergence toward flat minima by solving a min-max optimization problem that minimizes the worst-case loss within a neighborhood of the model. To further mitigate the impact of data heterogeneity, we proposed Locally Aligned-SMRFL (LA-SMRFL), which incorporates a consensus constraint into the min-max optimization and solves it via inexact Alternating Direction Method of Multipliers (ADMM). We provide theoretical analysis for the convergence of SMRFL and LA-SMRFL in the non-convex FL setting, and derive robustness bounds via the certified radius. Extensive experiments on two real-world datasets under three perturbation scenarios demonstrate that SMRFL and LASMRFL substantially outperform baseline methods in terms of robustness.

Semantic communication is a novel communication paradigm focusing on the transmission of meaningful, task-oriented information. Recent results have shown that graphical structures represent the most robust and structurally faithful formalism for modeling the semantic knowledge within a wide range of source signals. However, previous solutions focus primarily on the pairwise relational graphs, which inherently lack the capacity to encapsulate complex, higher-order interactions fundamental to specific semantic contexts. In contrast, hypergraphs provide a more flexible mathematical framework that can more accurately map the multidimensional dependencies found in intricate data sources. In this paper, we investigate hypergraph-based semantic representation for the semantic communication system. We propose a novel hypergraph information bottleneck-based implicit semantic communication framework (HIB-SC), in which the semantic encoder is developed and optimized to extract the minimally sufficient representation of the hypergraph-based semantic information source, that maximizes the mutual information between the encoded representation and the implicit high-order semantic relations that are intended for the receiver. We theoretically prove that the proposed framework is able to extract the most informative subgraphs or motifs that are significantly more robust against adversarial attacks with improved generalization performance. Extensive experiments verify that the proposed HIB-SC achieves superior semantic compression efficiency, higher accuracy in implicit semantic inference, and enhanced resilience against noise, compared to the state-of-the-art solutions.

Agentic AI networking (AgentNet) is a novel AI-native networking paradigm in which a large number of specialized AI agents collaborate to perform autonomous decisions, dynamic environmental adaptation, and complex missions. AgentNet has the potential to facilitate real-time network management and optimization functions, including self-configuration, self-optimization, and self-adaptation across diverse and complex environments, laying the foundation for fully autonomous networking systems. Despite its promise, AgentNet is still in the early stages of development and still lacks an effective networking framework to support automatic goal discovery, multi-agent self-orchestration, and task assignment. This paper proposes SANet, a novel semantic-aware AgentNet architecture for wireless networks. SANet can infer the semantic goal of the user and automatically assign agents associated with different layers of the network stack to fulfill the inferred goal. Motivated by the fact that AgentNet is a decentralized framework in which collaborating agents may generally have different and even conflicting objectives, we formulate the decentralized optimization of SANet as a multi-agent multi-objective problem, and focus on finding the Pareto-optimal solution for agents with distinct and potentially conflicting objectives. We propose three novel metrics for evaluating SANet: (the agents' objective) optimization error, (dynamic environment) generalization error, and (multi-objective) conflicting error. Furthermore, we develop a model partition and sharing (MoPS) framework in which large models, e.g., deep learning models, of different agents can be partitioned into shared and agent-specific parts that are jointly constructed and deployed according to agents' local computational resources. Two decentralized optimization algorithms, static-weighting and dynamic-weighting algorithms, are introduced to optimize the above three metrics. A bandwidth-adaptive compression framework is also proposed to enable different agents to perform in situ compression of their intermediate embeddings, dynamically adjusting to localized resource constraints and task requirements. We derive theoretical bounds for all these performance metrics and prove that there exists a three-way tradeoff among optimization, generalization, and conflicting errors. Finally, to validate our theoretical results, we develop an open-source Radio Access Network (RAN) and core network-based hardware prototype that implements three Transformer-based time-series prediction agents to interact with three different layers of the network. Experimental results show that the proposed MoPS framework achieves performance gains of up to$14.61\%$while requiring only$44.37\%$of the Floating-Point Operations (FLOPs) for inference at each agent compared to state-of-the-art algorithms. Also, compared to the static-weighting algorithm, the dynamic-weighting algorithm achieves up to$83.81\%$reduction in training errors caused by conflicting objectives.

Agentic AI networking (AgentNet) has attracted significant interest due to its promising potential to move traditional AI-based networking solutions beyond closed-loop and passive learning to proactive interaction and goal-driven action, offering a path to self-learning and generally intelligent networking systems. Despite its promise, ensuring the security and trustworthiness of such systems presents significant challenges, particularly concerning identity management, agent capability verification, and data integrity during collaborative learning. To address these issues, this paper proposes TrustAgentNet, a novel consortium blockchain-based framework for unified and trusted agent identification, traceable skillset and tag descriptions, and secure on-chain collaborative learning in AgentNet. In TrustAgentNet, a chain of skillset (CoS) is introduced, consisting of a skillset chain to distributedly store all the verified skillsets and associated tags, and a dedicated training chain for each distinct skillset can be jointly constructed and maintained by the authorized agents using a collaborative learning-based approach. Theoretical analysis suggests that there exists a three-way trade-off among the security level, skillset performance, and resource cost. This tradeoff is also empirically validated by the experimental results obtained from a hardware prototype implemented based on a Hyperledger Fabric-based consortium blockchain. To verify the practical performance of TrustAgentNet, we consider a real-world scenario of multi-agent collaborative learning under malicious attack. Experimental results suggest that TrustAgentNet can effectively guarantee the security of skillset training and enable rapid response and recovery from potential attacks within seconds.

Agentic AI networking (AgentNet) has attracted significant interest recently due to its promising potential in supporting proactive learning and seamless collaboration among distributed task-oriented agents in various environments. However, existing solutions face inherent dilemmas. On the one hand, developing a single globalized model that can generalize well for diverse agents incurs inconsistent and unreliable performance due to the neglect of their distinct deployment environments. On the other hand, constructing personalized models that are tailored according to the individual needs of each agent often suffers from resource inefficiency and under-utilization of shared knowledge among agents. To overcome these challenges, we propose MAN, a novel Meta learning-based AgentNet architecture that optimally balances generalization and personalization for all the agents when performing different tasks in dynamic environments. Specifically, MAN adopts a bi-level optimization framework to develop foundation meta-models as the shared initialization of all agents, and each agent can then fine-tune the meta model to enable personalized deployment. We derive theoretical bounds on both global generalization and local personalization errors, demonstrating that the fundamental tradeoff between these two can only be optimized but cannot be fully eliminated. Extensive experiments on real-world datasets validate the performance of the proposed MAN and confirm the generality of our theoretical insights.

Federated Learning (FL) is a promising paradigm for realizing edge intelligence, allowing collaborative learning among distributed edge devices by sharing models instead of raw data. However, the shared models are often assumed to be ideal, which would be inevitably violated in practice due to various perturbations, leading to significant performance degradation. To overcome this challenge, we propose a novel method, termed Sharpness-Aware Minimization-based Robust Federated Learning (SMRFL), which aims to improve model robustness against perturbations by exploring the geometrical property of the model landscape. Specifically, SMRFL solves a min-max optimization problem that promotes model convergence towards a flat minimum by minimizing the maximum loss within a neighborhood of the model parameters. In this way, model sensitivity to perturbations is reduced, and robustness is enhanced since models in the neighborhood of the flat minimum also enjoy low loss values. The theoretical result proves that SMRFL can converge at the same rate as FL without perturbations. Extensive experimental results show that SMRFL significantly enhances robustness against perturbations compared to three baseline methods on two real-world datasets under three perturbation scenarios.

Semantic-aware communication (SAC) has attracted significant interest recently due to its potential to revolutionize the traditional communication framework by focusing on delivering the meaning of information, enabling more efficient, reliable, and intelligent communication. Most existing AI-based solutions for multi-user SAC focus on developing encoding models for all users and a decoding model for a specific receiver. While powerful, this single-task-oriented codec design faces significant challenges when deployed in more general multi-task scenarios. In this paper, we investigate codec design problems in multi-user multitask SAC based on distributed information bottleneck (DIB) theory. We propose a novel task-aware DIB scheme (TADIB) for joint codec designing. In TADIB, the receiver, when performing a specific task, first estimates the relevance between users' datasets and the task based on their mutual information, which is incorporated into the training phase of both encoders and decoders. Then most task-relevant users are selected to send the encoded signals for task inference during the deployment phase. Furthermore, we employ variational approximation to derive tractable upper bounds for the DIB-based objective, which would otherwise be computationally prohibitive for high-dimensional data. This approach also reduces the computational complexity of the user selection procedures. Extensive results show that the proposed TADIB can achieve up to 3.38% improvements in inference accuracy of classification tasks, compared to existing solutions for task-oriented SAC.

This paper investigates the joint source-channel coding (JSCC) problem for semantic-aware communication (SAC) systems with multi-view data sources. We extend the theory of multi-view information bottleneck by incorporating a constraint that characterizes the impact of channel corruption on the recovery of task signals at the receiver, referred to as the multiview information bottleneck with channel protection (MVIB-CP). We propose a computationally efficient optimization framework for calculating the MVIB-CP problem in which a contrastive log-ratio upper bound and a simplified variation approximation solution are introduced to estimate mutual information and approximate the divergence of task signal recovery caused by the noisy channel corruption. The proposed MVIB-CP can investigate the tradeoff of the multi-view source compression and the protection of channel corruptions while the above optimization framework can significantly reduce the computational complexity of addressing the MVIB-CP. We present the optimization algorithm for developing the JSCC schemes in multi-view SAC systems. Extensive experiments are conducted based on realworld multi-view source datasets. Our results show that the MVIB-CP-based JSCC achieves up to$\mathbf{5. 2 8 \%}$improvement in task signal recovery accuracy, compared to the classical JSCC solution.

Network slicing is one of the key enablers for B5G and 6G to support diversified IoT services and application scenarios. In this paper, the problem of network slicing for supporting time-sensitive edge learning in massive-scale IoT networks is studied. In particular, a novel distributed network slicing framework based on a new control plane entity, called D-orchestrator, is proposed. This framework can jointly optimize the allocation and orchestration of communication and edge computational resources without requiring exchanges of the local data or resource information between base stations (BSs) and edge servers. A distributed joint resource allocation algorithm is developed based on the alternating direction method of multipliers with partial variable splitting (DistADMM-PVS) that minimizes the average service response-time of a set of service instances when the coordination among the D-orchestrator, BSs, and edge servers is perfectly synchronized. Motivated by the observation that the synchronization of coordination may result in high coordination delay that can be intolerable in many practical scenarios, particularly for large IoT networks, a novel asynchronized ADMM (AsyncADMM) algorithm is proposed. In AsyncADMM, the D-orchestrator, BSs, and edge servers can be coordinated asynchronously. AsyncADMM is then shown to converge to the global optimal solution with improved scalability and negligible coordination delay. The performance of the proposed framework is evaluated using two-month of traffic data collected in an in-campus smart transportation system supported by a 5G network. Extensive simulations are conducted for both pedestrian and vehicular-related services during peak and non-peak hours. Simulation results show that the proposed distributed network slicing framework offers a significant reduction in the service response time for both supported services.

Autonomous aerial vehicles (AAV)-enabled IoT networks have shown promising potential in a range of novel applications and service scenarios, such as extending the network coverage, extending the battery lifetime of IoT networks, and also supporting temporary data collecting and processing needs in various emergency situations. This article studies a federated edge intelligence (FEI) network based on the data collected and uploaded by a AAV-enabled IoT network. More specifically, a set of AAVs has periodically collected and uploaded the data generated by an IoT network to a set of edge servers. Edge servers will then collaboratively construct shared models based on the uploaded datasets. The data uploading performance of a AAV-enabled IoT network and the computational capacity of edge servers are entangled with each other in influencing the overall model training process. We propose a new framework called AAV-enabled IoT network for FEI (U-FEI). This framework enables edge servers to assess how many data samples need to be collected based on the energy costs of the AAV-enabled IoT network. It also considers the local data processing capacity of the edge servers. As a result, the edge servers can request just the right amount of data from the AAVs, which is enough to train a satisfactory model. We evaluate the energy cost for data uploading of AAVs when the data can be uploaded from two different types of frequencies: 1) licensed bands (e.g., using 5G) and 2) unlicensed bands (e.g., using Wi-Fi, ZigBee, or 5G NR-U). We prove that the cost minimization problem of the entire AAV-enabled IoT network is separable and can be divided into a set of subproblems, each of which can be solved by an individual edge server. We also introduce a mapping function to quantify the computational load of edge servers under the combinations of three key parameters: 1) size of the dataset; 2) local batch size; and 3) number of local training passes. Finally, we adopt an alternative direction method of multipliers (ADMM)-based approach to jointly optimize the energy cost of the AAV-enabled IoT network and average resource utilization of edge servers. We prove that our proposed algorithm does not cause any data leakage nor disclose any topological information of the AAV-enabled IoT networks. Simulation results show that our proposed framework significantly improves the resource efficiency of both the AAV-enabled IoT network and edge servers.

Contactless device-free wireless sensing has recently attracted significant interest due to its potential to support a wide range of immersive human-machine interactive applications using ubiquitously available radio frequency (RF) signals. Traditional approaches focus on developing a single global model based on a combined dataset collected from different locations. However, wireless signals are known to be location and environment specific. Thus, a global model results in inconsistent and unreliable sensing results. It is also unrealistic to construct individual models for all the possible locations and environmental scenarios. Motivated by the observation that signals recorded at different locations are closely related to a set of physical-layer semantic features, in this paper we propose SANSee, a semantic-aware networking-based framework for distributed wireless sensing. SANSee allows models constructed in one or a limited number of locations to be transferred to new locations without requiring any locally labeled data or model training. SANSee is built on the concept of physical-layer semantic-aware network (pSAN), which characterizes the semantic similarity and the correlations of sensed data across different locations. A pSAN-based zero-shot transfer learning solution is introduced to allow receivers in new locations to obtain location-specific models by directly aggregating the models trained by other receivers. We theoretically prove that models obtained by SANSee can approach the locally optimal models. Experimental results based on real-world datasets are used to verify that the accuracy of the transferred models obtained by SANSee matches that of the models trained by the locally labeled data based on supervised learning approaches.

RF-based wireless sensing is a promising technology for enabling applications such as human activity recognition, intelligent healthcare, and robotics. However, the growing concern in data privacy and also the complexity in modeling and keeping track of the statistical heterogeneity of RF signal hinders its wide application, especially in large-scale wireless networking systems. In this paper, we introduce a hierarchical clustering-based federated learning framework, called Uniform Manifold Clustering Federated Learning (UMCFL), that has the potential to address the above challenges. UMCFL first divides all the RF signal receivers into different clusters according to the similarity of their data distributions and then construct an individual model for receivers within each cluster. To measure the data distribution similarity between receivers in a computationally efficient way, UMCFL first adopts a uniform manifold approximation and projection (UMAP)-based solution to convert data samples at each receiver into a low-dimensional representation and then use maximum mean discrepancy (MMD) to calculate the similarity score between datasets of different receivers. We prove the convergence of UMCFL and perform extensive experiments to evaluate its performance. Experimental results show that UMCFL achieves up to 63% improvement in sensing accuracy, compared to the traditional FedAvg-based wireless sensing solution.

Wireless sensing has recently attracted significant interest due to its potential to support a wide range of immersive human-machine interactive applications without requiring any extra devices to be carried out by human users. However, previous studies have shown that wireless sensing performance can be significantly degraded if the relative locations of the transmitters, human users, and receivers are non-ideal and/or the distances between the user and receivers are large. These constraints hinder the wide applications of wireless sensing in many practical scenarios. A promising approach for wireless sensing is through the use of reconfigurable intelligent surfaces (RISs) that can control the propagation environment to create a customizable wireless environment for wireless sensing. To this end, in this paper, the use of RIS-assisted wireless sensing for enhanced human gesture recognition is investigated. A novel RIS-assisted distributed wireless sensing framework that utilizes federated learning (FL) is proposed to enable collaborative model training among decentralized receivers. Then, a novel metric, called human-influencing signal-to-interference ratio (HSIR), is introduced to characterize the quality of locally recorded data as well as its impact on the performance of wireless sensing. To alleviate the model draft problem of FL-assisted wireless sensing, caused by spatial heterogeneity of the quality of wireless sensing data at different receivers, the optimal amplitudes and phases of the RIS are derived so as to improve the HSIR of a set of low-performance receivers located at non-ideal locations. Simulation results show that the proposed RIS-assisted system can significantly improve wireless sensing accuracy by up to 20.1% compared to traditional distributed system.

Developing sustainable and environmentally friendly network AI solutions has attracted significant interest recently. Unfortunately, analyzing the overall environmental impact, the greenhouse emissions in particular, of a network AI implementation is known to be a notoriously challenging task. As a popular distributed AI framework, federated edge intelligence (FEI) has been promoted as a candidate technology for implementing network AI in 6G. Unfortunately, recent studies suggest that the FEI network may generate more carbon emissions than the traditional centralized AI solutions. In this paper, we propose a novel analytical framework to quantify and optimize the carbon emissions of FEI networks. We develop an analytical model for quantifying the overall carbon emissions required for constructing a shared model in FEI with the guaranteed accuracy level. We propose a server-dropping-based algorithm that removes the highest-emitting and low-contributing edge servers from participating in the model training to minimize the overall carbon emissions. We conduct extensive experiments and the experimental results show that our proposed algorithm reduces up to 80% of carbon emissions, compared to the traditional FL-based solution.

The Digital Twin Network (DTN) holds immense potential in shaping future networks by seamlessly integrating physical networks and virtual representations. However, high-fidelity twin network modeling proves complicated and resource-intensive. To address this challenge, this paper proposes a federated generative model with multiple generators for DTN (FMG-DTN) modeling, which can generate high-fidelity data without increasing communication overhead. Firstly, generative learning is employed, enabling FMG to accurately synthesize data following the distribution of real data. Secondly, the model of FMG and its corresponding loss function are designed to mitigate the mode collapse problem in the presence of data heterogeneity by encouraging different generators to synthesize data with different categories. The mode collapse problem, referring to the generated data lacking diversity, can be exacerbated by data heterogene-ity. Finally, complexity analysis reveals that FMG requires a smaller communication overhead than a state-of-the-art method. Empirical results on a real-world traffic dataset demonstrate that the FMG can be trained to synthesize data accurately within a few training iterations, even under heterogeneous data settings. Moreover, the FMG model exhibits a higher diversity in the categories of synthesized samples compared to the state-of-the-art method.

There is still lacking a simple and comprehensive framework to model and optimize the overall energy consumption of an FEI network, especially in heterogeneous scenarios. This paper proposes a comprehensive framework to characterize the overall energy consumption of FEI networks. The computation and communication overhead as well as the number of coordination rounds required to train a satisfactory model are analytically modeled and evaluated. We investigate and compare the energy consumption of FEI networks with two popular distributed algorithmic implementations: FedAvg and FedMeta. We observe that although FedMeta consumes more energy than FedAvg in each single coordination round, the overall energy consumption of FedMeta is much lower than that of FedAvg. Finally, we evaluate the energy consumption of both algorithms based on a hardware prototype. Numerical results show that the overall energy consumption of FedMeta is 77.9% less than that of FedAvg.

With the rising demand for wireless services and increased awareness of the need for data protection, existing network traffic analysis and management architectures are facing unprecedented challenges in classifying and synthesizing the increasingly diverse services and applications. This paper proposes FS-GAN, a federated self-supervised learning framework to support automatic traffic analysis and synthesis over a large number of heterogeneous datasets. FS-GAN is composed of multiple distributed Generative Adversarial Networks (GANs), with a set of generators, each being designed to generate synthesized data samples following the distribution of an individual service traffic, and each discriminator being trained to differentiate the synthesized data samples and the real data samples of a local dataset. A federated learning-based framework is adopted to coordinate local model training processes of different GANs across different datasets. FS-GAN can classify data of unknown types of service and create synthetic samples that capture the traffic distribution of the unknown types. We prove that FS-GAN can minimize the Jensen-Shannon Divergence (JSD) between the distribution of real data across all the datasets and that of the synthesized data samples. FS-GAN also maximizes the JSD among the distributions of data samples created by different generators, resulting in each generator producing synthetic data samples that follow the same distribution as one particular service type. Extensive simulation results show that the classification accuracy of FS-GAN achieves over$20\%$improvement in average compared to the state-of-the-art clustering-based traffic analysis algorithms. FS-GAN also has the capability to synthesize highly complex mixtures of traffic types without requiring any human-labeled data samples.

Real-time machine learning (ML) has recently attracted significant interest due to its potential to support instantaneous learning, adaptation, and decision making in a wide range of application domains, including self-driving vehicles, intelligent transportation, and industry automation. In this paper, we investigate real-time ML in a federated edge intelligence (FEI) system, an edge computing system that implements federated learning (FL) solutions based on data samples collected and uploaded from decentralized data networks, e.g., Internet-of-Things (IoT) and/or wireless sensor networks. FEI systems often exhibit heterogenous communication and computational resource distribution, as well as non-i.i.d. data samples arrived at different edge servers, resulting in long model training time and inefficient resource utilization. Motivated by this fact, we propose a time-sensitive federated learning (TS-FL) framework to minimize the overall run-time for collaboratively training a shared ML model with desirable accuracy. Training acceleration solutions for both TS-FL with synchronous coordination (TS-FL-SC) and asynchronous coordination (TS-FL-ASC) are investigated. To address the straggler effect in TS-FL-SC, we develop an analytical solution to characterize the impact of selecting different subsets of edge servers on the overall model training time. A server dropping-based solution is proposed to allow some slow-performance edge servers to be removed from participating in the model training if their impact on the resulting model accuracy is limited. A joint optimization algorithm is proposed to minimize the overall time consumption of model training by selecting participating edge servers, the local epoch number (the number of model training iterations per coordination), and the data batch size (the number of data samples for each model training iteration). Motivated by the fact that data samples at the slowest edge server may exhibit special characteristics that cannot be removed from model training, we develop an analytical expression to characterize the impact of both staleness effect of asynchronous coordination and straggler effect of FL on the time consumption of TS-FL-ASC. We propose a load forwarding-based solution that allows a slow edge server to offload part of its training samples to trusted edge servers with higher processing capability. We develop a hardware prototype to evaluate the model training time of a heterogeneous FEI system. Experimental results show that our proposed TS-FL-SC and TS-FL-ASC can provide up to 63% and 28% of reduction, in the overall model training time, respectively, compared with traditional FL solutions.

Semantic-aware communication is a novel paradigm that draws inspiration from human communication focusing on the delivery of the meaning of messages. It has attracted significant interest recently due to its potential to improve the efficiency and reliability of communication and enhance users’ quality-of-experience (QoE). Most existing works focus on transmitting and delivering the explicit semantic meaning that can be directly identified from the source signal. This paper investigates the implicit semantic-aware communication in which the hidden information, e.g., hidden relations, concepts and implicit reasoning mechanisms of users, that cannot be directly observed from the source signal must be recognized and interpreted by the intended users. To this end, a novel implicit semantic-aware communication (iSAC) architecture is proposed for representing, communicating, and interpreting the implicit semantic meaning between source and destination users. A graph-inspired structure is first developed to represent the complete semantics, including both explicit and implicit, of a message. A projection-based semantic encoder is then proposed to convert the high-dimensional graphical representation of explicit semantics into a low-dimensional semantic constellation space for efficient physical channel transmission. To enable the destination user to learn and imitate the implicit semantic reasoning process of source user, a generative adversarial imitation learning-based solution, called G-RML, is proposed. Different from existing communication solutions, the source user in G-RML does not focus only on sending as much of the useful messages as possible; but, instead, it tries to guide the destination user to learn a reasoning mechanism to map any observed explicit semantics to the corresponding implicit semantics that are most relevant to the semantic meaning. By applying G-RML, we prove that the destination user can accurately imitate the reasoning process of the source user and automatically generate a set of implicit reasoning paths following the same probability distribution as the expert paths. Compared to the existing solutions, our proposed G-RML requires much less communication and computational resources and scales well to the scenarios involving the communication of rich semantic meanings consisting of a large number of concepts and relations. Numerical results show that the proposed solution achieves up to 92% accuracy of implicit meaning interpretation.

Semantic communication is a novel communication paradigm that focuses on recognizing and delivering the desired meaning of messages to the destination users. Most existing works in this area focus on delivering explicit semantics, labels or signal features that can be directly identified from the source signals. In this paper, we consider the implicit semantic communication problem in which hidden relations and closely related semantic terms that cannot be recognized from the source signals need to also be delivered to the destination user. We develop a novel adversarial learning-based implicit semantic-aware communication (iSAC) architecture in which the source user, instead of maximizing the total amount of information transmitted to the channel, aims to help the recipient learn an inference rule that can automatically generate implicit semantics based on limited clue information. We prove that by applying iSAC, the destination user can always learn an inference rule that matches the true inference rule of the source messages. Experimental results show that the proposed iSAC can offer up to a 19.69 dB improvement over existing non-inferential communication solutions, in terms of symbol error rate at the destination user.

Device-free wireless sensing has recently attracted significant interest due to its potential to support a wide range of immersive human-machine interactive applications. However, data heterogeneity in wireless signals and data privacy regulation of distributed sensing have been considered as the major challenges that hinder the wide applications of wireless sensing in large area networking systems. Motivated by the observation that signals recorded by wireless receivers are closely related to a set of physical-layer semantic features, in this paper we propose a novel zero-shot wireless sensing solution that allows models constructed in one or a limited number of locations to be directly transferred to other locations without any labeled data. We develop a novel physical-layer semantic-aware network (pSAN) framework to characterize the correlation between physical-layer semantic features and the sensing data distributions across different receivers. We then propose a pSAN-based zero-shot learning solution in which each receiver can obtain a location-specific gesture recognition model by directly aggregating the already constructed models of other receivers. We theoretically prove that models obtained by our proposed solution can approach the optimal model without requiring any local model training. Experimental results once again verify that the accuracy of models derived by our proposed solution matches that of the models trained by the real labeled data based on supervised learning approach.

This paper analyzes the fundamental limit of the strategic semantic communication problem in which a transmitter obtains a limited number of indirect observations of an intrinsic semantic information source and can then influence the receiver’s decoding by sending a limited number of messages over an imperfect channel. The transmitter and the receiver can have different distortion measures and can make rational decisions about their encoding and decoding strategies, respectively. The decoder can also have some side information (e.g., background knowledge and/or information obtained from previous communications) about the semantic source to assist its interpretation of the semantic information. We focus particularly on the case that the transmitter can commit to an encoding strategy and study the impact of the strategic decision making on the rate distortion of semantic communication. Three equilibrium solution concepts including the optimal Stackelberg equilibrium, robust Stackelberg equilibrium, as well as Nash equilibrium are studied and compared. The optimal encoding and decoding strategy profiles under various equilibrium solutions are derived. We prove that committing to an encoding strategy cannot always bring benefit to the encoder. We provide a feasible condition under which committing to an encoding strategy can always reduce the distortion of semantic communication. We consider an example with a dictionary-based semantic information source to verify our observation.

This paper studies a multi-Intelligent Reflecting Surfaces (IRSs)-assisted wireless network consisting of multiple base stations (BSs) serving a set of mobile users. We focus on the IRS-BS association problem in which multiple BSs compete with each other for controlling the phase shifts of a limited number of IRSs to maximize the long-term downlink data rate for the associated users. We propose MDLBI, a Multi-agent Deep Reinforcement Learning-based BS-IRS association scheme that optimizes the BS-IRS association as well as the phase-shift of each IRS when being associated with different BSs. MDLBI does not require information exchanging among BSs. Simulation results show that MDLBI achieves significant performance improvement and is scalable for large networking systems.

The effective deployment of connected vehicular networks is contingent upon maintaining a desired performance across spatial and temporal domains. In this paper, a graph-based framework, called SMART, is proposed to model and keep track of the spatial and temporal statistics of vehicle-to-infrastructure (V2I) communication latency across a large geographical area. SMART first formulates the spatio-temporal performance of a vehicular network as a graph in which each vertex corresponds to a subregion consisting of a set of neighboring location points with similar statistical features of V2I latency and each edge represents the spatio-correlation between latency statistics of two connected vertices. Motivated by the observation that the complete temporal and spatial latency performance of a vehicular network can be reconstructed from a limited number of vertices and edge relations, we develop a graph reconstruction-based approach using a graph convolutional network integrated with a deep Q-networks algorithm in order to capture the spatial and temporal statistic of feature map pf latency performance for a large-scale vehicular network. Extensive simulations have been conducted based on a five-month latency measurement study on a commercial LTE network. Our results show that the proposed method can significantly improve both the accuracy and efficiency for modeling and reconstructing the latency performance of large vehicular networks.

With the fast growing demand on new services and applications as well as the increasing awareness of data protection, traditional centralized traffic classification approaches are facing unprecedented challenges. This paper introduces a novel framework, Federated Generative Adversarial Networks and Automatic Classification (FGAN-AC), which integrates decentralized data synthesizing with traffic classification. FGAN-AC is able to synthesize and classify multiple types of service data traffic from decentralized local datasets without requiring a large volume of manually labeled dataset or causing any data leakage. Two types of data synthesizing approaches have been proposed and compared: computation-efficient FGAN (FGAN-I) and communication-efficient FGAN (FGAN-II). The former only implements a single CNN model for processing each local dataset and the later only requires coordination of intermediate model training parameters. An automatic data classification and model updating framework has been proposed to automatically identify unknown traffic from the synthesized data samples and create new pseudo-labels for model training. Numerical results show that our proposed framework has the ability to synthesize highly mixed service data traffic and can significantly improve the traffic classification performance compared to existing solutions.

Network slicing has been considered as one of the key enablers for 5G to support diversified services and application scenarios. This paper studies the distributed network slicing utilizing both the spectrum resource offered by communication network and computational resources of a coexisting fog computing network. We propose a novel distributed framework based on a new control plane entity, regional orchestrator, which can be deployed between base stations and fog nodes to coordi- nate and control their bandwidth and computational resources. We propose a distributed resource allocation algorithm based on Alternating Direction Method of Multipliers with Partial Variable Splitting (DistADMM-PVS). We prove that DistADMM-PVS minimizes the average latency of the entire network and at the same time guarantee satisfactory latency performance for every supported type of service. Simulation results show that DistADMM-PVS converges much faster than some other existing algorithms. In addition, the joint network slicing with both bandwidth and computational resources offers around 15% overall latency reduction compared to network slicing with only a single resource.

Spatio-temporal modeling of wireless access latency is of great importance for connected-vehicular systems. The quality of the molded results rely heavily on the number and quality of samples which can vary significantly due to the sensor deployment density as well as traffic volume and density. This paper proposes LaMI (Latency Model Inpainting), a novel framework to generate a comprehensive spatio-temporal of wireless access latency of a connected vehicles across a wide geographical area. LaMI adopts the idea from image inpainting and synthesizing and can reconstruct the missing latency samples by a two-step procedure. In particular, it first discovers the spatial correlation between samples collected in various regions using a patching-based approach and then feeds the original and highly correlated samples into a Variational Autoencoder (VAE), a deep generative model, to create latency samples with similar probability distribution with the original samples. Finally, LaMI establishes the empirical PDF of latency performance and maps the PDFs into the confidence levels of different vehicular service requirements. Extensive performance evaluation has been conducted using the real traces collected in a commercial LTE network in a university campus. Simulation results show that our proposed model can significantly improve the accuracy of latency modeling especially compared to existing popular solutions such as interpolation and nearest neighbor-based methods.

In order to fully enjoy high rate broadband multimedia services, prolonging the battery lifetime of user equipment is critical for mobile users, especially for smartphone users. In this paper, the problem of distributing cellular data via a wireless power transfer enabled collaborative mobile cloud (WeCMC) in an energy efficient manner is investigated. WeCMC is formed by a group of users who have both functionalities of information decoding and energy harvesting, and are interested for cooperating in downloading content from the operators. Through device-to-device communications, the users inside WeCMC are able to cooperate during the downloading procedure and offload data from the base station to other WeCMC members. When considering multi-input multi-output wireless channel and wireless power transfer, an efficient algorithm is presented to optimally schedule the data offloading and radio resources in order to maximize energy efficiency as well as fairness among mobile users. Specifically, the proposed framework takes energy minimization and quality of service requirement into consideration. Performance evaluations demonstrate that a significant energy saving gain can be achieved by the proposed schemes.

Bandwidth efficiency is one of the most important indicators to measure different modulation schemes in digital communication systems. The waveforms of existing modulation schemes are all separated in time domain, making it difficult for them to improve in bandwidth efficiency. Compressive Sensing (CS) theory shows that it is possible to reconstruct original signals in aliasing measurements. In this paper, we propose a Compressive Modulation scheme by combining CS theory and traditional BPSK pattern. Theoretic analysis and experimental results show that the bandwidth efficiency can be highly improved by using the proposed scheme.