Xuemin Shen’s research while affiliated with University of Waterloo and other places

This paper investigates adaptive transmission strategies in embodied AI-enhanced vehicular networks by integrating large language models (LLMs) for semantic information extraction and deep reinforcement learning (DRL) for decision-making. The proposed framework aims to optimize both data transmission efficiency and decision accuracy by formulating an optimization problem that incorporates the Weber-Fechner law, serving as a metric for balancing bandwidth utilization and quality of experience (QoE). Specifically, we employ the large language and vision assistant (LLAVA) model to extract critical semantic information from raw image data captured by embodied AI agents (i.e., vehicles), reducing transmission data size by approximately more than 90\% while retaining essential content for vehicular communication and decision-making. In the dynamic vehicular environment, we employ a generalized advantage estimation-based proximal policy optimization (GAE-PPO) method to stabilize decision-making under uncertainty. Simulation results show that attention maps from LLAVA highlight the model's focus on relevant image regions, enhancing semantic representation accuracy. Additionally, our proposed transmission strategy improves QoE by up to 36\% compared to DDPG and accelerates convergence by reducing required steps by up to 47\% compared to pure PPO. Further analysis indicates that adapting semantic symbol length provides an effective trade-off between transmission quality and bandwidth, achieving up to a 61.4\% improvement in QoE when scaling from 4 to 8 vehicles.

Recent years have witnessed a thriving growth of computing facilities connected at the network edge, cultivating edge networks as a fundamental infrastructure for supporting miscellaneous intelligent services. Meanwhile, Artificial Intelligence (AI) frontiers have extrapolated to the graph domain and promoted Graph Intelligence (GI). Given the inherent relation between graphs and networks, the interdiscipline of graph learning and edge networks, i.e., Edge GI or EGI, has revealed a novel interplay between them – GI aids in optimizing edge networks, while edge networks facilitate GI model deployment. Driven by this delicate closed-loop, EGI is recognized as a promising solution to fully unleash the potential of edge computing power and is garnering growing attention. Nevertheless, research on EGI remains nascent, and there is a soaring demand within both the communications and AI communities for a dedicated venue to share recent advancements. To this end, this paper promotes the concept of EGI, explores its scope and core principles, and conducts a comprehensive survey concerning recent research efforts on this emerging field. Specifically, this paper introduces and discusses: 1) fundamentals of edge computing and graph learning, 2) emerging techniques centering on the closed loop between graph intelligence and edge networks, and 3) open challenges and research opportunities of future EGI. By bridging the gap across communication, networking, and graph learning areas, we believe that this survey can garner increased attention, foster meaningful discussions, and inspire further research ideas in EGI.

Innovative mobile artificial intelligence-generated content (AIGC) can support the evolution and updating processes of virtual twins (VTs) in human digital twin (HDT) systems. With a reliable and efficient automatic data generation process, the requirement for a timely physical-to-virtual synchronization in HDT can be satisfied. While such an AIGC-enabled HDT system can facilitate modelling high fidelity VTs, generating content that represents the true states in the physical environment and providing timely customized services, it may suffer from a poor understanding of contexts, a lack of creativity, and various security and privacy concerns. In this paper, we propose a novel framework, which integrates federated learning (FL) and semantic communication (SemCom) to enhance performance in the AIGC-enabled HDT system while improving accuracy and convergence properties. First, we present a holistic architectural framework for the proposed FL-enhanced SemCom (FLeS) solution for mobile AIGC-enabled HDT systems and discuss its design requirements and challenges. We later present key technologies necessary to realize the FLeS solution, followed by elaborating on important technical issues to suggest future directions. Experimental results demonstrate that FLeS not only facilitates reliable and personalized content generation but also shows better performance when compared to existing solutions.

AI technologies have become increasingly adopted in wireless communications. As an emerging type of AI technologies, generative artificial intelligence (GAI) is gaining attention in communication security. Due to its powerful learning ability, GAI models have demonstrated superiority over conventional AI methods. However, GAI still has several limitations, including high computational complexity and limited adaptability. Mixture of experts (MoE) technology, which uses multiple expert models for prediction through a gate mechanism, proposes possible solutions. In this article, we first review GAI model applications in physical layer communication security, discuss limitations, and explore how MoE can help GAI overcome these limitations. Furthermore, we propose an MoE-enabled GAI framework for network optimization problems for communication security. To demonstrate the framework's effectiveness, we provide a case study in a cooperative- friendly jamming scenario. The experimental results show that the MoE-enabled framework effectively assists the GAI algorithm, solves its limitations, and enhances communication security.

In this article, we propose a digital agent (DA)-assisted network management framework for future sixth generation (6G) networks considering users' quality of experience (QoE). Particularly, a novel QoE metric is defined by incorporating the impact of user behavior dynamics and environment complexity on quality of service (QoS). A two-level DA architecture is developed to assist the QoE-driven network orchestration and slicing, respectively. To further improve the performance of proposed framework, three potential solutions are presented from the perspectives of DA data collection, network scheduling algorithm selection, and DA deployment. A case study demonstrates that the proposed framework can effectively improve users' QoE compared with benchmark schemes.

With the rapid advancement and deployment of intelligent agents and artificial general intelligence (AGI), a fundamental challenge for future networks is enabling efficient communications among agents. Unlike traditional human-centric, data-driven communication networks, the primary goal of agent-based communication is to facilitate coordination among agents. Therefore, task comprehension and collaboration become the key objectives of communications, rather than data synchronization. Semantic communication (SemCom) aims to align information and knowledge among agents to expedite task comprehension. While significant research has been conducted on SemCom for two-agent systems, the development of semantic communication networks (SemComNet) for multi-agent systems remains largely unexplored. In this paper, we provide a comprehensive and up-to-date survey of SemComNet, focusing on their fundamentals, security, and privacy aspects. We introduce a novel three-layer architecture for multi-agent interaction , comprising the control layer, semantic transmission layer, and cognitive sensing layer. We explore working modes and enabling technologies, and present a taxonomy of security and privacy threats, along with state-of-the-art defense mechanisms. Finally, we outline future research directions, paving the way toward intelligent, robust, and energy-efficient SemComNet. This survey represents the first comprehensive analysis of SemComNet, offering detailed insights into its core principles as well as associated security and privacy challenges.

With the explosive development of mobile computing, federated learning (FL) has been considered as a promising distributed training framework for addressing the shortage of conventional cloud based centralized training. In FL, local model owners (LMOs) individually train their respective local models and then upload the trained local models to the task publisher (TP) for aggregation to obtain the global model. When the data provided by LMOs do not meet the requirements for model training, they can recruit workers to collect data. In this paper, by considering the interactions among the TP, LMOs and workers, we propose a three-layer hierarchical game framework. However, there are two challenges. Firstly, information asymmetry between workers and LMOs may result in that the workers hide their types. Secondly, incentive mismatch between TP and LMOs may result in a lack of LMOs' willingness to participate in FL. Therefore, we decompose the hierarchical-based framework into two layers to address these challenges. For the lower-layer, we leverage the contract theory to ensure truthful reporting of the workers' types, based on which we simplify the feasible conditions of the contract and design the optimal contract. For the upper-layer, the Stackelberg game is adopted to model the interactions between the TP and LMOs, and we derive the Nash equilibrium and Stackelberg equilibrium solutions. Moreover, we develop an iterative H ierarchical-based U tility M aximization A lgorithm (HUMA) to solve the coupling problem between upper-layer and lower-layer games. Extensive numerical experimental results verify the effectiveness of HUMA, and the comparison results illustrate the performance gain of HUMA.

In this paper, we propose an efficient and distributed service access control framework (E-DAC) in the pervasive edge computing (PEC) environment, where the resources of peer devices at the network edge are integrated to provide latencysensitive computing services to the nearby devices on behalf of edge servers. E-DAC addresses the challenge of efficient and distributed service access control, comprising edge service authorization, service access authorization, and mutual authentication between edge servers and edge devices. In dong so, E-DAC first extends a key-aggregate cryptosystem to enable batch service authorization, in which a service provider can aggregate the authorization keys of different services to produce a constant-size aggregate key for an edge server. Second, E-DAC enables users to acquire authorization from the service provider for service access on edge servers by using efficient secret sharing. Third, edge servers and users can authenticate with each other without interacting with a centralized server, while enabling secure zero-round trip communication, so that the service data is protected and the communication bandwidth cost is low. In addition, the service provider is capable of efficiently revoking the authorization of the dropout or compromised edge servers or users in response to the dynamics of the PEC environment. Finally, we prove the security of service access control in E-DAC, including unforgeability of service authorization and confidentiality of service data, and conduct extensive analysis and experiments to demonstrate that E-DAC is highly computational and communication-efficient on service authorization, authentication, and revocation.

Multi-agent reinforcement learning (MARL) has become a fundamental component of next-generation wireless communication systems. Theoretically, although MARL has the advantages of low computational complexity and fast convergence rate, there exist several challenges including partial observability, non-stationary, and scalability. In this article, we investigate a novel MARL with graph neural network-aided communication (GNNComm- MARL) to address the aforementioned challenges by making use of graph attention networks to effectively sample neighborhoods and selectively aggregate messages. Furthermore, we thoroughly study the architecture of GNNComm-MARL and present a systematic design solution. We then present the typical applications of GNNComm-MARL from two aspects: resource allocation and mobility management. The results obtained reveal that GNNComm-MARL can achieve better performance with lower communication overhead compared to conventional communication schemes. Finally, several important research directions regarding GNNComm-MARL are presented to facilitate further investigation.