As new applications evolve rapidly, wireless networks increasingly require low-delay communication to significantly enhance the quality of user experience. In response, the evolution of the medium access control (MAC) layer has gained more attention, particularly through the application of reinforcement learning to optimize access strategies. In order to meet the low-delay requirements, we propose a reinforcement learning-based MAC protocol, named soft actor-critic multiple access (SAC-MA). To mitigate frequent collisions caused by the exploratory behavior, we propose a multiple waiting actions mechanism that allows stations to wait for multiple time slots. This mechanism enables the agent to develop a more flexible and intelligent access strategy, thereby effectively reducing delay. Additionally, we introduce an innovative formulation in which the head-of-line packet is treated as the agent, enabling more timely feedback and observations. We conduct extensive simulations to demonstrate that SAC-MA: 1) reduces delay by approximately 27.9% and 56.5% compared to the conventional MAC protocol with standard parameters under the collision and capture models, respectively; 2) adapts to environmental changes in dynamic scenarios; 3) coexists harmoniously with legacy stations and reduces the network delay in heterogeneous scenarios. Finally, we perform ablation studies to evaluate the effectiveness of the proposed mechanisms.

Simultaneous wireless information and power transfer (SWIPT) has emerged as a cornerstone technology for sustainable connectivity in sixth-generation (6G) space–air–ground integrated networks (SAGIN). This paper proposes a unified signal design framework that jointly supports radio-frequency (RF) coherent reception and noncoherent energy detection with colocated or separated deployments of information/energy receivers (IR/ER), thereby bridging RF and intensity-modulation/direct-detection (IM/DD) optical links. Guided by reliability, spectral efficiency, and harvested power metrics, we develop a generalized signal design framework based on a refined sphere-packing aimed at constructing high-dimensional symbols across space-time-frequency resources subject to symbol-level wireless power transfer constraints and an average power budget. The resulting nonconvex quadratically constrained quadratic program (QCQP) is efficiently solved using an alternating semidefinite programming–linear programming (ASDP–LP) method and an augmented Lagrangian dual-ascent (ALDA) algorithm. Analytical and simulation results confirm that the proposed approach achieves significant gains in communication-power trade-offs compared with conventional schemes, providing a foundation for sustainable RF–optical SWIPT in future 6G integrated networks.

The emergence of new intelligent applications has fostered the development of a task-oriented communication paradigm, where a comprehensive, universal, and practical metric is crucial for unleashing the potential of this paradigm. To this end, we introduce an innovative metric, the Task-oriented Age of Information (TAoI), to measure whether the content of information is relevant to the system task, thereby assisting the system in efficiently completing designated tasks. We apply TAoI to a wireless monitoring system tasked with identifying targets and transmitting their images for subsequent analysis. To minimize TAoI and determine the optimal transmission policy, we formulate the dynamic transmission problem as a Semi-Markov Decision Process (SMDP) and transform it into an equivalent Markov Decision Process (MDP). Our analysis demonstrates that the optimal policy is threshold-based with respect to TAoI. Building on this, we propose a low-complexity relative value iteration algorithm tailored to this threshold structure to derive the optimal transmission policy. Additionally, we introduce a simpler single-threshold policy, which, despite a slight performance degradation, offers faster convergence. Comprehensive experiments and simulations validate the superior performance of our optimal transmission policy compared to two established baseline approaches.

This paper focuses on spectrum sharing in heterogeneous wireless networks, where nodes with different Media Access Control (MAC) protocols to transmit data packets to a common access point over a shared wireless channel. While previous studies have proposed Deep Reinforcement Learning (DRL)-based multiple access protocols tailored to specific scenarios, these approaches are limited by their inability to generalize across diverse environments, often requiring time-consuming retraining. To address this issue, we introduce Generalizable Multiple Access (GMA), a novel Meta-Reinforcement Learning (meta-RL)-based MAC protocol designed for rapid adaptation across heterogeneous network environments. GMA leverages a context-based meta-RL approach with Mixture of Experts (MoE) to improve representation learning, enhancing latent information extraction. By learning a meta-policy during training, GMA enables fast adaptation to different and previously unknown environments, without prior knowledge of the specific MAC protocols in use. Simulation results demonstrate that, although the GMA protocol experiences a slight performance drop compared to baseline methods in training environments, it achieves faster convergence and higher performance in new, unseen environments.

Semantic communication (SemCom), as a novel paradigm for future communication systems, has recently attracted much attention due to its superiority in communication efficiency. However, similar to traditional communication, it also suffers from eavesdropping threats. Intelligent eavesdroppers could launch advanced semantic analysis techniques to infer secret semantic information. Therefore, some researchers have designed Semantic Steganography Communication (SemSteCom) schemes to confuse semantic eavesdroppers. However, the state-of-the-art SemSteCom schemes for image transmission rely on the pre-selected cover image, which limits the generalization. To address this issue, we propose a Generative Diffusion Model-based Coverless Semantic Steganography Communication (SemSteDiff) scheme to hide secret images into generated stego images. The semantic related private and public keys enable legitimate receiver to decode secret images correctly while the eavesdropper without the completely correct key-pairs fail to obtain them. Simulation results demonstrate the effectiveness of the plug-and-play design in different Joint Source-Channel Coding (JSCC) frameworks. Results under different eavesdropping settings show that, when Signal-to-Noise Ratio (SNR) = 0 dB, the peak signal-to-noise ratio (PSNR) of the legitimate receiver is 4.14 dB higher than that of the eavesdropper.

Digital task-oriented semantic communication (ToSC) aims to transmit only task-relevant information, significantly reducing communication overhead. Existing ToSC methods typically rely on learned codebooks to encode semantic features and map them to constellation symbols. However, these codebooks are often sparsely activated, resulting in low spectral efficiency and underutilization of channel capacity. This highlights a key challenge: how to design a codebook that not only supports task-specific inference but also approaches the theoretical limits of channel capacity. To address this challenge, we construct a spectral efficiency-aware codebook design framework that explicitly incorporates the codebook activation probability into the optimization process. Beyond maximizing task performance, we introduce the Wasserstein (WS) distance as a regularization metric to minimize the gap between the learned activation distribution and the optimal channel input distribution. Furthermore, we reinterpret WS theory from a generative perspective to align with the semantic nature of ToSC. Combining the above two aspects, we propose a WS-based adaptive hybrid distribution scheme, termed WS-DC, which learns compact, task-driven and channel-aware latent representations. Experimental results demonstrate that WS-DC not only outperforms existing approaches in inference accuracy but also significantly improves codebook efficiency, offering a promising direction toward capacity-approaching semantic communication systems.

Federated Learning (FL) on low earth orbit (LEO) satellites represents a promising frontier for on-orbit edge intelligence. However, the inherent network dynamics and heterogeneity of datasets and resource across satellites pose challenges to efficient on-orbit FL. In this work, we model client selection and inter-satellite routing as a joint optimization problem. We derive and minimize an upper bound of the global empirical loss as the objective function, to enable fast convergence. We model the constraints of inter-satellite routing via time-varying graphs and network flow theory. We propose both exact and approximate solutions for the joint optimization problem. In addition, we formalize and prove the convergence property of our approach. Last, by simulation we demonstrate the efficiency and superiority of the proposed scheme for realistic satellite networking scenarios.

The rapid scalability of large language models (LLMs) has driven significant advancements across various natural language processing tasks. However, the immense size of LLMs and the growing demand for large-scale datasets present challenges in fine-tuning these models in resource-constrained environments. Federated learning (FL) has emerged as a promising solution, enabling collaborative model fine-tuning on distributed private data without requiring data sharing. Despite its potential, the heavy computational and communication burdens imposed by LLMs hinder the widespread adoption of FL-based fine-tuning. To mitigate these challenges, we propose FedSIT (Federated Split Importance-Based Tuning), a novel federated fine-tuning framework designed to optimize LLM training in environments with limited computational resources. FedSIT splits the pre-trained model into Bottom, Trunk, and Top layers, offloading the computationally intensive Trunk layer to the server while distributing the Bottom and Top layers to client devices. Additionally, FedSIT leverages layer importance scores to selectively fine-tune the most critical layers, reducing the number of parameters to be fine-tuned. Our extensive experiments demonstrate that FedSIT achieves comparable performance to existing methods while significantly reducing resource requirements, offering an efficient and scalable solution for federated fine-tuning of LLMs in real-world settings.

This work explores the data-driven online tracking control problem for linear dynamic systems across multiple-input multiple-output (MIMO) fading channels. Initially, we address the optimal tracking control for a system with known plant dynamics, and design an innovative stochastic-approximation (SA)-based data-driven algorithm that leverage the instantaneous wireless channel state information (CSI). Subsequently, we extend this approach to accommodate unknown plant dynamics by proposing a novel normalized-stochastic-gradient-descent (NSGD)-based algorithm. This algorithm facilitates simultaneous system identification and control in an online setting using the real-time plant state as well as the CSI. Through Lyapunov drift analysis, we establish the asymptotic optimality of our proposed data-driven algorithms. Numerical results and analysis further demonstrate notable performance improvements compared to several leading learning techniques.

Federated learning (FL) emerges as a potential solution for enabling multiple terminal devices to collaboratively accomplish computational tasks within an autonomous aerial vehicle (AAV) swarm. However, traditional FL approaches, predicated on synchronous data aggregation, are not feasible for a AAV swarm owing to the inherently variable and dynamic nature of their communication networks compared with terrestrial systems. Furthermore, the data procured by AAVs is often highly heterogeneous, attributable to disparities in deployment environments and device attributes. Considering the distinct flight paths and unique operational conditions encountered by different AAVs, a considerable amount of data remains unlabeled. To tackle the challenges associated with asynchronous operations and the prevalence of unlabeled data, we introduce a novel framework termed semi-synchronous FL with cross-sharpness and layer-freezing (SFedXL), tailored for a AAV swarm. In particular, we devise a cross-sharpness model training strategy aimed at optimizing the utilization of both labeled and unlabeled datasets. Additionally, we propose an innovative semi-synchronous model aggregation protocol, complemented by client-specific layer-freezing and client cluster scheduling, designed to expedite the training process. Our simulation results indicate that the proposed algorithm surpasses current FL methods in terms of object recognition accuracy and communication efficiency, albeit with a tradeoff of increased local computation latency.

Federated Learning (FL) stands as a privacy-preserving machine learning paradigm that enables collaborative training of a global model across multiple clients. However, the practical implementation of FL models often confronts challenges arising from data heterogeneity and limited communication resources. To address the aforementioned issues simultaneously, we develop a Sparsified Random Partial Update framework for personalized Federated Learning (SRP-pFed), which builds upon the foundation of dynamic partial model updates. Specifically, we decouple the local model into personal and shared parts to achieve personalization. For each client, the ratio of its personal part associated with the local model, referred to as the update rate, is regularly renewed over the training procedure via a random walk process endowed with reinforced memory. In each global iteration, clients are clustered into different groups where the ones in the same group share a common update rate. Benefiting from such design,SRP-pFedrealizes model personalization while substantially reducing communication costs in the uplink transmissions. We conduct extensive experiments on various training tasks with diverse heterogeneous data settings. The results demonstrate that theSRP-pFedconsistently outperforms the state-of-the-art methods in test accuracy and communication efficiency.

Recommendation system (RS) is an important information filtering tool in nowadays digital era. With the growing concern on privacy, deploying RSs in a federated learning (FL) manner emerges as a promising solution, which can train a high-quality model on the premise that the server does not directly access sensitive user data. Nevertheless, some malicious clients can deduce user data by analyzing the uploaded model parameters. Even worse, some Byzantine clients can also send contaminated data to the server, causing blockage or failure of model convergence. In addition, most existing researches on federated recommendation algorithms only focus on unimodality learning, ignoring the assistance of multiple modality data to promote recommendation accuracy. Therefore, this article designs an FL-based privacy-preserving multimodal RS framework. To distinguish various modality data, an attention mechanism is introduced, wherein different weight ratios are assigned to various modal features. To further strengthen the privacy, local differential privacy (LDP) and personalized FL strategies are designed to identify malicious clients and bolster the resilience against Byzantine attacks. Finally, two multimodal datasets are established to verify the effectiveness of the proposed algorithm. The superiority of our proposed techniques is confirmed by the simulation results.

The problem of resource-efficient beam alignment is a long standing one within massive MIMO (mMIMO) enabled wireless communication networks. In D2D networks, the beam alignment problem is repeated for every new pair that appears and wishes to communicate, leading to a seemingly unbounded resource expenditure as the network grows dense. In this paper, we develop a new approach that uses the implicit geometric structure of such networks to break the spell. Instead of combatting it, our method exploits densification to facilitate alignment with minimal resources. As far as we know, we are the first to address the beam alignment problem in mMIMO D2D networks, as most previous research has concentrated on single point-to-point or single base station to multiple users scenarios. Assuming a static (or slow varying) network, the intuition behind our approach is to utilize the beam alignment solutions at prior device pairs to predict optimal alignment in future pairs at independent new locations. We show the equivalence between this problem and a non-linear matrix completion (MC) problem under some sparsity condition. To solve it, we design an MC technique based on attention-based graph neural network (GNN) which proves effective to predict optimal beam pairs with little side-information.

Federated Learning (FL) is envisioned as the cornerstone of the next-generation mobile system, whereby integrating FL into the network edge elements (i.e., user terminals and edge/cloud servers), it is expected to unleash the potential of network intelligence by learning from the massive amount of users' data while concurrently preserving privacy. In this paper, we develop an analytical framework that quantifies the interplay of user mobility, a fundamental property of mobile networks, and data heterogeneity, the salient feature of FL, on the model training efficiency. Specifically, we derive the convergence rate of a hierarchical FL system operated in a mobile network, showing how user mobility exacerbates the divergence caused by data heterogeneity. The theoretical findings are corroborated by experimental simulations.

Recommendation algorithm can effectively reduce the difficulty of proactive edge caching prediction by excavating users’ preferences among the massive contents, which has drawn great attentions from both academia and industry. The effectiveness of prediction models depends on big data analysis of user information, however, traditional methods based on centralized learning become more and more impractical due to the growing concern on privacy data protection. Recently, implementing the recommendation algorithm in a federated learning (FL) manner has emerged as a promising approach. In an FL manner, users are allowed to keep their private data local and upload the model parameters learned by local training to the server for collaborative training. In this work, we propose a proactive caching prediction algorithm for mobile vehicle users based on differential privacy and federate learning. Our proposed algorithm not only predicts the popular contents with a strong protection for users’ private data, but also applies to large-scale networks with massive mobile users. In addition, we also investigate the impact of user mobility on the caching prediction accuracy, and propose an attention-based model aggregation mechanism, which assigns different aggregation weights to each vehicle user and edge server to mitigate the performance degradation caused by user movement. The results show that our proposed model can obtain high caching prediction accuracy and strong privacy protection level in vehicular networks.

To reduce the delay and network congestion for content delivery in wireless networks, proactive caching scheme has attracted lots of attentions from both academia and industry. However, traditional caching prediction methods require to collect user data in a centralized server, which is becoming unreliable and impractical due to regulatory restrictions. To circumvent this issue, deploying caching prediction system in a federated learning (FL) fashion becomes a promising solution. However, there still exist privacy risks, and even worse, the FL is vulnerable to low-cost attacks. To solve this problem, a novel federated prediction system (FPS) is studied to provide high robustness and privacy. Firstly, to keep a balance between further enhancing privacy protection and alleviating the performance degradation caused by additional protection schemes, we propose an edge-assisted, robust and privacy-preserving FPS framework based on the local differential privacy (LDP) scheme. Secondly, to mitigate the impact of heterogeneous data, we add a regularization term to the local loss function. Furthermore, an attention-based aggregation scheme is proposed to defend against Byzantine attacks during the training process. Finally, the experiment results are provided to show the superiority of our proposed algorithm in terms of prediction accuracy and robustness.

Stream media content caching is a key enabling technology to promote the value chain of future urban vehicular networks. Nevertheless, the high mobility of vehicles, intermittency of information transmissions, high dynamics of user requests, limited caching capacities and extreme complexity of business scenarios pose an enormous challenge to content caching and distribution in vehicular networks. To tackle this problem, this paper aims to design a novel edge-computing-enabled hierarchical cooperative caching framework. Firstly, we profoundly analyze the spatio-temporal correlation between the historical vehicle trajectory of user requests and construct the system model to predict the vehicle trajectory and content popularity, which lays a foundation for mobility-aware content caching and dispatching. Meanwhile, we probe into privacy protection strategies to realize privacy-preserved prediction model. Furthermore, based on trajectory and popular content prediction results, content caching strategy is studied, and adaptive and dynamic resource management schemes are proposed for hierarchical cooperative caching networks. Finally, simulations are provided to verify the superiority of our proposed scheme and algorithms. It shows that the proposed algorithms effectively improve the performance of the considered system in terms of hit ratio and average delay, and narrow the gap to the optimal caching scheme comparing with the traditional schemes.

Federated learning is a new artificial intelligence technology with which an edge server can orchestrate with multiple end users to train a global model collaboratively. Under this setting, users only upload the locally trained parameters instead of their local data, substantially reducing communication costs and boosting data privacy. Nonetheless, federated learning mainly relies on users’ local training, overlooking the abundant computing resources owned by the edge server. To exploit the edge server’s processing power, we propose a hybrid learning paradigm that consists of centralized and federated learning components. This scheme uploads a portion of users’ data for centralized learning when the local model is trained under federated learning. We derive a theoretical upper bound for the model accuracy, which can be used to assess the performance of the proposed new learning paradigm. To balance the computation and communication resources for a good model accuracy performance, we establish a joint optimization problem of model accuracy, latency, and energy consumption. We also devise the corresponding joint optimization algorithm to solve the problem. Experiment results show that compared with centralized and federated learning, the proposed hybrid learning algorithm can effectively improve the model accuracy and significantly reduce computation and communication resources.

Personalized Federated Learning (PFL) is a new Federated Learning (FL) approach to address the heterogeneity issue of the datasets generated by distributed user equipments (UEs). However, most existing PFL implementations rely on synchronous training to ensure good convergence performances, which may lead to a serious straggler problem, where the training time is heavily prolonged by the slowest UE. To address this issue, we propose a semi-synchronous PFL algorithm, termed as Semi-Synchronous Personalized FederatedAveraging (PerFedS2), over mobile edge networks. By jointly optimizing the wireless bandwidth allocation and UE scheduling policy, it not only mitigates the straggler problem but also provides convergent training loss guarantees. We derive an upper bound of the convergence rate of PerFedS2 in terms of the number of participants per global round and the number of rounds. On this basis, the bandwidth allocation problem can be solved using analytical solutions and the UE scheduling policy can be obtained by a greedy algorithm. Experimental results verify the effectiveness of PerFedS2 in saving the training time as well as guaranteeing the convergence of training loss, in contrast to synchronous and asynchronous PFL algorithms.

To preserve participants' privacy, Federated Learning (FL) has been proposed to let participants collaboratively train a global model by sharing their training gradients instead of their raw data. However, several studies have shown that con-ventional FL is insufficient to protect privacy from adversaries, as even from gradients, useful information can still be recovered. To obtain stronger privacy protection, Differential Privacy (DP) has been proposed on the server's side and the clients' side. Although adding artificial noise to the raw data can enhance users' privacy, the accuracy performance of the FL is inevitably degraded. In addition, although the communication overhead caused by the FL is much smaller than that of centralized learning, it still becomes a bottleneck of the learning performance and utilization efficiency due to its frequent parameters exchange. To tackle these problems, we propose a new FL framework via applying DP both locally and centrally in order to strengthen the protection of par-ticipants' privacy. To improve the accuracy performance of the model, we also apply sparse gradients and Momentum Gradient Descent on the server's side and the clients' side. Moreover, using sparse gradients can reduce the total communication costs. We provide the experiments to evaluate our proposed framework and the results show that our framework not only outperforms other DP-based FL frameworks in terms of the model accuracy but also provides a more powerful privacy guarantee. Besides, our framework can save up to 90% of communication costs while achieving the best accuracy performance.

With the remarkable development of the 5G technologies, more and more real-time and complex computational tasks from the Internet-of-Things (IoT) systems can be fulfilled by 5G edge servers. While the ultradense deployment is required for 5G edge services, in the upcoming era of 6G with an even more limited communication range, it is almost impossible to achieve 6G service coverage with dense deployments. To address this fundamental limit, we propose EdgeGO, a mobile resource-sharing framework that employs mobile edge servers to provide a cost-effective deployment of 6G edge computing, which enables edge resource sharing for massive IoT devices. Unlike traditional mobile cloudlets, EdgeGO exploits the asynchronization between requests receiving and results returning to decouple the stringent delay and resource requirements for edge computing. As a result, the server moving and task processing could be paralleled. Besides, EdgeGO incorporates a two-layer iterative updating algorithm, which jointly optimizes path planning and task scheduling to improve the overall task efficiency. Extensive simulation results show that by careful managing mobility and task execution of the edge servers, EdgeGO is able to drastically increase the resource utilization by 166.67% and decrease the deployment cost of 6G edge computing by 25.58%.

Implementing federated learning (FL) algorithms in wireless networks has garnered a wide range of attention. However, few works have considered the impact of user mobility on the learning performance. To fill this research gap, we develop a theoretical model to characterize the hierarchical federated learning (HFL) algorithm in wireless networks where the mobile users may roam across edge access points (APs), leading to incompletion of inconsistent FL training. We provide the convergence analysis of conventional HFL with user mobility. Our analysis proves that the learning performance of conventional HFL deteriorates drastically with highly-mobile users. And such a decline in the learning performance will be exacerbated with small number of participants and large data distribution divergences among users’ local data. To circumvent these issues, we propose a mobility-aware cluster federated learning (MACFL) algorithm by redesigning the access mechanism, local update rule, and model aggregation scheme. We also conduct experiments to evaluate the learning performance of conventional HFL, a cluster federated learning (CFL) with simple averaging, and our proposed MACFL. The results show that our MACFL can enhance the learning performance, especially for three different cases: ($i$) the case of users with non-independent and identically distributed (non-IID) data, ($ii$) the case of users with high mobility, and ($iii$) the case with a small number of users.

Federated learning provides a promising paradigm to enable network edge intelligence in the future sixth generation (6G) systems. However, due to the high dynamics of wireless circumstances and user behavior, the collected training data is non-independent and identically distributed (non-IID), which causes severe performance degradation of federated learning. To solve this problem, federated learning with non-IID data in wireless networks is studied in this paper. Firstly, based on the derived upper bound of expected weight divergence, a federated averaging scheme is proposed to reduce the distribution divergence of non-IID data. Secondly, to further harmonize the distribution divergence, data sharing is associated with federated learning in wireless networks, and a joint optimization algorithm is designed to keep a sophisticated balance between the model accuracy and the cost. Finally, the simulation results based on a common-used image data set are provided to evaluate the performance of our proposed schemes, which can achieve significant performance gains with a small price of latency and energy consumption.

Recently, the implementation of federated learning (FL) in wireless networks becomes a hotspot due to its flexible collaborative learning methods and privacy-preserving benefits. However, most of the existing works overlook the impact of user mobility on the learning performance, which is critical. Specifically, the mobile users may roam among multiple edge access points (APs) during the local training procedures, leading to incompletion of inconsistent FL training. In this paper, we theoretically study the impact of user mobility on the FL in hierarchical wireless networks. In our system model, the network consists of one cloud server, several edge APs, and multiple mobile users that have their positions vary over time. During the local training process, users may stay in or move out of the coverage area of the originally attached edge AP. In such a practical context, we analyze the convergence rate of the FL algorithm and provide experiments to evaluate the learning performance under different network parameters. Our results provide insights in further improvements of FL in hierarchical wireless networks.

The combination of artificial intelligence and mobile edge computing (MEC) is considered as a promising evolution path of the future wireless networks. As a model-level coordination learning paradigm, federated learning can make full use of the distributed computation resource in the MEC systems, which allows the users to keep their private data locally. However, due to the unreliable wireless transmission circumstances and resource constraints in the MEC systems, both the performance and training efficiency of federated learning cannot be guaranteed. To solve this problem, the optimization design of federated learning in the MEC systems is studied in this paper. First, an optimization problem is formulated to manage the tradeoff between model accuracy and training cost. Second, a joint optimization algorithm is designed to optimize the model compression, sample selection, and user selection strategies, which can approach a stationary optimal solution in a computationally efficient way. Finally, the performance of our proposed optimization scheme is evaluated by numerical simulation and experiment results, which show that both the accuracy loss and the cost of federated learning in the MEC systems can be reduced significantly by employing our proposed algorithm.

Matrix completion with rating data and auxiliary information for users and items is a challenging task in recommendation systems. In this paper, we propose an end-to-end architecture named Attention-based Graph Convolutional Network (AGCN) to embed both rating data and auxiliary information in a unified space, and subsequently learn low-rank dense representations via graph convolutional networks and attention layers. Compared to previous work, AGCN reduces computational complexity with Chebyshev polynomial graph filters. The introduced attention layer, which encourages weighing the neighbor information to learn more expressive structural graph representations, can improve the prediction accuracy, and lead to faster and more stable convergence. Experimental results show that our model can perform better and converge faster than current state-of-the-art methods on the real-world MovieLens and Flixster datasets.

Full-duplex (FD) allows the exchange of data between nodes on the same temporal and spectrum resources, however, it introduces self interference (SI) and additional network interference compared to half-duplex (HD). Power control in the FD networks, which is seldom studied in the literature, is promising to mitigate the interference and improve the performance of the overall network. In this work, we investigate the random and deterministic power control strategies in the FD networks, namely, constant power control, uniform power control, fractional power control and ALOHA-like random on-off power control scheme. Based on the obtained coverage probabilities and their robust approximations, we show that power control provides remarkable gain in area spectrum efficiency (ASE) and energy efficiency (EE), and improves the fairness among the uplink (UL) and downlink (DL) transmissions with respect to the FD networks. Moreover, we evaluate the minimum SI cancellation capability to guarantee the performance of the cell-edge users in FD networks. Generally, power control is helpful to improve the performance of the transmission for long distance in the FD networks and reduce the requirement of SI cancellation capability.