Robust Federated Learning (RoFL) extends traditional federated learning, not only by enabling multiple clients to collaboratively train a shared model under the coordination of an edge server, but also by incorporating client-side defense mechanisms (e.g., adversarial training) to defend against adversarial attacks while preserving data privacy. However, recent studies have shown that RoFL also remains vulnerable to the challenges posed by non-independent and identically distributed (non-IID) data distributions across heterogeneous clients, which can degrade overall model generalization and robustness. To mitigate this challenge, in this paper, we propose a novel RoFL framework, called RoFLCCA, to address non-IID challenges while defending against adversarial attacks. In particular, we first introduce a local classifier calibration mechanism that utilizes feature-level augmentation to mitigate the effects of non-IID data. By incorporating global class-wise feature statistics, each client can adjust its classifier using synthetic features derived from these shared representations. Second, we propose a calibrated classifier-guided global adversarial alignment strategy, which enforces consistency between augmented and adversarial predictions to improve robustness. Simulation results demonstrate the effectiveness of the proposed RoFLCCA, which consistently outperforms existing robust federated baselines across different datasets and settings. On average, it achieves a 7.07% improvement in clean accuracy and a 4.71% gain in adversarial robustness, highlighting its ability to enhance both generalization and defense against adversarial threats.

This paper proposes an AI framework that leverages integrated sensing and communication (ISAC), aided by the age of sensing (AoS) to ensure the timely location updates of the users for a holographic MIMO (HMIMO)-assisted base station (BS)-enabled wireless network. The AI-driven framework aims to achieve optimized power allocation for efficient beamforming by activating the minimal number of grids from the HMIMO BS for serving the users. An optimization problem is formulated to maximize the sensing utility function, aiming to maximize the communication signal-to-interference-plus-noise ratio (SINRc) of the received signals and beam-pattern gains to improve the sensing SINR of reflected echo signals, which in turn maximizes the achievable rate of users. A novel AI-driven framework is presented to tackle the formulated NP-hard problem that divides it into two problems: a sensing problem and a power allocation problem. The sensing problem is solved by employing a variational autoencoder (VAE)-based mechanism that obtains the sensing information leveraging AoS, which is used for the location update. Subsequently, a deep deterministic policy gradient-based deep reinforcement learning scheme is devised to allocate the desired power by activating the required grids based on the sensing information achieved with the VAE-based mechanism. Simulation results demonstrate the superior performance of the proposed AI framework compared to advantage actor-critic and deep Q-network-based methods, achieving a cumulative average SINRcimprovement of 8.5 dB and 10.27 dB, and a cumulative average achievable rate improvement of 21.59 bps/Hz and 4.22 bps/Hz, respectively. Therefore, our proposed AI-driven framework guarantees efficient power allocation for holographic beamforming through ISAC schemes leveraging AoS.

The rapid evolution towards the sixth-generation (6G) networks demands advanced beamforming techniques to address challenges in dynamic, high-mobility scenarios, such as vehicular communications. Vision-based beam prediction utilizing RGB camera images emerges as a promising solution for accurate and responsive beam selection. However, reliance on visual data introduces unique vulnerabilities, particularly susceptibility to adversarial attacks, thus potentially compromising beam accuracy and overall network reliability. In this paper, we conduct the first systematic exploration of adversarial threats specifically targeting vision-based mmWave beam selection systems. Traditional white-box attacks are impractical in this context because ground-truth beam indices are inaccessible and spatial dynamics are complex. To address this, we propose a novel black-box adversarial attack strategy, termed Spatial Proxy Attack (SPA), which leverages spatial correlations between user positions and beam indices to craft effective perturbations without requiring access to model parameters or labels. To counteract these adversarial vulnerabilities, we formulate an optimization framework aimed at simultaneously enhancing beam selection accuracy under clean conditions and robustness against adversarial perturbations. We introduce a hybrid deep learning architecture integrated with a dedicated Feature Refinement Module (FRM), designed to systematically reshaping irrelevant, noisy and adversarially perturbed visual features. Evaluations using standard backbone models such as ResNet-50 and MobileNetV2 demonstrate that our proposed method significantly improves performance, achieving up to an +21.07% gain in Top-K accuracy under clean conditions and up to a +37.32% increase in Top-1 adversarial robustness compared to different baseline models.

The Open Radio Access Network (O-RAN) paradigm offers a compelling solution to the constraints of traditional RAN by establishing an open framework that enables data-driven optimization at the individual user level, which is essential for the evolution of the next-generation (NextG) cellular networks. Accurate predictions of CPU demand for each user's equipment (UE) in the O-Cloud at the next step will enable more efficient CPU resource optimization. While AI is promising to optimize CPU utilization, it encounters two significant challenges. First, the varying number of UEs leads to shifts in feature dimensions, rendering the model unable to accept these inputs since the input dimension of the AI model remains fixed. Second, the ongoing introduction of new types of UEs over time with distinct CPU demands and dynamic combinations of various active devices adds further variability, thereby complicating predictive accuracy. To address the first challenge, in this research, we propose a novel dynamic number of devices management (DNDM) framework that effectively accommodates a dynamic number of devices in O-RAN, addressing the challenges associated with variable UE demands in future NextG O-RAN. We formulate an optimization problem for the second challenge, enabling the model to learn new demand scenarios while preserving knowledge from previously encountered configurations. To solve the optimization, we propose an exemplar replaybased continual adaptation (CA) framework designed to operate within the near real-time RAN Intelligence Controller (RT-RIC). The CA-DNDM actively prevents catastrophic forgetting and delivers continuous adaptability, seamlessly handling evolving UE types and quantities. Through extensive experimental results, we demonstrate that the proposed CA-DNDM framework effectively handles scenarios with varying UE counts and reliably predicts CPU demand for new situations while preserving the knowledge gained from prior scenarios.

Deep Joint Source-Channel Coding (Deep-JSCC) has emerged as a promising semantic communication approach for wireless image transmission by jointly optimizing source and channel coding using deep learning techniques. However, traditional Deep-JSCC architectures employ fixed encoder-decoder structures, limiting their adaptability to varying device capabilities, real-time performance optimization, power constraints and channel conditions. To address these limitations, we propose DD-JSCC: Dynamic Deep Joint Source-Channel Coding for Semantic Communications, a novel encoder-decoder architecture designed for semantic communication systems. Unlike traditional Deep-JSCC models, DD-JSCC is flexible for dynamically adjusting its layer structures in real-time based on transmitter and receiver capabilities, power constraints, compression ratios, and current channel conditions. This adaptability is achieved through a hierarchical layer activation mechanism combined with implicit regularization via sequential randomized training, effectively reducing combinatorial complexity, preventing overfitting, and ensuring consistent feature representations across varying configurations. Simulation results demonstrate that DDJSCC enhances the performance of image reconstruction in semantic communications, achieving up to 2 dB improvement in Peak Signal-to-Noise Ratio (PSNR) over fixed Deep-JSCC architectures, while reducing training costs by over 40%. The proposed unified framework eliminates the need for multiple specialized models, significantly reducing training complexity and deployment overhead.

Low Earth orbit (LEO) satellites nowadays play a pivotal role in collecting images for the Earth observation. However, the images collected by satellites are possibly tremendous, which causes challenges in dealing with the satellite images. Those challenges include: 1) the unrealistic of transmitting those massive image data to the ground station for centralized analysis because of restricted satellite communication bandwidth and the data privacy issue, and 2) satellite data may be non-independent and identically distributed (non-IID). In this paper, we propose a prototype-guided federated knowledge distillation (Pro-FedKD) approach in an LEO Satellite-high altitude platform (HAP) system, which is designed based on self-knowledge distillation (SKD), federated prototype learning (FedProto) and federated learning (FL). Owing to the adoption of FL, the first challenge can be handled since FL does not require data to leave the local side. To cope with the second challenge, SKD and FedProto are employed. In addition, both model aggregation and prototype aggregation are employed on a pre-defined HAP. To enhance the effectiveness, a top-$N$model aggregation mechanism is proposed, in which among all models,$N$local models that can achieve the top$N$maximum accuracies over the validation dataset of the pre-defined HAP will be selected for aggregation. Experiments demonstrate the error rate gained by the proposed Pro-FedKD method is separately 3.76×, 3.17×, 1.55×, and 1.18× smaller than FedExP, MOON, FedProto, and pFedSD over the EuroSAT dataset, demonstrating a significant reduction. The proposed method also exhibits preeminence in other datasets.

Federated learning (FL) enables privacy-preserving model training across decentralized data. However, significant data heterogeneity, common in domains like the Internet of Things (IoT), hinders generalization. Federated Domain Generalization (FDG) extends the FL paradigm by aiming to train models that generalize effectively to unseen domains, without requiring access to data from those domains during training. Current FDG methods primarily use ResNet backbones pre-trained on ImageNet-1K, limiting adaptability due to architectural constraints and limited pre-training diversity. This reliance has created a gap in leveraging advanced architectures and diverse pre-training datasets to address these challenges. To bridge this gap, we present the first comprehensive investigation into the efficacy of advanced pre-trained architectures such as Vision Transformers, ConvNeXt, and Swin Transformers, in enhancing FDG performance. Unlike ResNet, these architectures capture global context and long-range dependencies, making them well-suited for FDG. Beyond architectural evaluation, we systematically assess the impact of diverse pre-training datasets and compare self-supervised and supervised strategies. Our analysis rigorously investigates the influence of architectural depth, parameter efficiency, and the interplay between diverse model families and dataset characteristics on FDG performance. We find that advanced architectures pre-trained on large datasets significantly outperform ResNet models. Specifically, ConvNeXt architectures outperform all other candidates. We find self-supervised methods using masked image patch reconstruction via discrete token prediction outperform their supervised counterparts. We observe that certain advanced model variants with fewer parameters outperform larger ResNet models. This underscores the need for advanced architectures and scalable pretraining to enable efficient and generalizable FDG.

Federated learning (FL) makes it possible to advance towards edge intelligence by enabling collaborative and privacy-preserving model training across distributed edge devices. One of the main challenges in FL is non-IID (not Independent and Identically Distributed) nature of data distribution across edge devices, which results in inconsistent update directions of local and global models, thus hindering model convergence. Moreover, recent studies have shown that FL models can significantly degrade performance under adversarial attacks, which further poses challenges for deployment at edge sides. In this work, we attempt to improve the robustness of FL model under adversarial attacks in non-IID settings by sharing knowledge between a central server and edge devices via knowledge distillation. Specifically, we propose a new knowledge distillation-based federated adversarial training (FAT) framework, termed FedAdv (Federated Adversarial), which involves an edge server collecting global prototypes by aggregating local prototypes obtained from participating devices after adversarial training (AT). These global prototypes are subsequently distributed to the edge devices for regularization. This regularization mechanism aims to encourage each device to align its local representation with the corresponding global prototype. By doing so, it helps prevent significant deviations of local model updates from the global model. Experimental results on MNIST and Fashion-MNIST show that our strategy yields comparable or superior performance gains in both natural and robust accuracy compared to several baselines.

The 6G wireless communication networks need an intelligent networking system to meet the ever-increasing de-mands of various applications and mobile devices to ensure power savings, energy efficiency (EE), high integration of devices, and mass connection. To achieve these aims, an artificial intelligence (AI)-based holographic MIMO (HMIMO)-aided cell-free (CF) network is suggested to allocate desired power for beamforming by activating the required number of grids from the serving HMIMOs for serving the users. An optimization problem is developed to ensure effective power allocation that maximizes the EE of the system. A Transformer-based AI framework is proposed to solve the formulated NP-hard problem that distributes desired power for serving the users by activating the required number of grids from the required number of serving HMIMOs in the CF network. Finally, simulation results represent that the proposed power allocation framework outperforms the gated recurrent unit and long short-term memory-based mechanisms, achieving a combined power savings of 12.5% and 4.06%, and a combined EE improvement of 14.68% and 8.93%, correspondingly. Therefore, our suggested AI-based framework guarantees effective power allocation for beamforming to serve the users.

Federated learning (FL) is a privacy-preserving distributed management framework based on collaborative model training of distributed devices in edge networks. However, recent studies have shown that FL is vulnerable to adversarial examples (AEs), leading to a significant drop in its performance. Meanwhile, the non-independent and identically distributed (non-IID) challenge of data distribution between edge devices can further degrade the performance of models. Consequently, both AEs and non-IID pose challenges to deploying robust learning models at the edge. In this work, we adopt the adversarial training (AT) framework to improve the robustness of FL models against adversarial example (AE) attacks, which can be termed as federated adversarial training (FAT). Moreover, we address the non-IID challenge by implementing a simple yet effective logits calibration strategy under the FAT framework, which can enhance the robustness of models when subjected to adversarial attacks. Specifically, we employ a direct strategy to adjust the logits output by assigning higher weights to classes with small samples during training. This approach effectively tackles the class imbalance in the training data, with the goal of mitigating biases between local and global models. Experimental results on three dataset benchmarks, MNIST, Fashion-MNIST, and CIFAR-10 show that our strategy achieves competitive results in natural and robust accuracy compared to several baselines.

The upcoming 6G wireless communication networks are anticipated to offer extensive mobile connectivity, faster data services with reduced power consumption, and seamless integration among different technologies for providing effective beamforming. To accomplish these aims, a transfer learning empowered AI framework is proposed to allocate the power for serving the users under the coverage areas of the corresponding holographic MIMOs (HMIMOs) by activating the required number of grids from the respective HMIMOs. An optimization problem is formulated with the goal of maximizing the utility function for achievable rate, which in turn maximizes the signal-to-interference-plus-noise ratio (SINR), and achievable rate of the users. The HMIMO that serves the highest number of users is considered as the parent HMIMO and the rest of the HMIMOs are regarded as the child HMIMOs. A Transformer-based AI framework is utilized for allocating the power to the users under the coverage areas of the parent HMIMO and transfers the knowledge of the trained model to the child HMIMOs which requires lower learning cost to allocate power to the corresponding users within the coverage areas of the child HMIMOs. Finally, simulation results show that the proposed AI framework empowered by transfer learning surpasses the baseline methods such as gated recurrent unit and long short-term memory, achieving power savings ranging from 28.14% to 38.92% and achievable rate enhancements from 16.58 bps/Hz to 16.84 bps/Hz.

The future cellular networks, known as Next Generation (NextG), are anticipated to employ infrastructure based on cloud computing, with programmable, virtualized, and disaggregated designs. The separation of control functions from physical infrastructure will be implemented, and the utilization of standardized interfaces will facilitate the establishment of tailored closed-control loops. The O-RAN (Open Radio Access Network) paradigm aims to resolve the issue of limited control over the RAN by proposing an open design framework that enables data-driven and intelligent optimization at the individual user level. The growing ubiquity of O-RAN networks has underscored the significance of network traffic categorization in effectively managing O-RAN networks and preserving cybersecurity. This article analyzes the O-RAN alliance’s disaggregated network architecture, focusing on its significant contribution to NextG networks. This paper proposes a novel approach to examine and assess traffic patterns inside the O-RAN architecture. The ongoing acquisition of knowledge regarding encrypted traffic is of utmost importance in light of the perpetual advancements in applications and the advent of encryption technologies. The ability to dynamically adjust in traffic analysis is crucial for effectively addressing the evolving network environment, specifically inside the O-RAN architecture. To address this, we propose a new method named Incremental O-RAN Traffic Categorization (IORTC), specially designed to categorize encrypted data within the O-RAN framework. The IORTC system manages the continuous collection of knowledge from encrypted traffic in the O-RAN framework. It is designed to adapt to the evolution of various encrypted traffic categories while retaining information about earlier encrypted traffic. Based on the experimental results, our method demonstrates a remarkable ability to assimilate new traffic patterns while managing the retention of previously acquired knowledge, and it performed well in all evaluation criteria with an average accuracy of 98%.

Wireless power transfer for charging electric vehicles (EVs) using the inductive charging mechanism enables EVs to recharge their batteries wirelessly while in motion or during halts at traffic signals. Additionally, resonant inductive charging (RIC) can wirelessly transfer energy with high efficiency and over longer distances. To achieve these objectives, we propose a RIC-enabled system for traffic signal scenarios capable of selecting EVs based on their required energy needs for travel and the remaining traffic signal time. We formulate an optimization problem that allows the selected EVs to maximize their battery energy during traffic signal halts, consequently optimizing the defined utility function. Given the dynamic nature of the problem, it falls under the category of NP-hard problems, and to address this, we propose a novel artificial intelligence framework. Our approach utilizes both the halt time and energy demand information, resulting in the development of the Traffic Signal-Aware Electric Vehicle Selection and Resource Allocation algorithm. We employ long short-term memory based deep learning model to predict battery energy needs and generate energy demand score information. The generated demand score, along with the remaining traffic signal time, serves as conditions for the final selection and allocation of charging resources to EVs. Finally, experimental results confirm the effectiveness of our proposed method, demonstrating superior performance compared to the deep neural network model. Furthermore, in terms of battery energy, our approach achieves a 55.1% increase compared to baseline-B and an 8.4% increase compared to baseline-C.

In the rapidly advancing landscape of 6G wireless communication, beamforming plays a crucial role especially with the utilization of millimeter-wave and terahertz frequency bands being pivotal for achieving ultra-high data rates. Despite their promise, these bands present a significant challenge due to the beam training overheads required for precise beamforming, particularly in high-mobility applications like intelligent transportation systems and emerging virtual reality platforms such as the metaverse. While initial deep learning models mitigates the beam training overheads, their performance is compromised due to sensitivity to environmental and lighting conditions, revealing a critical gap in robustness. To address this limitation, this paper proposed a semantic-based method specifically designed to enhance the robustness of beamforming. Utilizing the cutting-edge You Only Look Once version 8 (YOLOv8) algorithm, semantic data from RGB camera images has been extracted to significantly improve the system’s adaptability across a range of environmental conditions. Further, to complement the beam management a novel approach is proposed for the identification of target vehicle by employing K-means clustering in conjunction with the GPS data of the target vehicle. For maintaining the ultra reliable low latency communication (URLLC) a lightweight model has been used to predict the optimal beamforming index. The efficacy of our proposed model is empirically substantiated through rigorous experimental trials in real-world 6G environment, demonstrating significant improvements in average received power ranging from 6.49% to 38.27%, compared to the baselines.

Federated learning-assisted edge intelligence enables privacy protection in modern intelligent services. However, not independent and identically distributed (non-IID) distribution among edge clients can impair the local model performance. The existing single prototype-based strategy represents a class by using the mean of the feature space. However, feature spaces are usually not clustered, and a single prototype may not represent a class well. Motivated by this, this article proposes a multiprototype federated contrastive learning approach (MP-FedCL) which demonstrates the effectiveness of using a multiprototype strategy over a single-prototype under non-IID settings, including both label and feature skewness. Specifically, a multiprototype computation strategy based on k-means is first proposed to capture different embedding representations for each class space, using multiple prototypes$(k$centroids) to represent a class in the embedding space. In each global round, the computed multiple prototypes and their respective model parameters are sent to the edge server for aggregation into a global prototype pool, which is then sent back to all clients to guide their local training. Finally, local training for each client minimizes their own supervised learning tasks and learns from shared prototypes in the global prototype pool through supervised contrastive learning, which encourages them to learn knowledge related to their own class from others and reduces the absorption of unrelated knowledge in each global iteration. Experimental results on MNIST, Digit-5, Office-10, and DomainNet show that our method outperforms multiple baselines, with an average test accuracy improvement of about 4.6% and 10.4% under feature and label non-IID distributions, respectively.

Sixth-generation wireless networks are required to satisfy the ever-increasing demands of diverse applications to guarantee power savings, energy efficiency (EE), and mass connectivity. To accomplish these goals, in this article, an artificial intelligence (AI)-based holographic MIMO (HMIMO)-empowered cell-free (CF) network is proposed while leveraging integrated sensing and communication (ISAC). The proposed AI-based framework allocates the desired power for beamforming by activating the required number of grids from the serving HMIMO base stations (BSs) in the CF network to serve the users. An optimization problem is formulated that maximizes the sensing utility function, which in turn maximizes the signal-to-interference-plus-noise ratio (SINR) of the received signal, the sensing SINR of the reflected echo signal, and EE, ensuring efficient power allocation. To solve the optimization problem, an AI-based framework is proposed to enable a decomposition of the NP-hard problem into two subproblems: 1) a sensing subproblem and 2) a power allocation subproblem. Initially, a variational autoencoder (VAE)-based scheme is utilized to solve the sensing subproblem that identifies the current location of the users with the sensing information. Then, a transformer-based mechanism is devised to allocate the desired power to users by activating the required grids from the serving HMIMO BSs in the CF network based on the sensing information achieved with the VAE-based scheme. Simulation results demonstrate that the proposed AI-based framework outperforms the long short-term memory and gated recurrent unit-based mechanisms, with cumulative power savings of 8.64% and 16.02%, and cumulative EE of 14.49% and 16.61%, accordingly, considering the ground truth values.

The impending sixth-generation wireless communication networks are anticipated to guarantee mass connectivity, high integration, and lower power consumption for generating the required beamforming. To achieve these goals, an artificial intelligence (AI) framework is proposed by utilizing holographic MIMO-assisted integrated sensing, localization, and communication. The proposed AI framework ensures lower power consumption to activate the minimum number of grids from the holographic grid array for the generation of holographic beamforming. An optimization problem is formulated to maximize the signal-to-interference-plus-noise ratio received by the users, which in turn maximizes the utility function for sensing considering the user distances, beampattern gains, sensing-communication loss, and dense locations controlling parameter. A novel AI-based framework is proposed to solve the formulated NP-hard optimization problem by decomposing it into two subproblems: the sensing problem and the communication resource allocation problem. First, a variational autoencoder (VAE) based mechanism is devised to solve the sensing problem mitigating the disputes to obtain the users’ exact location. Second, a sequential neural network-based scheme is utilized to allocate the communication resources to the heterogeneous users for generating the desired beamforming based on the findings of the VAE-based mechanism. Moreover, an extreme case power allocation strategy is presented once a large number of users enter the system. The extreme case power allocation strategy applies when the total power prediction exceeds the total system power for allocating the communication resources to the users. Finally, simulation results validate that the proposed AI-based framework outperforms the long short-term memory method with a cumulative power savings of 34.02% taking the ground truth power into account. Therefore, the proposed AI framework generates effective beamforming to serve the communication users.

The future sixth-generation (6G) wireless communication networks are expected to provide massive connectivity with lower power requirements for generating the desired beamforming. Therefore, holographic MIMO assisted integrated sensing and communication framework is proposed that ensures lower power requirements to activate the minimum number of grids from the holographic grid array (HGA) for the effective beamforming. An optimization problem is formulated that maximizes the signal to noise-interference ratio (SNIR) of the users which in turn maximizes the utility function for sensing (UFS) considering the beampattern gains, distances, and sensing-communication loss. A novel artificial intelligence (AI) framework is proposed to solve the formulated problem which is a NP-hard problem. First, a variational autoencoder (VAE) based scheme is developed to solve the challenges of determining the exact location of the users and complete data distribution. Then, a sequential neural network-based mechanism is devised to allocate the communication resources to the heterogeneous users for the desired beamforming based on the results obtained from VAE. Finally, simulation results demonstrate that the proposed algorithms confirm 23% power savings compared to long short-term memory (LSTM) method to perform effective beamforming for serving the users.

Federated learning (FL) allows local clients to train a global model by cooperating with a server while ensuring that their raw data is not revealed. However, most existing works usually choose clients randomly, regardless of their capabilities and contributions to training. Additionally, FL client selection mechanisms concentrate on a significant challenge associated with system or statistical heterogeneity. This paper tries to manage both the system and statistical heterogeneity of distributed clients in the networks. First, to manage the system heterogeneity, an optimization objective is first proposed to maximize the number of clients with similar capabilities such as storage, computational, and communication capabilities. Then, a network framework with a logical layer is proposed to logically group similar clients by checking their capabilities. Finally, to manage the statistical heterogeneity among clients, a novel Contribution-based Dynamic Federated training strategy, called CDFed, is designed to dynamically adjust the probability of clients being chosen based on Shapley values in each global round. Experimental results on two baseline datasets: MNIST and FMNIST, demonstrate that our proposal has a faster convergence rate, about 50%, and a higher average test accuracy, at least 1%, than baselines in most cases.

Explainable artificial intelligence (XAI) twin systems will be a fundamental enabler of zero-touch network and service management (ZSM) for sixth-generation (6G) wireless networks. Thus, a reliable XAI twin system becomes essential to discretizing the physical behavior of the Internet of Everything (IoE) and identifying the reasons behind that behavior for enabling ZSM. To address the challenges of extensible, modular, and stateless management functions in ZSM, a novel neuro-symbolic XAI twin framework is proposed that to enable trustworthy ZSM for a wireless IoE. The proposed neuro-symbolic XAI twin framework consists of two learning systems: 1) implicit learner that acts as an unconscious learner in physical space and 2) explicit leaner that can exploit symbolic reasoning based on implicit learner decisions and prior evidence. The physical space of the XAI twin executes a neural-network-driven multivariate regression to capture the time-dependent wireless IoE environment while determining unconscious decisions of IoE service aggregation, such as uplink, downlink, and service provisioning. Subsequently, the virtual space of the XAI twin constructs a directed acyclic graph (DAG)-based Bayesian network that can infer a symbolic reasoning score over unconscious decisions through a first-order probabilistic language model. Furthermore, a Bayesian multiarm bandit-based learning problem is proposed for reducing the gap between the expected explained score and the current obtained score of the proposed neuro-symbolic XAI twin. Experimental results show that the proposed neuro-symbolic XAI twin can achieve around 96.26% accuracy while guaranteeing from 18% to 44% more trust score in terms of reasoning and closed-loop automation.