Acquiring synthetic aperture radar (SAR) images is inherently difficult and laborious. To mitigate this data scarcity, generative models for SAR images aim to learn underlying data distributions from large-scale datasets, ensuring robust performance. Generative models mitigate data scarcity but rely on centralized frameworks, posing privacy risks and limiting deployment in Internet of Things (IoT) scenarios. To tackle the aforementioned challenges, we introduce an innovative federated angle-aware generative diffusion (FAGD) framework for secure SAR image generation. This framework integrates three key innovations: federated learning (FL), the angle-aware generative diffusion (AAGDiff) model, and the local data knowledge distillation (LDKD) strategy. Specifically, we introduce the FL framework, which enables clients to collaboratively train a generative model by transmitting model weights, thereby eliminating raw data exchange and enhancing security. We then propose the AAGDiff model for client-side high-quality generation, leveraging denoising diffusion probabilistic models (DDPMs) to synthesize high-quality SAR images from noise using an angle-conditioned encoder, enabling the generation of SAR images at different target azimuth angles. Additionally, the LDKD strategy alleviates overfitting during federated training under Non-Independent and Non-Identically Distributed (non-IID) data distributions by allowing the model to distill knowledge primarily from less frequent classes, thus enhancing generalization and robustness. Evaluated extensively on MSTAR and OpenSARShip datasets, the proposed framework ensures secure SAR image generation while achieving superior target recognition performance. Overall, the FAGD framework offers an effective and scalable solution for privacy-preserving SAR image synthesis.

Driven by the escalating demand for extensive coverage and ultra-reliable communication in the Internet of Vehicles (IoV), conventional single-transmission technologies frequently encounter a severe ”bottleneck effect” in long-distance and heavily obstructed environments. To break through this limitation, this paper investigates a Reconfigurable Intelligent Surface (RIS)-assisted cascaded amplify-and-forward (AF) and decode-andforward (DF) relay system over independent and identically distributed (i.i.d.) Nakagami-mfading channels. The proposed architecture innovatively exploits the synergistic advantages of cascaded active relays (providing initial power amplification via AF and terminal signal regeneration via DF) alongside the ”passive array gains” from the RIS, thereby effectively overcoming the severe ”double path loss” inherent in passive links while suppressing accumulated noise. Addressing the challenges of prohibitive pilot overhead and latency associated with acquiring instantaneous channel state information (CSI) in highly dynamic IoV environments, we propose a statistical CSI-based adaptive power allocation algorithm utilizing particle swarm optimization (PSO). By jointly optimizing the transmit power allocation among the source node, the AF relay, and the DF relay, the proposed algorithm efficiently tackles the intricate non-convex optimization problem subject to a total power constraint. Theoretically, we derive exact closed-form expressions for the system outage probability (OP) and average channel capacity, establishing a rigorous theoretical evaluation framework. Extensive simulation results not only validate the accuracy of the theoretical analysis but also demonstrate that the proposed PSO strategy effectively exploits spatial diversity gains and RIS passive beamforming gains. The findings reveal that the scheme significantly enhances transmission reliability and system robustness in complex propagation environments, substantiating its application potential for Intelligent Transportation Systems (ITS).

Distributed Graph Neural Network (DGNN) is a powerful tool in large-scale graph representation learning. However, high data-transfer overhead among workers in a DGNN training job confines its scalability and thus the overall performance. Vertex-wise historical embedding methods have demonstrated high potential to alleviate the problems, but still suffer from severe accuracy loss and limited performance scalability, which has been attributed to the information loss of critical channels in historical vertices and redundant information in local channels. This article explores the optimization of channel level and construct a quantitative accuracy model for channel-wise historical embedding. We propose Sift, a novel DGNN training framework, supporting channel-wise partial historical embedding with accuracy guarantee. Sift has three components: a historical embedding evaluator with channel-wise quantitative accuracy model, a sawtooth-like matrix rearrangement for accelerating message passing, and a hybrid parallel framework for overlapping communication overhead. Comprehensive experimental results show that Sift achieves near-linear parallel convergence speedup, outperforming the state-of-the-art baselines by up to 72% in total training performance and up to 21% in convergence speed.

Federated Learning (FL) is widely used in mobile computing as a communication-efficient distributed machine learning (ML) paradigm; however, it faces challenges such as model convergence to local optima or slow convergence due to the heterogeneity of client data. To mitigate data heterogeneity, the Nesterov Accelerated Gradient (NAG) method demonstrates its effectiveness by predictively updating the gradient to improve system performance. However, the performance of NAG depends heavily on the choice of decay coefficients; larger coefficients have greater acceleration but may lead to an unstable convergence process due to their unreasonable prediction of the descent gradient. To solve the above problems, this paper proposes the first radical heavy ball (RHB) method that combines momentum and NAG. In Stochastic Gradient Descent (SGD), momentum stabilizes the gradient descent process by integrating the historical gradients to update the parameters, and the RHB strategy decouples a single decay coefficient into an NAG component and a momentum component. The RHB introduces a gradient recall after each gradient acceleration by the NAG to strengthen the NAG's perception of the historical gradients, thus stabilizing the gradient descent process. By weighing the historical gradients and the predicted gradient, RHB effectively mitigates the instability of NAG convergence and demonstrates better performance. As a result, the algorithm further mitigates the impact of customer data heterogeneity in FL and can effectively deliver global update information to participants without additional communication costs. We conduct comprehensive experiments in a binary function, single node, and federated model environment to analyze the convergence properties in non-convex loss functions. RHB exhibits better performance and less computational overhead than many existing algorithms.

In this paper, we pay our attention towards secure and robust communication in the presence of a Reconfigurable Intelligent Surface (RIS)-enhanced mobile eavesdropping attacker in Multiple-Input Multiple-Output (MIMO) wireless networks. Specifically, we first provide a unifying framework that generalizes specific intelligent wiretap model wherein the passive eavesdropper configured with any number of antennas is potentially mobile and can actively optimize its received signal strength with the help of RIS by intelligently manipulating wiretap channel characteristics. To effectively mitigate this intractable threat, we then propose a novel and lightweight secure communication scheme from the perspective of information theory. The main idea is that the data processing can in some cases be observed as communication channel, and a random bit-flipping scheme is then carefully involved for the legitimate transmitter to minimize the mutual information between the secret message and the passive eavesdropper’s received data. The Singular Value Decomposition (SVD)-based precoding strategy is also implemented to optimize power allocation, and thus ensure that the legitimate receiver is not subject to interference from this random bit-flipping. The corresponding results depict that our secure communication scheme is practically desired, which does not require any a prior knowledge of the eavesdropper’s full instantaneous Channel State Information (ICSI). Perfect acquisition of ICSI is clearly always not affordable, which is further exacerbated by the RIS involved and the potential mobility of the passive eavesdropper that leads to unavoidable fast fading channels. Furthermore, we consider the RIS optimization problem from the eavesdropper’s perspective, and provide RIS phase shift design solutions under different attacking scenarios. Finally, the optimal detection schemes respectively for the legitimate user and the eavesdropper are provided, and comprehensive simulations are presented to verify our theoretical analysis and show the effectiveness and robustness of our secure communication scheme across a wide range of attacking scenarios.

Sand dust weather has adverse effects on image quality, making single-image sand dust removal a classic research topic in the field of image restoration. However, existing learning-based image restoration methods fail to account for uncertainties in both data and model dimensions, thus being unable to produce satisfactory results for sand dust image restoration. To address this challenge, we introduce a novel framework called the Uncertainty-aware SAM-aided Prompt-interaction Network (USPNet). USPNet comprises two key modules: the Uncertainty-aware SAM Priors Module (USPM), which addresses data-wise aleatoric uncertainties, and the Uncertainty-aware Prompt Learning Module (UPLM), which tackles model-wise epistemic uncertainties. By integrating data-wise and model-wise uncertainty learning, USPNet leverages uncertainty modeling through SAM semantic priors and distributionally representative prompts. Recognizing the unexplored uncertainties inherent in the learning process, we propose an Uncertainty-aware Perceptual Loss (UPL) to enhance the visual quality of restored images through perceptual learning. Through comprehensive perceptual studies and analysis of real sand-dust images, we propose a dataset named SanddustClearity. SanddustClearity includes daytime, nighttime synthetic, and real-world sand dust images. Our extensive experiments, conducted on both synthetic and real-world images exhibiting various levels of sand dust degradation, confirm the effectiveness and robustness of our proposed method. Our code will be available at https://github.com/WBC-ML/USPNet.

Federated Learning (FL) has been extensively applied in urban environmental prediction tasks of mobile edge computing by training a global machine learning model without data sharing. However, the training of FL faces the challenges such as the poor generalization capability of a single global model over heterogeneous data and hefty communication overhead caused by the frequent model exchange between massive edge servers and remote cloud servers. To address such issues, we propose HPFL-CN, a novel communication-efficient Hierarchical Personalized Federated edge Learning framework with Complex Network clustering. HPFL-CN introduces Privacy-preserving Feature Clustering (PFC) to extract privacy-preserving low-dimensional feature representations of each edge server via mapping the environmental data to different complex network domains for clustering similar edge servers accurately. Based on the clustering results of PFC, anedge-mediator-cloudhierarchical architecture is proposed to realize personalization at the cluster level by Effective Hierarchical Scheduling (EHS). Furthermore, to adapt to dynamic scenarios of new edge servers joining and streaming data generation, we further extend HPFL-CN to Adaptive personalized federated learning with dynamic grouping (Ada-HPFL-CN), which can flexibly re-group edge servers and adjust mixed model weights and the model aggregation frequency adaptively. Our extensive experiments on real-world datasets demonstrate the efficacy of our framework, which outperforms state-of-the-art FL methods regarding personalization and communication efficiency performance.

Federated Learning (FL) is a promising machine learning paradigm to train a global model from multiple clients while ensuring privacy. A key challenge in FL is the data heterogeneity that impairs the generalization of the single global model on each client. As a prevalent solution, the existing personalized FL primarily concentrates on the client-level personalization process, which may pose an overfitting problem since the local data of a single device is usually limited. Additionally, these methods lack the cognitive ability for collaborative learning among similar clients, which also restricts the performance of personalized models. To address this, we propose CFPA, a novel communication-efficient, and computation-efficient Cognitive Federated Partial Adaptation framework to boost personalization performance via the Soft-grouping Weighted Aggregation (SWA) strategy. Specifically, CFPA decouples the model into the body and the head and requires clients collaboratively train a well-performing federated pre-personalized model. Then, CFPA leverages the distribution knowledge extracted from the output feature maps of the convolutional layers in the federated pre-personalized model to identify the similarity among clients efficiently. Guided by the similarity matrix, CFPA further performs weighted federated adaption on the head of each local model, ultimately generating a personalized local model for each client. Comprehensive experiments on three benchmark datasets with various heterogeneous settings demonstrate that CFPA outperforms other state-of-the-art FL approaches.

Sparse mobile crowdsensing (Sparse MCS) is an emerging paradigm for urban-scale sensing applications, which recruits suitable participants to complete sensing tasks in only a few selected cells and then infers data of unsensed cells for saving sensing costs and obtaining high-quality sensing maps. In Sparse MCS, one crucial issue is task assignment, in which the platform selects cells whose sensing data can reduce inferred sensing maps errors (i.e., cell selection) and recruits the participant set with the maximum contribution for performing tasks (i.e., participant recruitment). The research on participant recruitment mainly focuses on single participatory-based or single opportunistic-based sensing mode. Due to the complementarity of two sensing modes, recruiting participants by only one sensing mode would result in wasting sensing resources and compromising the quality of task completion. Thus, combining the advantages of two sensing modes, we propose a task assignment framework based on hybrid sensing modes in Sparse MCS (HSM-SMCS) for achieving a good tradeoff between sensing quality and cost. Specifically, we propose a heuristic two-stage search strategy that simultaneously recruits opportunistic and participatory participants to perform tasks in significant cells within the constraint of total costs, considering their contributions to sensing map inference. Thereinto, for opportunistic participants, mobility prediction greatly affects task assignment effectiveness. However, existing prediction algorithms lead to unsatisfactory outcomes when the historical trajectory data of opportunistic participants are scarce. To effectively improve the predictive accuracy, we design a mobility prediction model based on transfer learning. The experimental evaluation on real trajectory data sets and sensor data sets of corresponding areas demonstrates that our framework outperforms state-of-the-art methods with higher quality reconstructed sensing maps.

Federated Learning (FL), a promising privacy-preserving distributed learning paradigm, has been extensively applied in urban environmental prediction tasks of Mobile Edge Computing (MEC) by training a global machine learning model without data sharing. However, it is hard for the shared global model to be well generalized among local edge servers, due to the statistical data heterogeneity, especially in real-world urban environmental data. Besides, the existing FL approaches may result in excessive communication and computation overhead due to the frequent transmission and aggregation of model parameters between massive edge servers and remote cloud servers. To address the above issues, we propose HPFL-CN, a novel communication-efficient Hierarchical Personalized Federated edge Learning framework via Complex Network feature clustering, aiming to cluster edge servers with similar environmental data distributions and then high-efficiently train personalized models for each cluster via hierarchical architecture. Specifically, HPFL-CN introduces Privacy-preserving Feature Clustering (PFC) to extract privacy-preserving low-dimensional feature representations of each edge server via mapping the environmental data to different complex network domains for clustering similar edge servers accurately. According to the clustering results of PFC, HPFL-CN further introduces an edge-mediator-cloud architecture for hierarchical model aggregation by Effective Hierarchical Scheduling (EHS), in which every mediator coordinates the training of edge servers within each cluster and periodically uploads model to cloud server for global model aggregation. Meanwhile, each mediator server would find a trade-off between cloud and edge models to realize personalization within clusters. Our extensive experiments on real-world datasets demonstrate the effectiveness and generalization of HPFL-CN, which outperforms other state-of-the-art FL methods regarding personalization performance and communication efficiency.