Satellite-terrestrial integrated network (STIN) has been recognized as a promising paradigm to provide ubiquitous and reliable coverage for billions of devices over the world. Integrated sensing and communication (ISAC) can achieve higher spectrum resource utilization efficiency, reduce the hardware size and lighten the payload of satellites for STIN. Multi-access mobile edge computing (MEC) leverages distributed edge servers to alleviate the computational burden for sensing data processing on the satellites. In this paper, we propose multi-access MEC empowered ISAC for STIN. Specifically, a group of low earth orbit (LEO) satellites perform radar sensing operations with optimized scheduling. While a portion of the acquired sensing data undergoes onboard processing at the satellites, the remaining part is processed remotely on multiple terrestrial edge servers. We formulate an optimization problem which concurrently optimizes the following strategy variables: the sensing scheduling, the beamforming for offloading transmission, the beamforming for radar sensing, the duration for sensing and data offloading, the offloaded workload and the computing capacity allocation of each edge server. Notwithstanding the non-convex nature of the formulated optimization problem, we develop a hierarchical decomposition algorithm for achieving the solution efficiently. Extensive numerical simulations confirm the superior performance of our proposed multi-access MEC-enabled ISAC framework in STIN scenarios while simultaneously verifying the efficiency of our optimization algorithm.

Cardiovascular disease (CVD) is one of the foremost causes of mortality globally, and cardiac arrhythmias constitute a major contributing factor. Continuous monitoring of cardiac signals plays a vital role for early detection and prevention. However, traditional electrocardiogram (ECG) devices require skin contact, which can be uncomfortable and inconvenient for long-term usage. In contrast, contactless cardiac health monitoring technologies, such as Wi-Fi and millimeter-wave (mmWave) radar, present a promising alternative. Millimete-rwave radar provides high range resolution, strong immunity to ambient light, and high sensitivity to small vibrations, making it ideal for contactless monitoring. However, mmWave radar primarily captures cardiac mechanical vibrations, known as radar cardiography (RCG) signals, which differ from the electrical activity recorded by clinical ECGs. To bridge this gap, we propose a contactless framework that uses mmWave radar and a conditional diffusion model to reconstruct ECG signals and then utilizes a deep learning model to classify arrhythmias. Specifically, mmWave radar captures RCG signals associated with cardiac activities. Leveraging the nonlinear relationship between cardiac mechanics and electrical activities, we design a Residual Network (ResNet)-based conditional diffusion model to convert these RCG signals into ECG signals. Finally, we develop a CNN-BiLSTM-SE network for arrhythmia classification. Experimental findings demonstrate the efficacy of the proposed approach for signal conversion as well as arrhythmia classification, offering a promising pathway toward contactless cardiac health monitoring.

Cross-view geo-localization is a crucial task with diverse applications, yet it remains challenging due to the significant variations in viewpoints and visual appearances between images from different perspectives. While recent advancements have been made, existing methods often suffer from high model complexity, excessive resource consumption, and the impact of sample learning difficulty on optimization. To overcome these limitations, we optimize the Vision Mamba (Vim) model, built on a State Space Model (SSM) architecture, by replacing the traditional classification head with Channel Group Pooling (CGP) for efficient feature integration. This optimization reduces model parameters by 1.5% and computational complexity by 0.4%. Additionally, we propose a novel Dynamic Weighted Batch-tuple Loss (DWBL) to dynamically adjust the weighting of negative samples, improving model performance. By combining CGP and DWBL, we develop an efficient end-to-end network, VimGeo, which achieves state-of-the-art performance with enhanced computational efficiency. Specifically, VimGeo achieves a Recall@1 of 81.67% on the CVACT_test dataset, outperforming prior approaches. Extensive experiments on CVUSA, CVACT, and VIGOR datasets validate VimGeo's effectiveness and competitiveness in cross-view geo-localization tasks, achieving the leading results among sequence modeling-based methods. The implementation is available at: https://github.com/VimGeoTeam/VimGeo.

Federated learning (FL) encounters slow convergence due to data heterogeneity issues. Recently, generative artificial intelligence (AI) has showcased remarkable capabilities in synthesizing realistic data. To effectively address the challenges of nonindependent and identically distributed (non-IID) data, this article introduces a collaborative AI training framework that leverages generative AI to enhance the learning performance of FL. In this framework, heterogeneous edge devices (HEDs) identify specific data categories lacking in their local data sets and acquire these data from generative AI providers (GAPs). This strategy aims to improve the convergence rate of FL. However, HEDs and GAPs may be reluctant to contribute their resources to FL training due to self-interest. Therefore, an incentive mechanism is necessary to encourage their participation. We propose a reverse auction model to facilitate data transactions among FL training buyers, GAPs, and HEDs within the FL training buyer’s budget. It focuses on determining winners and devising payment rules to maximize the FL training buyer’s utility. This involves solving a 0-1 programming problem with two sellers (GAPs and HEDs). To tackle this, we use joint bidding and virtual seller pairs for analysis. We demonstrate that our method ensures truthfulness, individual rationality, and computational efficiency. Furthermore, we employ a one-side matching mechanism to approximate the optimal solution. We further investigate a strategy to analyze and allocate data based on variance, aiming to minimize non-IID issues in local data. Simulation results demonstrate that our proposed matching mechanism can effectively improve the computational efficiency, with the test accuracy differing from the theoretical optimum by only about 0.7%, and our mechanism can outperform the other greedy algorithms. Additionally, our data allocation strategy enhances the test accuracy by approximately 7% compared to existing methods.

Federated learning (FL) has been regarded as a promising paradigm for enabling distributed model training over resource-limited edge devices. Although FL maintains data locality and enhances model generalization, it faces challenges such as model leakage and pressure from frequent model updates. Some existing schemes, such as differential privacy and model encryption, can partially alleviate these issues while sacrificing the accuracy of the modeling training or increasing the computational overheads in training. To address this issue, we design a low-complexity linear collaborative FL (LCFL) framework to enhance the privacy and accuracy of FL. Specifically, we propose the collaborative secrecy transmission (CST) algorithm by integrating a variant of Shamir's secret-sharing with the model segmentation, which can compresses and encrypts the local models for FL. The decoding complexity of the CST algorithm is only$O(N^{3})$under the compression ratio of$N$, which reduces the communication overhead and computational complexity. We conduct a quantitative analysis of the model error induced by the CST algorithm and derive its closed-form upper bound. Within LCFL, we formulate an optimization problem to maximize the global model accuracy in wireless FL by optimizing compression ratios, bandwidth allocation, and transmit-powers. Subsequently, we propose a low-complexity algorithm to solve this problem effectively. Numerical simulations demonstrate the efficacy of LCFL in improving FL's accuracy and security, and the results validate the efficiency of the proposed optimization scheme for wireless FL. The source code can be downloaded from the Github:https://github.com/MinITerence/LCFL.

Distributed Artificial Intelligence (AI) model training over mobile edge networks encounters significant challenges due to the data and resource heterogeneity of edge devices. The former hampers the convergence rate of the global model, while the latter diminishes the devices' resource utilization efficiency. In this paper, we propose a generative AI-empowered federated learning to address these challenges by leveraging the idea of FIlling the MIssing (FIMI) portion of local data. Specifically, FIMI can be considered as a resource-aware data augmentation method that effectively mitigates the data heterogeneity while ensuring efficient FL training. We first quantify the relationship between the training data amount and the learning performance. We then study the FIMI optimization problem with the objective of minimizing the device-side overall energy consumption subject to required learning performance constraints. The decomposition-based analysis and the cross-entropy searching method are leveraged to derive the solution, where each device is assigned suitable AI-synthetic data and resource utilization policy. Experiment results demonstrate that FIMI can save up to 50% of the device-side energy to achieve the target global test accuracy in comparison with the existing methods. Meanwhile, FIMI can significantly enhance the converged global accuracy under the non-independently-and-identically distribution (non-IID) data.

In this work, we investigate the challenging problem of on-demand semantic communication over heterogeneous wireless networks. We propose a fidelity-adjustable semantic transmission framework (FAST) that empowers wireless devices to send data efficiently under different application scenarios and resource conditions. To this end, we first design a dynamic sub-model training scheme to learn the flexible semantic model, which enables edge devices to customize the transmission fidelity with different widths of the semantic model. After that, we focus on the FAST optimization problem to minimize the system energy consumption with latency and fidelity constraints. Following that, the optimal transmission strategies including the scaling factor of the semantic model, computing frequency, and transmitting power are derived for the devices. Experiment results indicate that, when compared to the baseline transmission schemes, the proposed framework can reduce up to one order of magnitude of the system energy consumption and data size for maintaining reasonable data fidelity.

In this work, we investigate the challenging problem of on-demand federated learning (FL) over heterogeneous edge devices with diverse resource constraints. We propose a cost-adjustable FL framework, named AnycostFL, that enables diverse edge devices to efficiently perform local updates under a wide range of efficiency constraints. To this end, we design the model shrinking to support local model training with elastic computation cost, and the gradient compression to allow parameter transmission with dynamic communication overhead. An enhanced parameter aggregation is conducted in an element-wise manner to improve the model performance. Focusing on AnycostFL, we further propose an optimization design to minimize the global training loss with personalized latency and energy constraints. By revealing the theoretical insights of the convergence analysis, personalized training strategies are deduced for different devices to match their locally available resources. Experiment results indicate that, when compared to the state-of-the-art efficient FL algorithms, our learning framework can reduce up to 1.9 times of the training latency and energy consumption for realizing a reasonable global testing accuracy. Moreover, the results also demonstrate that, our approach significantly improves the converged global accuracy.

Multi-camera three-dimensional (3D) pose estimation (MCTPE) has already achieved very high estimation accuracy by utilizing deep neural network (DNN) based models. However, long inference latency of the utilized complex DNN models prevents the real-time deployment of MCTPE. Device-edge collaborative inference (co-inference) is a promising way to reduce the total inference latency of MCTPE, which performs one part of the inference operations on the devices and the other part of inference operations on the edge server to fully exploit computation resources of both the devices and the edge server. Besides, there is overlap between the detection ranges of different cameras in many cases. We propose the camera-selecting device-edge collaborative inference for MCTPE (CDC-MCTPE), which discards some of the raw data from parts of the cameras to reduce the inference task size without sacrificing estimation accuracy too much. In CDC-MCTPE, we formulate the joint optimization problem with regard to the model split points and camera-selecting decisions to minimize the total inference latency and the energy consumption of all devices under the constraints of the estimation accuracy. A Random-Ordered Greedy Algorithm (ROGA) is proposed to quickly solve the problem. The simulation results show that the proposed CDC-MCTPE achieves better performance compared with three benchmarks.

Model update compression is a widely used technique to alleviate the communication cost in federated learning (FL). However, there is evidence indicating that the compression-based FL system often suffers the following two issues, i) the implicit learning performance deterioration of the global model due to the inaccurate update, ii) the limitation of sharing the same compression rate over heterogeneous edge devices. In this paper, we propose an energy-efficient learning framework, named Snowball, that enables edge devices to incrementally upload their model updates in a coarse-to-fine compression manner. To this end, we first design a fine-grained compression scheme that enables a nearly continuous compression rate. After that, we investigate the Snowball optimization problem to minimize the energy consumption of parameter transmission with learning performance constraints. By leveraging the theoretical insights of the convergence analysis, the optimization problem is transformed into a tractable form. Following that, a water-filling algorithm is designed to solve the problem, where each device is assigned a personalized compression rate according to the status of the locally available resource. Experiments indicate that, compared to state-of-the-art FL algorithms, our learning framework can save five times the required energy of uplink communication to achieve a good global accuracy.

Federated learning (FL) enables devices in mobile edge computing (MEC) to collaboratively train a shared model without revealing the local data. Gradient compression could be applied to FL to alleviate the communication overheads but the existing schemes still face challenges. To deploy green MEC, we propose FedGreen, which enhances the original FL with fine-grained gradient compression to control the total energy consumption of the devices. Specifically, we introduce the relevant operations including device-side gradient reduction and server-side element-wise aggregation to facilitate the gradient compression in FL. According to a public dataset, we evaluate the contributions of the compressed local gradients with respect to different compression ratios. Furthermore, we investigate a learning accuracy-energy efficiency tradeoff problem and the optimal compression ratio and computing frequency are derived for each device. Experimental results show that given the 80% test accuracy requirement, compared with the baseline schemes, FedGreen reduces at least 32% of the total energy consumption of the devices.