Federated learning (FL) has been recognized as a promising paradigm to support distributed AI model training among wireless devices (WDs) under the coordination of an edge server (ES) without sharing local datasets. To alleviate computation burden of resource-limited WDs, model partitioning that leverages computing capability at the ES is further integrated into FL, yielding the split (S) FL framework. In this paper, we study online bandit model partitioning and resource allocation for SFL over dynamic wireless networks, aiming to minimize overall energy-latency cost (ELC). Unlike prior works focusing on offline static or online gradient-based model splitting and resource allocation, we consider a practical setting where the analytical expression of ELC function is unavailable, and instead only the function values at queried points are revealed. To tackle such a challenging mixed-integer non-linear programming problem in the online bandit context, novel Bayesian optimization (BO)-based approaches are put forth by relying on a Gaussian process (GP)-based surrogate model to actively select the model splitting points and resource allocation decisions per round via the low-complexity acquisition. Besides incorporating training model-specific structural information in the kernel design of the GP surrogate, an ensemble of GP models with data-adaptive weights is further leveraged to capture system dynamics. To cope with the challenging combinatorial nature and strong coupling over mixed action space during acquisition, an efficient alternating optimization approach is proposed building upon a novel contextual local search method. Numerical tests demonstrate that the proposed BO-based approaches outperform the contemporary baselines under various practical SFL settings.

This paper presents our indoor pathloss prediction solution to ICASSP 2025 Signal Process Grand Challenge: First Indoor Path Loss Prediction Challenge. The proposed U-Net-based network incorporates dedicated asymmetric convolutions and spatial pyramid pooling to enhance reconstruction quality. Our approach achieves a weighted root mean squared error (RMSE) of 9.411 dB on the final test set, securing the 1st place in the challenge.

The rapid proliferation of artificial intelligence (AI) services gives rise to the development of federated learning (FL), enabling the cooperative learning among wireless devices (WDs) with only local model parameters communicated. Nevertheless, the current emergence of large AI models renders the existing FL approaches inefficient, due to the huge communication overhead. In this paper, we propose a novel over-the-air federated distillation (FD) framework by synergizing the strength of FL and knowledge distillation to avoid the heavy local model transmission. Instead of sharing model parameters, only WDs' model outputs, referred to as knowledge, are shared and aggregated over-the-air by exploiting the superposition property of the multiple-access channel. Accordingly, we study the communication-learning co-design in over-the-air FD, aiming to maximize the learning convergence rate while meeting the power constraints of the transceivers. The main challenge lies in the intractability of the learning performance analysis, as well as the non-convex nature and the optimization spanning the whole FD training period. To tackle this problem, we propose an efficient algorithm to jointly optimize the transmit power of the WDs, estimator for over-the-air aggregation, and receiver beamforming per training round. Numerical results demonstrate that the proposed over-the-air FD achieves significant communication overhead reduction, with only a slight compensation of testing accuracy compared to conventional FL benchmarks.

Recent years have witnessed the development of federated learning (FL) that allows wireless devices (WDs) to collaboratively learn a global model under the coordination of a parameter server without sharing their local datasets. To meet the communication efficiency and privacy requirements, over-the-air computation and differential privacy (DP) have been incorporated in FL by leveraging the signal-superposition property of multiple-access channels and using artificial noises to perturb local model updates, thereby preserving DP. In this paper, we propose an exploration into device sampling with replacement as a potential mechanism for augmenting the DP levels of WDs in over-the-air FL. In particular, we delve into the joint optimization of device sampling strategy, the number of training rounds, and over-the-air transceiver design. Our goal is to maximize the learning performance while ensuring each WD meets the DP requirement. The problem is challenging due to the intractable FL convergence rate and privacy losses under random sampling, coupled with the strong interconnection among mixed continuous and integer decision variables. To tackle this problem, we first analyze the learning convergence rate and privacy losses of WDs. The analysis allows us to derive the optimal transceiver design per round in closed forms. Then, we propose an efficient alternating optimization algorithm by deriving the optimal device sampling strategy and the number of training rounds in semi-closed forms. Our numerical results, based on real-world learning tasks, showcase the effectiveness of our proposed approach compared with representative baselines.

Federated learning (FL) enables edge devices to collaboratively train machine learning models, with model communication replacing direct data uploading. While over-the-air model aggregation improves communication efficiency, uploading models to an edge server over wireless networks can pose privacy risks. Differential privacy (DP) is a widely used quantitative technique to measure statistical data privacy in FL. Previous research has focused on over-the-air FL with a single-antenna server, leveraging communication noise to enhance user-level DP. This approach achieves the so-called "free DP" by controlling transmit power rather than introducing additional DP-preserving mechanisms at devices, such as adding artificial noise. In this paper, we study differentially private over-the-air FL over a multiple-input multiple-output (MIMO) fading channel. We show that FL model communication with a multiple-antenna server amplifies privacy leakage when the multiple-antenna server employs separate receive combining for model aggregation and information inference. Consequently, relying solely on communication noise, as done in the multiple-input single-output system, cannot meet high privacy requirements, and a device-side privacy-preserving mechanism is necessary for optimal DP design. We analyze the learning convergence and privacy loss of the studied FL system and propose a transceiver design algorithm based on alternating optimization. Numerical results demonstrate that the proposed method achieves a better privacy-learning trade-off compared to prior work.

Recent years have witnessed the emergence of mobile edge computing (MEC), on the premise of a cost-effective enhancement in the computational ability of hardware-constrained wireless devices (WDs) comprising the Internet of Things (IoT). In a general multi-server multi-user MEC system, each WD has a computational task to execute and has to select binary (off)loading decisions, along with the analog-amplitude resource allocation variables in an online manner, with the goal of minimizing the overall energy-delay cost (EDC) with dynamic system states. While past works typically rely on the explicit expression of the EDC function, the present contribution considers a practical setting, where in lieu of system state information, the EDC function is not available in analytical form, and instead only the function values at queried points are revealed. Towards tackling such a challenging online combinatorial problem with only bandit information, novel Bayesian optimization (BO) based approaches are put forth by leveraging the multi-armed bandit (MAB) framework. Per time slot, the discrete offloading decisions are first obtained via the MAB method, and the analog resource allocation variables are subsequently optimized using the BO selection rule. By exploiting both temporal and contextual information, two novel BO approaches, termed time-varying BO and contextual time-varying BO, are developed. Numerical tests validate the merits of the proposed BO approaches compared with contemporary benchmarks under different MEC network sizes.

Recent years have witnessed the development of federated learning (FL) that allows wireless devices (WDs) to collaboratively learn a global model under the coordination of a parameter server without sharing local datasets. To meet the communication efficiency and privacy requirements, over-the-air computation and differential privacy (DP) are further incorporated in FL by leveraging the signal-superposition property of multiple-access channels, as well as artificial noises to perturb local model updates for DP preservation. In this paper, we consider the device sampling with replacement, as an amplifier for the DP levels of WDs, in differentially private over-the-air FL. Accordingly, we study the joint optimization of device sampling strategy and over-the-air transceiver design that maximizes the learning performance while satisfying the DP requirement of each WD. The problem is challenging due to the intractable FL convergence rate and privacy losses under the sampling randomness, and the strong coupling among mixed decision variables. To tackle this problem, we first derive the analytical learning convergence rate and privacy losses of WDs, based on which the optimal transceiver design and device sampling strategy are obtained in closed forms. Numerical results demonstrate the effectiveness of our proposed approach compared with representative baselines.

Federated learning (FL) allows edge devices to collaboratively train machine learning models without directly sharing data. While over-the-air model aggregation improves communication efficiency, model uploading can lead to privacy risks. Previous research has focused on over-the-air FL with a single-antenna server, leveraging communication noise to enhance user-level privacy. This method achieves the so-called “free” privacy by decreasing transmit power instead of introducing additional privacy-preserving mechanisms at the devices. In this paper, we analyze the privacy leakage of over-the-air FL over a multiple-input multiple-output (MIMO) fading channel. We show that FL model aggregation with a multiple-antenna server amplifies privacy leakage. Consequently, relying solely on communication noise is inefficient to meet high privacy requirements, particularly when the receive antenna array is large. This calls for a joint optimization algorithm for the device-side privacy-preserving mechanism and the receiving protocol to achieve a better privacy-learning tradeoff. Numerical results validate our analysis and highlight the impact of the transmit power and the receive antenna array size on the privacy leakage.

Over-the-air federated learning (OTA-FL) is a communication-effective approach for achieving distributed learning tasks. In this paper, we aim to enhance OTA-FL by seamlessly combining sensing into the communication-computation integrated system. Our research reveals that the wireless waveform used to convey OTA-FL parameters possesses inherent properties that make it well-suited for sensing, thanks to its remarkable auto-correlation characteristics. By leveraging the OTA-FL learning statistics, i.e., means and variances of local gradients in each training round, the sensing results can be embedded therein without the need for additional time or frequency resources. Finally, by considering the imperfections of learning statistics that are neglected in the prior works, we end up with an optimized the transceiver design to maximize the OTA-FL performance. Simulations validate that the proposed method not only achieves outstanding sensing performance but also significantly lowers the learning error bound.

Device-edge co-inference opens up new possibilities for resource-constrained wireless devices (WDs) to execute deep neural network (DNN)-based applications with heavy computation workloads. In particular, the WD executes the first few layers of the DNN and sends the intermediate features to the edge server that processes the remaining layers of the DNN. By adapting the model splitting decision, there exists a tradeoff between local computation cost and communication overhead. In practice, the DNN model is re-trained and updated periodically at the edge server. Once the DNN parameters are regenerated, part of the updated model must be placed at the WD to facilitate on-device inference. In this paper, we study the joint optimization of the model placement and online model splitting decisions to minimize the energy-and-time cost of device-edge co-inference in presence of wireless channel fading. The problem is challenging because the model placement and model splitting decisions are strongly coupled, while involving two different time scales. We first tackle online model splitting by formulating an optimal stopping problem, where the finite horizon of the problem is determined by the model placement decision. In addition to deriving the optimal model splitting rule based on backward induction, we further investigate a simple one-stage look-ahead rule, for which we are able to obtain analytical expressions of the model splitting decision. The analysis is useful for us to efficiently optimize the model placement decision in a larger time scale. In particular, we obtain a closed-form model placement solution for the fully-connected multilayer perceptron with equal neurons. Simulation results validate the superior performance of the joint optimal model placement and splitting with various DNN structures.

Provided with mobile edge computing (MEC) services, wireless devices (WDs) no longer have to experience long latency in running their desired programs locally, but can pay to offload computation tasks to the edge server. Given its limited storage space, it is important for the edge server at the base station (BS) to determine which service programs to cache by meeting and guiding WDs' offloading decisions. In this article, we propose an MEC service pricing scheme to coordinate with the service caching decisions and control WDs' task offloading behavior in a cellular network. We propose a two-stage dynamic game of incomplete information to model and analyze the two-stage interaction between the BS and multiple associated WDs. Specifically, in Stage I, the BS determines the MEC service caching and announces the service program prices to the WDs, with the objective to maximize its expected profit under both storage and computation resource constraints. In Stage II, given the prices of different service programs, each WD selfishly decides its offloading decision to minimize individual service delay and cost, without knowing the other WDs' desired program types or local execution delays. Despite the lack of WD's information and the coupling of all the WDs' offloading decisions, we derive the optimal threshold-based offloading policy that can be easily adopted by the WDs in Stage II at the Bayesian equilibrium. In particular, a WD is more likely to offload when there are fewer WDs competing for the edge server's computation resource, or when it perceives a good channel condition or low MEC service price. Then, by predicting the WDs' offloading equilibrium, we jointly optimize the BS' pricing and service caching in Stage I via a low-complexity algorithm. In particular, we first study the differentiated pricing scheme and prove that the same price should be charged to the cached programs of the same workload. Motivated by this analysis, we further propose a low-complexity uniform pricing heuristics.

In this paper, we consider a mobile-edge computing (MEC) system, where an access point (AP) assists a mobile device (MD) to execute an application consisting of multiple tasks following a general task call graph. The objective is to jointly determine the offloading decision of each task and the resource allocation (e.g., CPU computing power) under time-varying wireless fading channels and stochastic edge computing capability, so that the energy-time cost (ETC) of the MD is minimized. Solving the problem is particularly hard due to the combinatorial offloading decisions and the strong coupling among task executions under the general dependency model. To address the issue, we propose a deep reinforcement learning (DRL) framework based on the actor-critic learning structure. In particular, the actor network utilizes a deep neural network (DNN) to learn the optimal mapping from the input states (i.e., wireless channel gains and edge CPU frequency) to the binary offloading decision of each task. Meanwhile, for the critic network, we show that given the offloading decision, the remaining resource allocation problem becomes convex, where we can quickly evaluate the ETC performance of the offloading decisions output by the actor network. Accordingly, we select the best offloading action and store the state-action pair in an experience replay memory as the training dataset to continuously improve the action generation DNN. Numerical results show that for various types of task graphs, the proposed algorithm achieves up to 99.5% of the optimal performance while significantly reducing the computational complexity compared to the existing optimization methods.

In this paper, we consider a mobile-edge computing (MEC) system, where an access point (AP) assists a mobile device (MD) to execute an application consisting of multiple tasks following a general task call graph. The objective is to jointly determine the offloading decision of each task and the resource allocation (e.g., CPU computing power) under time-varying wireless fading channels and stochastic edge computing capability, so that the energy-time cost (ETC) of the MD is minimized. Solving the problem is particularly hard due to the combinatorial offloading decisions and the strong coupling among task executions under the general dependency model. Conventional numerical optimization methods are inefficient to solve such a problem, especially when the problem size is large. To address the issue, we propose a deep reinforcement learning (DRL) framework based on the actor-critic learning structure. In particular, the actor network utilizes a DNN to learn the optimal mapping from the input states (i.e., wireless channel gains and edge CPU frequency) to the binary offloading decision of each task. Meanwhile, by analyzing the structure of the optimal solution, we derive a low-complexity algorithm for the critic network to quickly evaluate the ETC performance of the offloading decisions output by the actor network. With the low-complexity critic network, we can quickly select the best offloading action and subsequently store the state-action pair in an experience replay memory as the training dataset to continuously improve the action generation DNN. To further reduce the complexity, we show that the optimal offloading decision exhibits an one-climb structure, which can be utilized to significantly reduce the search space of action generation. Numerical results show that for various types of task graphs, the proposed algorithm achieves up to 99.1% of the optimal performance while significantly reducing the computational complexity compared to the existing optimization methods.

Mobile-edge computing (MEC) has recently emerged as a cost-effective paradigm to enhance the computing capability of hardware-constrained wireless devices (WDs). In this paper, we first consider a two-user MEC network, where each WD has a sequence of tasks to execute. In particular, we consider task dependency between the two WDs, where the input of a task at one WD requires the final task output at the other WD. Under the considered task-dependency model, we study the optimal task offloading policy and resource allocation (e.g., on offloading transmit power and local CPU frequencies) that minimize the weighted sum of the WDs' energy consumption and task execution time. The problem is challenging due to the combinatorial nature of the offloading decisions among all tasks and the strong coupling with resource allocation. To tackle this problem, we first assume that the offloading decisions are given and derive the closed-form expressions of the optimal offloading transmit power and local CPU frequencies. Then, an efficient bi-section search method is proposed to obtain the optimal solutions. Furthermore, we prove that the optimal offloading decisions follow an one-climb policy, based on which a reduced-complexity Gibbs Sampling algorithm is proposed to obtain the optimal offloading decisions. We then extend the investigation to a general multi-user scenario, where the input of a task at one WD requires the final task outputs from multiple other WDs. Numerical results show that the proposed method can significantly outperform the other representative benchmarks and efficiently achieve low complexity with respect to the call graph size.

In this paper, we consider a two-user mobile-edge computing (MEC) network, where each wireless device (WD) has a sequence of tasks to execute. In particular, we consider task dependency between the two WDs, where the input of a task at one WD requires the final task output at the other WD. Under the considered task-dependency model, we study the optimal task offloading policy and resource allocation (on offloading transmit power and local CPU frequencies) that minimize the weighted sum of the WDs' energy consumption and execution time. The problem is challenging due to the combinatorial nature of the offloading decision among all tasks and the strong coupling with resource allocation among subsequent tasks. When the offloading decision is given, we obtain the closed-form expressions of the offloading transmit power and local CPU frequencies and propose an efficient method to obtain the optimal solutions. Furthermore, we prove that the optimal offloading decision follows an one-climb policy, based on which a reduced-complexity algorithm is proposed to obtain the optimal offloading decision in polynomial time. Numerical results validate the effectiveness of our proposed methods.