In multi-cell wireless networks, providing intelligent services via federated learning (FL) becomes more challenging due to multi-level distribution shifts across clients and regions, as well as additional communication delays among edge and cloud servers. To address these issues, we propose SplitOMC, a split learning framework that integrates overlapping-area clients and a multi-exit neural architecture to jointly handle (i) client-preferred, (ii) out-of-preference, and (iii) out-of-region tasks. By strategically leveraging clients in overlapping regions, SplitOMC accelerates training without excessive backhaul communication, while maintaining both personalization and generalization. We theoretically analyze the convergence behavior of the proposed algorithm, ensuring performance stability under heterogeneous data and communication conditions. Extensive experiments on MNIST, CIFAR-10/100, and a real-world Jetson Nano testbed demonstrate that SplitOMC consistently achieves faster training and inference with improved accuracy compared to state-of-the-art methods. In particular, the framework shows robustness in resource-constrained and unstable network environments, highlighting its practical value for next-generation wireless intelligent services.

Extreme resource constraints make large-scale machine learning (ML) with distributed clients challenging in wireless networks. On the one hand, large-scale ML requires massive information exchange between clients and server(s). On the other hand, these clients have limited battery and computation powers that are often dedicated to operational computations. Split federated learning (SFL) is emerging as a potential solution to mitigate these challenges, by splitting the ML model into clientside and server-side model blocks, where only the client-side block is trained on the client device. However, practical applications require personalized models that are suitable for the client's personal task. Motivated by this, we propose a personalized hierarchical split federated learning (PHSFL) algorithm that is specially designed to achieve better personalization performance. More specially, owing to the fact that regardless of the severity of the statistical data distributions across the clients, many of the features have similar attributes, we only train the body part of the federated learning (FL) model while keeping the (randomly initialized) classifier frozen during the training phase. We first perform extensive theoretical analysis to understand the impact of model splitting and hierarchical model aggregations on the global model. Once the global model is trained, we finetune each client classifier to obtain the personalized models. Our empirical findings suggest that while the globally trained model with the untrained classifier performs quite similarly to other existing solutions, the fine-tuned models show significantly improved personalized performance.

Channel models that represent various operating conditions a communication system might experience are important for design and standardization of any communication system. While statistical channel models have long dominated this space, machine learning (ML) is becoming a popular alternative approach. However, existing approaches have mostly focused on predictive solutions to match instantaneous channel realizations. Other solutions have focused on pathloss modeling, while double-directional (DD) channel representation is needed for a complete description. Motivated by this, we (a) develop a generative solution that uses a hybrid Transformer (hTransformer) model with a low-rank projected attention calculation mechanism and a bidirectional long short-term memory (BiLSTM) layer to generate complete DD channel information and (b) design a domain-knowledge-informed training method to match the generated and true channel realizations' statistics. Our extensive simulation results validate that the generated samples' statistics closely align with the true statistics while mostly outperforming the performance of existing predictive approaches.

Backhaul traffic congestion caused by the video traffic of a few popular files can be alleviated by storing the to-be-requested content at various levels in wireless video caching networks. Typically, content service providers (CSPs) own the content, and the users request their preferred content from the CSPs using their (wireless) internet service providers (ISPs). As these parties do not reveal their private information and business secrets, traditional techniques may not be readily used to predict the dynamic changes in users’ future demands. Motivated by this, we propose a novelresource-awarehierarchicalfederatedlearning (RawHFL) solution for predicting user’s future content requests. A practical data acquisition technique is used that allows the user to update its local training dataset based on its requested content. Besides, since networking and other computational resources are limited, considering that only a subset of the users participate in the model training, we derive the convergence bound of the proposed algorithm. Based on this bound, we minimize a weighted utility function for jointly configuring the controllable parameters to train the RawHFL energy efficiently under practical resource constraints. Our extensive simulation results validate the proposed algorithm’s superiority, in terms of test accuracy and energy cost, over existing baselines.

Video caching can significantly improve backhaul traffic congestion by locally storing the popular content that users frequently request. A privacy-preserving method is desirable to learn how users' demands change over time. As such, this paper proposes a novel resource-aware hierarchical federated learning (RawHFL) solution to predict users' future content requests under the realistic assumptions that content requests are sporadic and users' datasets can only be updated based on the requested content's information. Considering a partial client participation case, we first derive the upper bound of the global gradient norm that depends on the clients' local training rounds and the successful reception of their accumulated gradients over the wireless links. Under delay, energy and radio resource constraints, we then optimize client selection and their local rounds and central processing unit (CPU) frequencies to minimize a weighted utility function that facilitates RawHFL's convergence in an energy-efficient way. Our simulation results show that the proposed solution significantly outperforms the considered baselines in terms of prediction accuracy and total energy expenditure.

While a practical wireless network has many tiers where end users do not directly communicate with the central server, the users’ devices have limited computation and battery powers, and the serving base station (BS) has a fixed bandwidth. Owing to these practical constraints and system models, this paper leverages model pruning and proposes a pruning-enabled hierarchical federated learning (PHFL) in heterogeneous networks (HetNets). We first derive an upper bound of the convergence rate that clearly demonstrates the impact of the model pruning and wireless communications between the clients and the associated BS. Then we jointly optimize the model pruning ratio, central processing unit (CPU) frequency and transmission power of the clients in order to minimize the controllable terms of the convergence bound under strict delay and energy constraints. However, since the original problem is not convex, we perform successive convex approximation (SCA) and jointly optimize the parameters for the relaxed convex problem. Through extensive simulation, we validate the effectiveness of our proposed PHFL algorithm in terms of test accuracy, wall clock time, energy consumption and bandwidth requirement.

This paper proposes a vehicular edge federated learning (VEFL) solution, where an edge server leverages highly mobile connected vehicles’ (CVs’) onboard central processing units (CPUs) and local datasets to train a global model. Convergence analysis reveals that the VEFL training loss depends on the successful receptions of the CVs’ trained models over the intermittent vehicle-to-infrastructure (V2I) wireless links. Owing to high mobility, in the full device participation case (FDPC), the edge server aggregates client model parameters based on a weighted combination according to the CVs’ dataset sizes and sojourn periods, while it selects a subset of CVs in the partial device participation case (PDPC). We then devise joint VEFL and radio access technology (RAT) parameters optimization problems under delay, energy and cost constraints to maximize the probability of successful reception of the locally trained models. Considering that the optimization problem is NP-hard, we decompose it into a VEFL parameter optimization sub-problem, given the estimated worst-case sojourn period, delay and energy expense, and an online RAT parameter optimization sub-problem. Finally, extensive simulations are conducted to validate the effectiveness of the proposed solutions with a practical 5G new radio (5G-NR) RAT under a realistic microscopic mobility model.

While privacy concerns entice connected and automated vehicles to incorporate on-board federated learning (FL) solutions, an integrated vehicle-to-everything communication with heterogeneous computation power aware learning platform is urgently necessary to make it a reality. Motivated by this, we propose a novel mobility, communication and computation aware online FL platform that uses on-road vehicles as learning agents. Thanks to the advanced features of modern vehicles, the on-board sensors can collect data as vehicles travel along their trajectories, while the on-board processors can train machine learning models using the collected data. To take the high mobility of vehicles into account, we consider the delay as a learning parameter and restrict it to be less than a tolerable threshold. To satisfy this threshold, the central server accepts partially trained models, the distributed roadside units (a) perform downlink multicast beamforming to minimize global model distribution delay and (b) allocate optimal uplink radio resources to minimize local model offloading delay, and the vehicle agents conduct heterogeneous local model training. Using real-world vehicle trace datasets, we validate our FL solutions. Simulation shows that the proposed integrated FL platform is robust and outperforms baseline models. With reasonable local training episodes, it can effectively satisfy all constraints and deliver near ground truth multi-horizon velocity and vehicle-specific power predictions.

Edge caching is a new paradigm that has been exploited over the past several years to reduce the load for the core network and to enhance the content delivery performance. Many existing caching solutions only consider homogeneous caching placement due to the immense complexity associated with the heterogeneous caching models. Unlike these legacy modeling paradigms, this paper considers heterogeneous content preference of the users with heterogeneous caching models at the edge nodes. Besides, aiming to maximize the cache hit ratio (CHR) in a two-tier heterogeneous network, we let the edge nodes collaborate. However, due to complex combinatorial decision variables, the formulated problem is hard to solve in the polynomial time. Moreover, there does not even exist a ready-touse tool or software to solve the problem. We propose a modified particle swarm optimization (M-PSO) algorithm that efficiently solves the complex constraint problem in a reasonable time. Using numerical analysis and simulation, we validate that the proposed algorithm significantly enhances the CHR performance when comparing to that of the existing baseline caching schemes.

While next-generation wireless networks intend leveraging edge caching for enhanced spectral efficiency, quality of service, end-to-end latency, content sharing cost, etc., several aspects of it are yet to be addressed to make it a reality. One of the fundamental mysteries in a cache-enabled network is predicting what content to cache and where to cache so that high caching content availability is accomplished. For simplicity, most of the legacy systems utilize a static estimation - based on Zipf distribution, which, in reality, may not be adequate to capture the dynamic behaviors of the contents popularities. Forecasting user's preferences can proactively allocate caching resources and cache the needed contents, which is especially important in a dynamic environment with real-time service needs. Motivated by this, we propose a long short-term memory (LSTM) based sequential model that is capable of capturing the temporal dynamics of the users' preferences for the available contents in the content library. Besides, for a more efficient edge caching solution, different nodes in proximity can collaborate to help each other. Based on the forecast, a non-convex optimization problem is formulated to minimize content sharing costs among these nodes. Moreover, a greedy algorithm is used to achieve a sub-optimal solution. Using extensive simulation and analysis, we validate that the proposed algorithm performs better than other existing schemes.

This paper introduces an energy-efficient, software-defined vehicular edge network for the growing intelligent connected transportation system. A joint user-centric virtual cell formation and resource allocation problem is investigated to bring eco-solutions at the edge. This joint problem aims to combat against the power-hungry edge nodes while maintaining assured reliability and data rate. More specifically, by prioritizing the downlink communication of dynamic eco-routing, highly mobile autonomous vehicles are served with multiple low-powered access points (APs) simultaneously for ubiquitous connectivity and guaranteed reliability of the network. The formulated optimization is exceptionally troublesome to solve within a polynomial time, due to its complicated combinatorial structure. Hence, a distributed multi-agent reinforcement learning (D-MARL) algorithm is proposed for eco-vehicular edges, where multiple agents cooperatively learn to receive the best reward. First, the algorithm segments the centralized action space into multiple smaller groups. Based on the model-free distributed Q learner, each edge agent takes its actions from the respective group. Also, in each learning state, a software-defined controller chooses the global best action from individual bests of the distributed agents. Numerical results validate that our learning solution achieves near-optimal performances within a small number of training episodes as compared with existing baselines.