Semantic communications, which aim to effectively convey the meaning of messages (such as text and images) rather than transmitting the exact messages themselves, have garnered widespread attention from industry and academia. A suitable joint source-channel coding (JSCC) scheme is crucial for semantic communication systems, as it can significantly improve system performance, such as communication reliability. Current research efforts primarily focus on employing various deep neural network (DNN) models, particularly the Transformer model, to design JSCC schemes. However, existing Transformer-based JSCC schemes usually exhibit a considerable number of model parameters and computational demands, limiting their real-world applicability. To address this challenge, we propose a novel DNN model based on DeLighT, a deep and lightweight variant of the standard Transformer, using a text semantic communication system (TSC) as an example. This proposed model enables a lightweight JSCC scheme for the TSC system. Through simulation results, we demonstrate that the proposed JSCC scheme achieves comparable or better communication reliability than the Transformer-based JSCC scheme while requiring significantly fewer parameters and smaller runtime.
4 October 2022 in IEEE Transactions on Vehicular Technology
This paper explores an item delivery scenario using an unmanned aerial vehicle (UAV). In this scenario, in the presence of multiple no-fly zones, an UAV starts from the point of departure, collects the items from ground users, and finally delivers the collected items to the destination. We mathematically characterize the item delivery scenario. Then, we formulate a problem of item value maximization to jointly optimize the UAV trajectory and item pick-up design. The formulated problem is a challenging mixed-integer non-convex optimization problem. Through some equivalent transformations, we convert the original problem into an equivalent problem with a difference-of-convex structure. Using the penalty convex-concave procedure method, we devise a low-complexity algorithm with promising performance. The numerical results demonstrate the superiority of the proposed algorithm.
8 July 2024 in IEEE Transactions on Cognitive Communications and Networking
Deploying federated learning at the wireless edge introduces federated edge learning (FEEL). Given FEEL’s limited communication resources and potential mislabeled data on devices, improper resource allocation or data selection can hurt convergence speed and increase training costs. Thus, to realize an efficient FEEL system, this paper emphasizes jointly optimizing resource allocation and data selection. Specifically, in this work, through rigorously modeling the training process and deriving an upper bound on FEE’s one-round convergence rate, we establish a problem of joint resource allocation and data selection, which, unfortunately, cannot be solved directly. Toward this end, we equivalently transform the original problem into a solvable form via a variable substitution and then break it into two subproblems, that is, the resource allocation problem and the data selection problem. The two subproblems are mixed-integer non-convex and integer non-convex problems, respectively, and achieving their optimal solutions is a challenging task. Based on the matching theory and applying the convex-concave procedure and gradient projection methods, we devise a low-complexity suboptimal algorithm for the two subproblems, respectively. Finally, the superiority of our proposed scheme of joint resource allocation and data selection is validated by numerical results.
In this work, we focus on a drone-fleet-enabled package delivery scenario, in which multiple drones fly from a start point and cooperatively deliver packages to the ground users in the presence of a number of no-fly zones (NFZs). We first mathematically model the package delivery scenario in a rigorous manner. Then, a package value maximization problem is established to optimize the flight trajectory and package delivery under the constraints of drone load and collision as well as NFZs. The formulated problem is a highly challenging mixed-integer non-convex problem. To facilitate solving it, we transform the formulated problem into an equivalent problem with special structure by using some appropriate transformations, based on which a low-complexity algorithm with favorable performance is developed using the penalty convex–concave procedure method. Finally, numerical results demonstrate the superiority of the proposed solution.
17 November 2025 in IEEE Transactions on Cognitive Communications and Networking
Multi-functional unmanned aerial vehicles (UAVs) are gaining attention for supporting multi-task missions such as delivery and federated learning (FL). However, asynchronous data uploading hinders synchronous model aggregation, and user behavior often exhibits group-level personalized data. To address these challenges, we propose a joint model training and UAV path optimization framework. We formulate a UAV network system model that enables the UAV to function as both a delivery carrier and an FL parameter server. We design a two-tier training framework to mitigate group heterogeneity and model staleness. Specifically, the inner tier conducts synchronous intra-group personalized updates, whereas the outer tier employs staleness-aware asynchronous global aggregation. To reduce model staleness during cargo delivery, we formulate a path optimization problem incorporating training window duration, and we solve it via deep reinforcement learning. Numerical results show that the proposed framework outperforms the static and random path baselines, reducing model staleness by 20.75% and 42.67% while improving convergence rates by 20.15% and 46.50%, respectively. In a group-level non-independent and identically distributed (non-IID) setting, the training framework achieves a 5.28% test accuracy improvement over an asynchronous, device-level personalized learning baseline.