Xuechen Chen

Deep learning-based joint source-channel coding (DeepJSCC) has demonstrated significant potential for task-oriented semantic communication. However, existing DeepJSCC frameworks exhibit limited generalization across multi-tasks. This limitation stems from bandwidth compression, which results a trade-off between preserving details and capturing semantics. To overcome this challenge, we propose a novel Task-Generalizable DeepJSCC framework, called TGDJSCC. In the pre-training phase, we devise a hierarchical masked autoencoder (HMAE) to learn hierarchical representations within bandwidth-constrained latent spaces. Specifically, we introduce a novel content-aware tree for establishing hierarchy, along with a dual self-supervised mask image modeling scheme to learn transferable hierarchical representations. During fine-tuning, a task-adaptive feature selection module dynamically routes hierarchical features according to specific task requirements. This enables efficient adaptation to new tasks with only a few fine-tuning epochs for both pixel-level and semantic-level tasks, eliminating the need for full retraining. Comprehensive experiments demonstrate that TGDJSCC significantly surpasses existing DeepJSCC methods in task generalization, while maintaining communication efficiency under stringent bandwidth constraints.

The intelligent development of high-speed railways (HSRs) necessitates support for various services to ensure safe and reliable train operations while providing high-quality travel experiences for passengers. Network slicing presents a promising solution via isolated and service-specific radio resource management. However, meeting heterogeneous quality of service (QoS) requirements in HSR communications is particularly challenging due to imperfect channel state information (CSI) caused by high-speed mobility. In this work, we investigate a slicing puncture strategy in a moving network with an imperfect train-to-ground downlink, supporting passenger entertainment and safety-related services. The system includes two transmission links: outboard and inboard. Given the impact of high-speed mobility, we characterize the statistical probability distribution of the actual CSI and model the average transmission rates in the outboard link. We aim to minimize the system Resource Block (RB) and power in the above two links while satisfying the diverse QoS requirements of services. Since the resource minimization problem is a mixed-integer nonlinear programming, we decompose it into three subproblems: RB allocation, power allocation, and slicing puncture optimization. A Speed-Aware Resource allocation and Slicing puncture (SA-RS) algorithm is proposed. Specifically, analytical expressions are derived for RB allocation, and a bisection-based algorithm is designed for power allocation. Moreover, the slicing puncture strategy is obtained using a genetic-based algorithm. Simulation results demonstrate that the proposed strategy can improve the system performance compared with other baseline schemes under imperfect CSI.

In recent years, Deep Joint Source-Channel Coding (DeepJSCC) has demonstrated superior performance over traditional digital schemes in wireless image transmission tasks. However, existing DeepJSCC approaches often overlook three critical challenges in broadcast communication scenarios: bandwidth heterogeneity among users, dynamic bandwidth variations experienced by individual users, and users diverse requirements. To address these issues, we propose a scalable DeepJSCC framework tailored for broadcast communications. This framework enables users to adaptively intercept an appropriate amount of encoded data according to their bandwidth conditions or specific requirements, thereby reconstructing images with corresponding quality. Specifically, the transmitter generates a multi-layered codestream, consisting of multiple base layers for image reconstruction at different resolutions, as well as enhancement layers built upon each base layer to improve visual quality. At the receiver, users can selectively intercept the base layer stream corresponding to their desired resolution, and further receive parts of the associated enhancement layer stream. This design allows for flexible and quality-adaptive image reconstruction based on the amount of data received. Extensive experiments demonstrate that the proposed scheme consistently achieves high-quality reconstruction across various resolutions and under diverse interception conditions.