Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks
Abstract
Multi-Task semantic communication (SemCom) prioritizes simultaneous execution of multiple tasks over bit-accurate reconstruction in future intelligent networks. In our prior work [1], we introduced the cooperative multi-task SemCom (CMT-SemCom) framework, in which the semantic encoder is divided into a common unit (CU) and multiple specific units (SUs) to facilitate cooperative multi-task processing. However, CMT-SemCom has been evaluated on homogeneous classification tasks on simplistic datasets, limiting its applicability to real-world perception systems. In this paper, we extend our CMT-SemCom to jointly handle heterogeneous classification and regression tasks on the complex Cityscapes dataset. We adopt the information maximization (InfoMax) principle so that it accommodates mixed discrete and continuous semantic variables. In particular, we benchmark the proposed framework against independent single-task training, a conventional task-agnostic digital transmission, and single-encoder multi-decoder SemCom. Additionally, we investigate the impact of CU capacity on joint task performance, providing design insights. Extensive evaluations demonstrate that CMT-SemCom significantly outperforms the benchmarks.
Related
- Principal profiles, characteristic communication and critical asymptotics for cooperative nonlocal systems on the circle
- SemRD-V2X: Closure-Guided Communication with Bounded Inference for Cooperative Perception
- Covert Digital Semantic Communication With Movable Antennas: Constellation Shaping, Spatial Optimization, and Semantic Mapping
- End-to-End Optical Semantic Communication over a Nonlinear WDM Fiber Link
- Towards Faithful and Efficient Semantic Communication: An Ontological Approach
BibTeX
@misc{razlighi2026cooperative,
title = {{Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks}},
author = {Ahmad Halimi Razlighi and Mohammad Siddiqur Rahman and Maximilian H. V. Tillmann and Edgar Beck and Armin Dekorsy},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.03977},
eprint = {2609.03977},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.03977},
}
RIS
TY - UNPB
TI - Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks
AU - Ahmad Halimi Razlighi
AU - Mohammad Siddiqur Rahman
AU - Maximilian H. V. Tillmann
AU - Edgar Beck
AU - Armin Dekorsy
PY - 2026
DA - 2026/09/03
PB - arXiv
DO - 10.48550/arxiv.2609.03977
UR - https://arxiv.org/abs/2609.03977
AB - Multi-Task semantic communication (SemCom) prioritizes simultaneous execution of multiple tasks over bit-accurate reconstruction in future intelligent networks. In our prior work [1], we introduced the cooperative multi-task SemCom (CMT-SemCom) framework, in which the semantic encoder is divided into a common unit (CU) and multiple specific units (SUs) to facilitate cooperative multi-task processing. However, CMT-SemCom has been evaluated on homogeneous classification tasks on simplistic datasets, limiting its applicability to real-world perception systems. In this paper, we extend our CMT-SemCom to jointly handle heterogeneous classification and regression tasks on the complex Cityscapes dataset. We adopt the information maximization (InfoMax) principle so that it accommodates mixed discrete and continuous semantic variables. In particular, we benchmark the proposed framework against independent single-task training, a conventional task-agnostic digital transmission, and single-encoder multi-decoder SemCom. Additionally, we investigate the impact of CU capacity on joint task performance, providing design insights. Extensive evaluations demonstrate that CMT-SemCom significantly outperforms the benchmarks.
ER -