Joint Deep Adversarial Semantic Decomposition Scheme for Model Division Multiple Access in IoT

To support the large-scale connectivity of massive intelligent devices in the Internet of Things (IoT) scenario, in this paper, an uplink multi-user semantic communication system based on model division multiple access (MDMA) is investigated. A model resource pool consisting of multiple mutually exclusive semantic models is built as one new kind of access resource, and a global optimization problem is formulated to make the mapping of different semantic models have stronger mutual exclusion. To solve this problem, a joint deep adversarial semantic decomposition (JDASD) algorithm is proposed to enhance the ability of the semantic models to eliminate interference from other devices. Simulation results demonstrate that the proposed JDASD algorithm achieves higher anti-interference capability in the MDMA system than the traditional independent training scheme applied in most works, showing the advantages of the proposed scheme for the IoT scenario with massive devices.