Natural Transports-Inspired Differential Semantic Communications: Intelligent Transceivers Carry Just Differences as Meanings

Communication is a fundamental process in the nature of interconnected entities. Conventional engineering models of information transmission and reception, namely Shannon’s bit communication and Weaver’s semantic communication, consist of a serial architecture with the elements of transmitter, channel, and receiver. However, in natural transport processes, such as human-to-human interactions, transceivers operate through bidirectional, iterative closed-loop feedback mechanisms. Inspired by this physical observation, we propose a novel generalised cognitive communication topology, called Differential Semantic Communications, abbreviated DSC. In the DSC model, only informational differences are coded for communication purposes. As a result, this intelligent strategy leads to communication efficiency by priorly suppressing redundancies. We demonstrate the concept of our architecture to visual transmission using state-of-the-art semantic computing and generative artificial intelligence techniques. For the problem of transmitting salient objects in digital images, our experiments show that DSC can appropriately balance between bandwidth usage and meanings reconstruction error, with approximately 22 % substantial improvement in the mean semantic misfit error when compared to the best lossless transmission scheme. Our model can be used in diverse applications, including: storage- and bandwidth-constrained scenarios, such as server-client communications, the Internet of Things, and edge computing. The implementation codes, datasets, and experimental results are publicly available to researchers and developers.