Towards Semantic Communication Protocols for 6G: From Protocol to Language-Oriented Approaches

The forthcoming 6G systems are expected to address a wide range of non-stationary tasks. This poses challenges to traditional medium access control (MAC) protocols that are static and predefined. In response, data-driven MAC protocols have recently emerged, offering ability to tailor their signaling messages for specific tasks. This article presents a novel categorization of these data-driven MAC protocols into three levels: Level 1 MAC. task-oriented neural protocols constructed using multi-agent deep reinforcement learning (MADRL); Level 2 MAC. neural network-oriented symbolic protocols developed by converting Level 1 MAC outputs into explicit symbols; and Level 3 MAC. language-oriented semantic protocols harnessing large language models (LLMs) and generative models. With this categorization, we aim to explore the opportunities and challenges of each level by delving into their foundational techniques. Drawing from information theory and associated principles as well as selected case studies, this study provides insights into the trajectory of data-driven MAC protocols and sheds light on future research directions.

Level 1 MAC - Task-Oriented Neural Protocols. The current studies in data-driven MAC protocols are primarily centered on multi-agent deep reinforcement learning (MADRL), which we classify under the Level 1 MAC protocols

Level 2 MAC - NN-Oriented Symbolic Protocols. Level 2 MAC transforms neural protocols into symbolic protocols, by identifying and transforming consistent messages from Level 1 MAC into explicit symbols. The resultant symbolic protocols present interpretable protocol operations, allowing direct manipulation.

Level 3 MAC - Language-Oriented Semantic Protocols. The advent of large language models (LLMs) hints at the potential for acquiring general knowledge in the domain of human language. Concurrently, recent advances in cross-modal generative models, such as BLIP for image-to-text conversion, advocate the feasibility of translating various data modalities into human language.

Full Paper: J. Park, S.-W. Ko, J. Choi, S.-L. Kim, and M. Bennis, "Towards Semantic Communication Protocols for 6G: From Protocol Learning to Language-Oriented Approaches,"