Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approach
- 30 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 4, 698-717
Abstract
A digital twin (DT) leverages a virtual representation of the physical world, along with communication (e.g., 6G), computing (e.g., edge computing), and artificial intelligence (AI) technologies to enable many connected intelligence services. In order to handle the large amounts of network data based on digital twins (DTs), wireless systems can exploit the paradigm of semantic communication (SC) for facilitating informed decision-making under strict communication constraints by utilizing AI techniques such as causal reasoning. In this paper, a novel framework called causal semantic communication (CSC) is proposed for DT-based wireless systems. The CSC system is posed as an imitation learning (IL) problem, where the transmitter, with access to optimal network control policies using a DT, teaches the receiver using SC over a bandwidth-limited wireless channel how to improve its knowledge to perform optimal control actions. The causal structure in the transmitter’s data is extracted using novel approaches from the framework of deep end-to-end causal inference, thereby enabling the creation of a semantic representation that is causally invariant, which in turn helps generalize the learned knowledge of the system to new and unseen situations. The CSC decoder at the receiver is designed to extract and estimate semantic information while ensuring high semantic reliability. The receiver control policies, semantic decoder, and causal inference are formulated as a bi-level optimization problem within a variational inference framework. This problem is solved using a novel concept called network state models, inspired from world models in generative AI, that faithfully represents the environment dynamics leading to data generation. Furthermore, the proposed framework includes an analytical characterization of the performance gap that results from employing a suboptimal policy learned by the receiver that uses the transmitted semantic information to construct a model of the physical environment. The CSC system utilizes two concepts, namely the integrated information theory principle in the theory of consciousness and the abstract cell complex concept in topology, to precisely express the information content conveyed by the causal states and their relationships. Through this analysis, novel formulations of semantic information, semantic reliability, distortion, and similarity metrics are proposed, which extend beyond Shannon’s concept of uncertainty. Simulation results demonstrate that the proposed CSC system outperforms conventional wireless and state-of-the-art SC systems by achieving better semantic reliability with reduced bits and enabling better control policies over time thanks to the generative AI architecture.Keywords
Funding Information
- U.S. National Science Foundation (CNS-2210254)
- National Natural Science Foundation of China (62071193)
- Major Key Project of Peng Cheng Laboratory (PCL2023AS1-2)
This publication has 31 references indexed in Scilit:
- Low-Latency Federated Learning and Blockchain for Edge Association in Digital Twin Empowered 6G NetworksIEEE Transactions on Industrial Informatics, 2020
- Deep Reinforcement Learning for Stochastic Computation Offloading in Digital Twin NetworksIEEE Transactions on Industrial Informatics, 2020
- Why Does Space Feel the Way it Does? Towards a Principled Account of Spatial ExperienceEntropy, 2019
- Digital Twin in Industry: State-of-the-ArtIEEE Transactions on Industrial Informatics, 2018
- An Algorithmic Perspective on Imitation LearningFoundations and Trends in Robotics, 2018
- Theories, Sites, Toposes2018
- Curiosity-Driven Exploration by Self-Supervised Prediction2017
- Variational Inference: A Review for StatisticiansJournal of the American Statistical Association, 2017
- From the Phenomenology to the Mechanisms of Consciousness: Integrated Information Theory 3.0PLOS Computational Biology, 2014
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008