Reasoning with the Theory of Mind for Pragmatic Semantic Communication

TL;DR

This paper introduces a novel pragmatic semantic communication framework utilizing theory of mind to enable goal-oriented information sharing, dynamically adapting to the receiver's reasoning to improve efficiency and semantic fidelity.

Contribution

It proposes a ToM-based semantic communication model with a two-level feedback mechanism, enhancing goal-oriented data exchange by mimicking receiver reasoning.

Findings

Achieves efficient communication with fewer bits while maintaining semantics

Outperforms conventional systems lacking ToM reasoning

Demonstrates dynamic adaptation to receiver's mental state

Abstract

In this paper, a pragmatic semantic communication framework that enables effective goal-oriented information sharing between two-intelligent agents is proposed. In particular, semantics is defined as the causal state that encapsulates the fundamental causal relationships and dependencies among different features extracted from data. The proposed framework leverages the emerging concept in machine learning (ML) called theory of mind (ToM). It employs a dynamic two-level (wireless and semantic) feedback mechanism to continuously fine-tune neural network components at the transmitter. Thanks to the ToM, the transmitter mimics the actual mental state of the receiver's reasoning neural network operating semantic interpretation. Then, the estimated mental state at the receiver is dynamically updated thanks to the proposed dynamic two-level feedback mechanism. At the lower level, conventional channel quality metrics are used to optimize the channel encoding process based on the wireless communication channel's quality, ensuring an efficient mapping of semantic representations to a finite constellation. Additionally, a semantic feedback level is introduced, providing information on the receiver's perceived semantic effectiveness with minimal overhead. Numerical evaluations demonstrate the framework's ability to achieve efficient communication with a reduced amount of bits while maintaining the same semantics, outperforming conventional systems that do not exploit the ToM-based reasoning.