An Indirect Rate-Distortion Characterization for Semantic Sources: General Model and the Case of Gaussian Observation

Jiakun Liu, Shuo Shao, Wenyi Zhang, H. Vincent Poor

Research output: Contribution to journalArticlepeer-review

Abstract

A new source model, which consists of an intrinsic state part and an extrinsic observation part, is proposed and its information-theoretic characterization, namely its rate-distortion function, is defined and analyzed. Such a source model is motivated by the recent surge of interest in the semantic aspect of information: the intrinsic state corresponds to the semantic feature of the source, which in general is not observable but can only be inferred from the extrinsic observation. There are two distortion measures, one between the intrinsic state and its reproduction, and the other between the extrinsic observation and its reproduction. Under a given code rate, the tradeoff between these two distortion measures is characterized by the rate-distortion function, which is solved via the indirect rate-distortion theory and is termed the semantic rate-distortion function of the source. As an application of the general model and its analysis, the case of Gaussian extrinsic observation is studied, assuming a linear relationship between the intrinsic state and the extrinsic observation, under a quadratic distortion structure. The semantic rate-distortion function is shown to be the solution of a convex programming problem with respect to an error covariance matrix, and a reverse water-filling type of solution is provided when the model further satisfies a diagonalizability condition.

Original languageEnglish (US)
Pages (from-to)5946-5959
Number of pages14
JournalIEEE Transactions on Communications
Volume70
Issue number9
DOIs
StatePublished - Sep 1 2022

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Keywords

  • Lossy compression
  • rate distortion theory
  • reverse water-filling
  • semantic rate distortion function
  • semantic source model
  • task-oriented communication

Fingerprint

Dive into the research topics of 'An Indirect Rate-Distortion Characterization for Semantic Sources: General Model and the Case of Gaussian Observation'. Together they form a unique fingerprint.

Cite this