Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Receiver-Centric Generative Semantic Communications

Xunze Liu, Yifei Sun, Zhaorui Wang, Lizhao You, Haoyuan Pan, Fangxin Wang, Shuguang Cui

TL;DR

This paper presents a receiver-centric generative semantic communication system, where each transmission is initialized by the receiver and the receiver first sends its request for the desired semantic information to the transmitter at the start of each transmission, and the transmitter extracts the required semantic information accordingly.

Abstract

This paper investigates semantic communications between a transmitter and a receiver, where original data, such as videos of interest to the receiver, is stored at the transmitter. Although significant process has been made in semantic communications, a fundamental design problem is that the semantic information is extracted based on certain criteria at the transmitter alone, without considering the receiver's specific information needs. As a result, critical information of primary concern to the receiver may be lost. In such cases, the semantic transmission becomes meaningless to the receiver, as all received information is irrelevant to its interests. To solve this problem, this paper presents a receiver-centric generative semantic communication system, where each transmission is initialized by the receiver. Specifically, the receiver first sends its request for the desired semantic information to the transmitter at the start of each transmission. Then, the transmitter extracts the required semantic information accordingly. A key challenge is how the transmitter understands the receiver's requests for semantic information and extracts the required semantic information in a reasonable and robust manner. We address this challenge by designing a well-structured framework and leveraging off-the-shelf generative AI products, such as GPT-4, along with several specialized tools for detection and estimation. Evaluation results demonstrate the feasibility and effectiveness of the proposed new semantic communication system.

Receiver-Centric Generative Semantic Communications

TL;DR

This paper presents a receiver-centric generative semantic communication system, where each transmission is initialized by the receiver and the receiver first sends its request for the desired semantic information to the transmitter at the start of each transmission, and the transmitter extracts the required semantic information accordingly.

Abstract

This paper investigates semantic communications between a transmitter and a receiver, where original data, such as videos of interest to the receiver, is stored at the transmitter. Although significant process has been made in semantic communications, a fundamental design problem is that the semantic information is extracted based on certain criteria at the transmitter alone, without considering the receiver's specific information needs. As a result, critical information of primary concern to the receiver may be lost. In such cases, the semantic transmission becomes meaningless to the receiver, as all received information is irrelevant to its interests. To solve this problem, this paper presents a receiver-centric generative semantic communication system, where each transmission is initialized by the receiver. Specifically, the receiver first sends its request for the desired semantic information to the transmitter at the start of each transmission. Then, the transmitter extracts the required semantic information accordingly. A key challenge is how the transmitter understands the receiver's requests for semantic information and extracts the required semantic information in a reasonable and robust manner. We address this challenge by designing a well-structured framework and leveraging off-the-shelf generative AI products, such as GPT-4, along with several specialized tools for detection and estimation. Evaluation results demonstrate the feasibility and effectiveness of the proposed new semantic communication system.

Paper Structure

This paper contains 15 sections, 3 equations, 4 figures, 3 tables, 4 algorithms.

Table of Contents

  1. Introduction
  2. Overview of Framework
  3. Transmitter Side
  4. Receiver Side
  5. Task Planning and Reflection
  6. Task Planning
  7. Task Reflection
  8. Frame Selection
  9. Tool Selection
  10. Overall Process
  11. System Performance
  12. Implementation
  13. Evaluation Methodology and Results
  14. Tools and Their Detailed Descriptions
  15. Tool and Their Labels

Figures (4)

  • Figure 1: An autoencoder with a compression rate of 0.5 used in semantic communications fails to recover the license plate number of interest to the receiver due to the out-of-distribution problem. The peak signal-to-noise ratio (PSNR) of (b) is 15. 97 dB. The autoencoder is pre-trained on the MNIST dataset726791 which consists of 70000 handwritten digits images.
  • Figure 2: Overall framework of the proposed receiver-centric generative semantic communication system.
  • Figure 3: Selected video frames where the objects highlighted in red boxes may be of interest to the receiver.
  • Figure 4: Performance of Task Reflection, where $\bar{N}$ in x-axis is a parameter that controls maximum number of iterations in Algorithm \ref{['alg:transmitter']}.