Saved in:
Bibliographic Details
Main Authors: Ren, Mengmeng, Qiao, Li, Yang, Long, Gao, Zhen, Chen, Jian, Mashhadi, Mahdi Boloursaz, Xiao, Pei, Tafazolli, Rahim, Bennis, Mehdi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.09715
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909598437343232
author Ren, Mengmeng
Qiao, Li
Yang, Long
Gao, Zhen
Chen, Jian
Mashhadi, Mahdi Boloursaz
Xiao, Pei
Tafazolli, Rahim
Bennis, Mehdi
author_facet Ren, Mengmeng
Qiao, Li
Yang, Long
Gao, Zhen
Chen, Jian
Mashhadi, Mahdi Boloursaz
Xiao, Pei
Tafazolli, Rahim
Bennis, Mehdi
contents This paper develops an edge-device collaborative Generative Semantic Communications (Gen SemCom) framework leveraging pre-trained Multi-modal/Vision Language Models (M/VLMs) for ultra-low-rate semantic communication via textual prompts. The proposed framework optimizes the use of M/VLMs on the wireless edge/device to generate high-fidelity textual prompts through visual captioning/question answering, which are then transmitted over a wireless channel for SemCom. Specifically, we develop a multi-user Gen SemCom framework using pre-trained M/VLMs, and formulate a joint optimization problem of prompt generation offloading, communication and computation resource allocation to minimize the latency and maximize the resulting semantic quality. Due to the nonconvex nature of the problem with highly coupled discrete and continuous variables, we decompose it as a two-level problem and propose a low-complexity swap/leaving/joining (SLJ)-based matching algorithm. Simulation results demonstrate significant performance improvements over the conventional semanticunaware/non-collaborative offloading benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2409_09715
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generative Semantic Communication via Textual Prompts: Latency Performance Tradeoffs
Ren, Mengmeng
Qiao, Li
Yang, Long
Gao, Zhen
Chen, Jian
Mashhadi, Mahdi Boloursaz
Xiao, Pei
Tafazolli, Rahim
Bennis, Mehdi
Information Theory
Computer Science and Game Theory
This paper develops an edge-device collaborative Generative Semantic Communications (Gen SemCom) framework leveraging pre-trained Multi-modal/Vision Language Models (M/VLMs) for ultra-low-rate semantic communication via textual prompts. The proposed framework optimizes the use of M/VLMs on the wireless edge/device to generate high-fidelity textual prompts through visual captioning/question answering, which are then transmitted over a wireless channel for SemCom. Specifically, we develop a multi-user Gen SemCom framework using pre-trained M/VLMs, and formulate a joint optimization problem of prompt generation offloading, communication and computation resource allocation to minimize the latency and maximize the resulting semantic quality. Due to the nonconvex nature of the problem with highly coupled discrete and continuous variables, we decompose it as a two-level problem and propose a low-complexity swap/leaving/joining (SLJ)-based matching algorithm. Simulation results demonstrate significant performance improvements over the conventional semanticunaware/non-collaborative offloading benchmarks.
title Generative Semantic Communication via Textual Prompts: Latency Performance Tradeoffs
topic Information Theory
Computer Science and Game Theory
url https://arxiv.org/abs/2409.09715