Energy-Efficient Downlink Semantic Generative Communication with Text-to-Image Generators

Hyein Lee; Jihong Park; Sooyoung Kim; Jinho Choi

doi:10.1109/GCWkshps58843.2023.10464910

Energy-Efficient Downlink Semantic Generative Communication with Text-to-Image Generators

Hyein Lee
, Jihong Park^*
, Sooyoung Kim^*
, Jinho Choi^*

^*Corresponding author for this work

Division of Electronic Engineering

Jeonbuk National University
Deakin University

Research output: Contribution to conference › Conference paper › peer-review

7 Scopus citations

Abstract

In this paper, we introduce a novel semantic generative communication (SGC) framework, where generative users leverage text-to-image (T2I) generators to create images locally from downloaded text prompts, while non-generative users directly download images from a base station (BS). Although generative users help reduce downlink transmission energy at the BS, they consume additional energy for image generation and for uploading their generator state information (GSI). We formulate the problem of minimizing the total energy consumption of the BS and the users, and devise a generative user selection algorithm. Simulation results corroborate that our proposed algorithm reduces total energy by up to 54% compared to a baseline with all non-generative users.

Original language	English
Title of host publication	2023 IEEE Globecom Workshops, GC Wkshps 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1291-1296
Number of pages	6
ISBN (Electronic)	9798350370218
DOIs	https://doi.org/10.1109/GCWkshps58843.2023.10464910
State	Published - 2023
Event	2023 IEEE Globecom Workshops, GC Wkshps 2023 - Kuala Lumpur, Malaysia Duration: 2023.12.4 → 2023.12.8

Publication series

Name	2023 IEEE Globecom Workshops, GC Wkshps 2023

Conference

Conference	2023 IEEE Globecom Workshops, GC Wkshps 2023
Country/Territory	Malaysia
City	Kuala Lumpur
Period	23.12.4 → 23.12.8

Keywords

bi-nary linear integer programming
generative model
Semantic communication

Quacquarelli Symonds(QS) Subject Topics

Computer Science & Information Systems
Engineering - Electrical & Electronic
Communication & Media Studies
Engineering - Petroleum

Access to Document

10.1109/GCWkshps58843.2023.10464910

Cite this

@inproceedings{2b55b28be32a44d494e38489b8ace8d7,

title = "Energy-Efficient Downlink Semantic Generative Communication with Text-to-Image Generators",

abstract = "In this paper, we introduce a novel semantic generative communication (SGC) framework, where generative users leverage text-to-image (T2I) generators to create images locally from downloaded text prompts, while non-generative users directly download images from a base station (BS). Although generative users help reduce downlink transmission energy at the BS, they consume additional energy for image generation and for uploading their generator state information (GSI). We formulate the problem of minimizing the total energy consumption of the BS and the users, and devise a generative user selection algorithm. Simulation results corroborate that our proposed algorithm reduces total energy by up to 54\% compared to a baseline with all non-generative users.",

keywords = "bi-nary linear integer programming, generative model, Semantic communication",

author = "Hyein Lee and Jihong Park and Sooyoung Kim and Jinho Choi",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Globecom Workshops, GC Wkshps 2023 ; Conference date: 04-12-2023 Through 08-12-2023",

year = "2023",

doi = "10.1109/GCWkshps58843.2023.10464910",

language = "English",

series = "2023 IEEE Globecom Workshops, GC Wkshps 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1291--1296",

booktitle = "2023 IEEE Globecom Workshops, GC Wkshps 2023",

}

Lee, H, Park, J, Kim, S & Choi, J 2023, Energy-Efficient Downlink Semantic Generative Communication with Text-to-Image Generators. in 2023 IEEE Globecom Workshops, GC Wkshps 2023. 2023 IEEE Globecom Workshops, GC Wkshps 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1291-1296, 2023 IEEE Globecom Workshops, GC Wkshps 2023, Kuala Lumpur, Malaysia, 23.12.4. https://doi.org/10.1109/GCWkshps58843.2023.10464910

Energy-Efficient Downlink Semantic Generative Communication with Text-to-Image Generators. / Lee, Hyein; Park, Jihong; Kim, Sooyoung et al.
2023 IEEE Globecom Workshops, GC Wkshps 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1291-1296 (2023 IEEE Globecom Workshops, GC Wkshps 2023).

Research output: Contribution to conference › Conference paper › peer-review

TY - GEN

T1 - Energy-Efficient Downlink Semantic Generative Communication with Text-to-Image Generators

AU - Lee, Hyein

AU - Park, Jihong

AU - Kim, Sooyoung

AU - Choi, Jinho

PY - 2023

Y1 - 2023

N2 - In this paper, we introduce a novel semantic generative communication (SGC) framework, where generative users leverage text-to-image (T2I) generators to create images locally from downloaded text prompts, while non-generative users directly download images from a base station (BS). Although generative users help reduce downlink transmission energy at the BS, they consume additional energy for image generation and for uploading their generator state information (GSI). We formulate the problem of minimizing the total energy consumption of the BS and the users, and devise a generative user selection algorithm. Simulation results corroborate that our proposed algorithm reduces total energy by up to 54% compared to a baseline with all non-generative users.

AB - In this paper, we introduce a novel semantic generative communication (SGC) framework, where generative users leverage text-to-image (T2I) generators to create images locally from downloaded text prompts, while non-generative users directly download images from a base station (BS). Although generative users help reduce downlink transmission energy at the BS, they consume additional energy for image generation and for uploading their generator state information (GSI). We formulate the problem of minimizing the total energy consumption of the BS and the users, and devise a generative user selection algorithm. Simulation results corroborate that our proposed algorithm reduces total energy by up to 54% compared to a baseline with all non-generative users.

KW - bi-nary linear integer programming

KW - generative model

KW - Semantic communication

UR - https://www.scopus.com/pages/publications/85172780614

U2 - 10.1109/GCWkshps58843.2023.10464910

DO - 10.1109/GCWkshps58843.2023.10464910

M3 - Conference paper

AN - SCOPUS:85172780614

T3 - 2023 IEEE Globecom Workshops, GC Wkshps 2023

SP - 1291

EP - 1296

BT - 2023 IEEE Globecom Workshops, GC Wkshps 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Globecom Workshops, GC Wkshps 2023

Y2 - 4 December 2023 through 8 December 2023

ER -

Energy-Efficient Downlink Semantic Generative Communication with Text-to-Image Generators

Abstract

Publication series

Conference

Keywords

Quacquarelli Symonds(QS) Subject Topics

Access to Document

Other files and links

Fingerprint

Cite this