Transfer prior knowledge from surrogate modelling: A meta-learning approach

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

  • Minghui Cheng
  • Chao Dang
  • Dan M. Frangopol
  • Michael Beer
  • Xian-Xun Yuan

Externe Organisationen

  • The University of Liverpool
  • Tongji University
  • Lehigh University
  • Ryerson University
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Aufsatznummer106719
FachzeitschriftComputers and Structures
Jahrgang260
Frühes Online-Datum9 Dez. 2021
PublikationsstatusVeröffentlicht - Feb. 2022

Abstract

Surrogate modelling has emerged as a useful technique to study complex physical and engineering systems in various disciplines, especially for engineering analysis. Previous studies mostly focused on developing new surrogate models and/or applying existing surrogate models to practical problems. Despite the computational efficiency, the surrogate for a new task is often built from scratch and the knowledge gained from previous surrogate modelling for similar tasks is neglected. As the need for quickly modifying simulation models to reflect design changes has significantly increased, one potential solution is to utilize prior knowledge from surrogate modelling. In this study, a novel meta-learning-based surrogate modelling framework is presented. The framework includes two phases: a meta-training and a few-shot learning phase. A meta-model that represents a family of tasks and the adaptation of this model to a new task with few data points are the results of the first and second phase, respectively. The study specifies the scope of the framework by classifying similar tasks. Applications of the framework to global sensitivity analysis, optimization, and reliability analysis are also addressed. Four numerical experiments are performed to demonstrate the feasibility and applicability of the framework.

ASJC Scopus Sachgebiete

Zitieren

Transfer prior knowledge from surrogate modelling: A meta-learning approach. / Cheng, Minghui; Dang, Chao; Frangopol, Dan M. et al.
in: Computers and Structures, Jahrgang 260, 106719, 02.2022.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Cheng M, Dang C, Frangopol DM, Beer M, Yuan XX. Transfer prior knowledge from surrogate modelling: A meta-learning approach. Computers and Structures. 2022 Feb;260:106719. Epub 2021 Dez 9. doi: 10.1016/j.compstruc.2021.106719
Cheng, Minghui ; Dang, Chao ; Frangopol, Dan M. et al. / Transfer prior knowledge from surrogate modelling : A meta-learning approach. in: Computers and Structures. 2022 ; Jahrgang 260.
Download
@article{72d9de8b35244ea6a41eef76cb5d2c92,
title = "Transfer prior knowledge from surrogate modelling: A meta-learning approach",
abstract = "Surrogate modelling has emerged as a useful technique to study complex physical and engineering systems in various disciplines, especially for engineering analysis. Previous studies mostly focused on developing new surrogate models and/or applying existing surrogate models to practical problems. Despite the computational efficiency, the surrogate for a new task is often built from scratch and the knowledge gained from previous surrogate modelling for similar tasks is neglected. As the need for quickly modifying simulation models to reflect design changes has significantly increased, one potential solution is to utilize prior knowledge from surrogate modelling. In this study, a novel meta-learning-based surrogate modelling framework is presented. The framework includes two phases: a meta-training and a few-shot learning phase. A meta-model that represents a family of tasks and the adaptation of this model to a new task with few data points are the results of the first and second phase, respectively. The study specifies the scope of the framework by classifying similar tasks. Applications of the framework to global sensitivity analysis, optimization, and reliability analysis are also addressed. Four numerical experiments are performed to demonstrate the feasibility and applicability of the framework.",
keywords = "Knowledge transfer, Meta-learning-based surrogate modelling, Model-agnostic meta-learning, Surrogate modelling",
author = "Minghui Cheng and Chao Dang and Frangopol, {Dan M.} and Michael Beer and Xian-Xun Yuan",
note = "Funding Information: The second author is grateful for the financial support received from China Scholarship Council (CSC). ",
year = "2022",
month = feb,
doi = "10.1016/j.compstruc.2021.106719",
language = "English",
volume = "260",
journal = "Computers and Structures",
issn = "0045-7949",
publisher = "Elsevier Ltd.",

}

Download

TY - JOUR

T1 - Transfer prior knowledge from surrogate modelling

T2 - A meta-learning approach

AU - Cheng, Minghui

AU - Dang, Chao

AU - Frangopol, Dan M.

AU - Beer, Michael

AU - Yuan, Xian-Xun

N1 - Funding Information: The second author is grateful for the financial support received from China Scholarship Council (CSC).

PY - 2022/2

Y1 - 2022/2

N2 - Surrogate modelling has emerged as a useful technique to study complex physical and engineering systems in various disciplines, especially for engineering analysis. Previous studies mostly focused on developing new surrogate models and/or applying existing surrogate models to practical problems. Despite the computational efficiency, the surrogate for a new task is often built from scratch and the knowledge gained from previous surrogate modelling for similar tasks is neglected. As the need for quickly modifying simulation models to reflect design changes has significantly increased, one potential solution is to utilize prior knowledge from surrogate modelling. In this study, a novel meta-learning-based surrogate modelling framework is presented. The framework includes two phases: a meta-training and a few-shot learning phase. A meta-model that represents a family of tasks and the adaptation of this model to a new task with few data points are the results of the first and second phase, respectively. The study specifies the scope of the framework by classifying similar tasks. Applications of the framework to global sensitivity analysis, optimization, and reliability analysis are also addressed. Four numerical experiments are performed to demonstrate the feasibility and applicability of the framework.

AB - Surrogate modelling has emerged as a useful technique to study complex physical and engineering systems in various disciplines, especially for engineering analysis. Previous studies mostly focused on developing new surrogate models and/or applying existing surrogate models to practical problems. Despite the computational efficiency, the surrogate for a new task is often built from scratch and the knowledge gained from previous surrogate modelling for similar tasks is neglected. As the need for quickly modifying simulation models to reflect design changes has significantly increased, one potential solution is to utilize prior knowledge from surrogate modelling. In this study, a novel meta-learning-based surrogate modelling framework is presented. The framework includes two phases: a meta-training and a few-shot learning phase. A meta-model that represents a family of tasks and the adaptation of this model to a new task with few data points are the results of the first and second phase, respectively. The study specifies the scope of the framework by classifying similar tasks. Applications of the framework to global sensitivity analysis, optimization, and reliability analysis are also addressed. Four numerical experiments are performed to demonstrate the feasibility and applicability of the framework.

KW - Knowledge transfer

KW - Meta-learning-based surrogate modelling

KW - Model-agnostic meta-learning

KW - Surrogate modelling

UR - http://www.scopus.com/inward/record.url?scp=85120950147&partnerID=8YFLogxK

U2 - 10.1016/j.compstruc.2021.106719

DO - 10.1016/j.compstruc.2021.106719

M3 - Article

AN - SCOPUS:85120950147

VL - 260

JO - Computers and Structures

JF - Computers and Structures

SN - 0045-7949

M1 - 106719

ER -

Von denselben Autoren