Locally linear ensemble for regression

Seokho Kang, Pilsung Kang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Considerable research effort has been dedicated to the development of prediction models for yielding greater prediction accuracy in regression problems. Although non-linear models have achieved superior prediction accuracy by addressing the non-linearity of complex data, linear models are still favored because of their high prediction speed. In this study, a locally linear ensemble regression (LLER) is proposed in order to effectively address non-linearity while maintaining the advantage of linear models. The LLER predicts new instances based on multiple linear models that are trained on the regions that identify the local linearity of data. To achieve this, data are decomposed into several locally linear regions based on an expectation-maximization procedure, and linear models are built as local experts for each region to constitute an ensemble. We demonstrate the effectiveness of the LLER through experimental validation with benchmark datasets.

Original languageEnglish
Pages (from-to)199-209
Number of pages11
JournalInformation Sciences
Volume432
DOIs
Publication statusPublished - 2018 Mar 1

Fingerprint

Linear Model
Ensemble
Regression
Linear regression
Prediction
Nonlinearity
Expectation Maximization
Experimental Validation
Multiple Models
Linearity
Prediction Model
Nonlinear Model
Benchmark
Predict
Demonstrate
Prediction accuracy

Keywords

  • Ensemble learning
  • Linear model
  • Local expert
  • Locally linear ensemble
  • Regression

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

Locally linear ensemble for regression. / Kang, Seokho; Kang, Pilsung.

In: Information Sciences, Vol. 432, 01.03.2018, p. 199-209.

Research output: Contribution to journalArticle

Kang, Seokho ; Kang, Pilsung. / Locally linear ensemble for regression. In: Information Sciences. 2018 ; Vol. 432. pp. 199-209.
@article{7660105c4c4a4b80b7f032b3998d9f29,
title = "Locally linear ensemble for regression",
abstract = "Considerable research effort has been dedicated to the development of prediction models for yielding greater prediction accuracy in regression problems. Although non-linear models have achieved superior prediction accuracy by addressing the non-linearity of complex data, linear models are still favored because of their high prediction speed. In this study, a locally linear ensemble regression (LLER) is proposed in order to effectively address non-linearity while maintaining the advantage of linear models. The LLER predicts new instances based on multiple linear models that are trained on the regions that identify the local linearity of data. To achieve this, data are decomposed into several locally linear regions based on an expectation-maximization procedure, and linear models are built as local experts for each region to constitute an ensemble. We demonstrate the effectiveness of the LLER through experimental validation with benchmark datasets.",
keywords = "Ensemble learning, Linear model, Local expert, Locally linear ensemble, Regression",
author = "Seokho Kang and Pilsung Kang",
year = "2018",
month = "3",
day = "1",
doi = "10.1016/j.ins.2017.12.022",
language = "English",
volume = "432",
pages = "199--209",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Locally linear ensemble for regression

AU - Kang, Seokho

AU - Kang, Pilsung

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Considerable research effort has been dedicated to the development of prediction models for yielding greater prediction accuracy in regression problems. Although non-linear models have achieved superior prediction accuracy by addressing the non-linearity of complex data, linear models are still favored because of their high prediction speed. In this study, a locally linear ensemble regression (LLER) is proposed in order to effectively address non-linearity while maintaining the advantage of linear models. The LLER predicts new instances based on multiple linear models that are trained on the regions that identify the local linearity of data. To achieve this, data are decomposed into several locally linear regions based on an expectation-maximization procedure, and linear models are built as local experts for each region to constitute an ensemble. We demonstrate the effectiveness of the LLER through experimental validation with benchmark datasets.

AB - Considerable research effort has been dedicated to the development of prediction models for yielding greater prediction accuracy in regression problems. Although non-linear models have achieved superior prediction accuracy by addressing the non-linearity of complex data, linear models are still favored because of their high prediction speed. In this study, a locally linear ensemble regression (LLER) is proposed in order to effectively address non-linearity while maintaining the advantage of linear models. The LLER predicts new instances based on multiple linear models that are trained on the regions that identify the local linearity of data. To achieve this, data are decomposed into several locally linear regions based on an expectation-maximization procedure, and linear models are built as local experts for each region to constitute an ensemble. We demonstrate the effectiveness of the LLER through experimental validation with benchmark datasets.

KW - Ensemble learning

KW - Linear model

KW - Local expert

KW - Locally linear ensemble

KW - Regression

UR - http://www.scopus.com/inward/record.url?scp=85038021510&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038021510&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2017.12.022

DO - 10.1016/j.ins.2017.12.022

M3 - Article

AN - SCOPUS:85038021510

VL - 432

SP - 199

EP - 209

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -