Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation for Unsupervised Domain Adaptation

Extreme Learning Machine (ELM) is widely used in various fields because of its fast training and high accuracy. However, it does not primarily work well for Domain Adaptation (DA) in which there are many annotated data from auxiliary domain and few even no annotated data in target domain. In this pa...

Full description

Saved in:
Bibliographic Details
Main Authors: Shaofei Zang, Xinghai Li, Jianwei Ma, Yongyi Yan, Jinfeng Lv, Yuan Wei
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2022/2463746
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850170664198078464
author Shaofei Zang
Xinghai Li
Jianwei Ma
Yongyi Yan
Jinfeng Lv
Yuan Wei
author_facet Shaofei Zang
Xinghai Li
Jianwei Ma
Yongyi Yan
Jinfeng Lv
Yuan Wei
author_sort Shaofei Zang
collection DOAJ
description Extreme Learning Machine (ELM) is widely used in various fields because of its fast training and high accuracy. However, it does not primarily work well for Domain Adaptation (DA) in which there are many annotated data from auxiliary domain and few even no annotated data in target domain. In this paper, we propose a new variant of ELM called Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation (DELM-CDMA) for unsupervised domain adaptation. It introduces Cross-Domain Mean Approximation (CDMA) into the hidden layer of ELM to reduce distribution discrepancy between domains for domain bias elimination, which is conducive to train a high accuracy ELM on annotated data from auxiliary domains for target tasks. Linear Discriminative Analysis (LDA) is also adopted to improve the discrimination of learned model and obtain higher accuracy. Moreover, we further provide a Discriminative Kernel Extreme Learning Machine with Cross-Domain Mean Approximation (DKELM-CDMA) as the kernelization extension of DELM-CDMA. Some experiments are performed to investigate the proposed approach, and the result shows that DELM-CDMA and DKELM-CDMA could effectively extend ELM suitable for domain adaptation and outperform ELM and many other domain adaptation approaches.
format Article
id doaj-art-9b32c9cfb67f48bf98050013eca95efd
institution OA Journals
issn 1099-0526
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-9b32c9cfb67f48bf98050013eca95efd2025-08-20T02:20:26ZengWileyComplexity1099-05262022-01-01202210.1155/2022/2463746Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation for Unsupervised Domain AdaptationShaofei Zang0Xinghai Li1Jianwei Ma2Yongyi Yan3Jinfeng Lv4Yuan Wei5College of Information EngineeringCollege of Information EngineeringCollege of Information EngineeringCollege of Information EngineeringCollege of Information EngineeringCollege of Vehicle and Traffic EngineeringExtreme Learning Machine (ELM) is widely used in various fields because of its fast training and high accuracy. However, it does not primarily work well for Domain Adaptation (DA) in which there are many annotated data from auxiliary domain and few even no annotated data in target domain. In this paper, we propose a new variant of ELM called Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation (DELM-CDMA) for unsupervised domain adaptation. It introduces Cross-Domain Mean Approximation (CDMA) into the hidden layer of ELM to reduce distribution discrepancy between domains for domain bias elimination, which is conducive to train a high accuracy ELM on annotated data from auxiliary domains for target tasks. Linear Discriminative Analysis (LDA) is also adopted to improve the discrimination of learned model and obtain higher accuracy. Moreover, we further provide a Discriminative Kernel Extreme Learning Machine with Cross-Domain Mean Approximation (DKELM-CDMA) as the kernelization extension of DELM-CDMA. Some experiments are performed to investigate the proposed approach, and the result shows that DELM-CDMA and DKELM-CDMA could effectively extend ELM suitable for domain adaptation and outperform ELM and many other domain adaptation approaches.http://dx.doi.org/10.1155/2022/2463746
spellingShingle Shaofei Zang
Xinghai Li
Jianwei Ma
Yongyi Yan
Jinfeng Lv
Yuan Wei
Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation for Unsupervised Domain Adaptation
Complexity
title Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation for Unsupervised Domain Adaptation
title_full Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation for Unsupervised Domain Adaptation
title_fullStr Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation for Unsupervised Domain Adaptation
title_full_unstemmed Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation for Unsupervised Domain Adaptation
title_short Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation for Unsupervised Domain Adaptation
title_sort discriminative extreme learning machine with cross domain mean approximation for unsupervised domain adaptation
url http://dx.doi.org/10.1155/2022/2463746
work_keys_str_mv AT shaofeizang discriminativeextremelearningmachinewithcrossdomainmeanapproximationforunsuperviseddomainadaptation
AT xinghaili discriminativeextremelearningmachinewithcrossdomainmeanapproximationforunsuperviseddomainadaptation
AT jianweima discriminativeextremelearningmachinewithcrossdomainmeanapproximationforunsuperviseddomainadaptation
AT yongyiyan discriminativeextremelearningmachinewithcrossdomainmeanapproximationforunsuperviseddomainadaptation
AT jinfenglv discriminativeextremelearningmachinewithcrossdomainmeanapproximationforunsuperviseddomainadaptation
AT yuanwei discriminativeextremelearningmachinewithcrossdomainmeanapproximationforunsuperviseddomainadaptation