Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature Representation
Extreme learning machine is characterized by less training parameters, fast training speed, and strong generalization ability. It has been applied to obtain feature representations from the complex data in the tasks of data clustering or classification. In this paper, a graph embedding-based denoisi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8620205/ |
id |
doaj-1251a15fd25541228baefa2b3f78b6f7 |
---|---|
record_format |
Article |
spelling |
doaj-1251a15fd25541228baefa2b3f78b6f72021-03-29T22:34:42ZengIEEEIEEE Access2169-35362019-01-017134331344410.1109/ACCESS.2019.28940148620205Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature RepresentationHongwei Ge0https://orcid.org/0000-0002-8937-1515Weiting Sun1Mingde Zhao2https://orcid.org/0000-0002-6687-8153Yao Yao3College of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaCollege of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaSchool of Computer Science, McGill University, Montreal, QC, CanadaCollege of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaExtreme learning machine is characterized by less training parameters, fast training speed, and strong generalization ability. It has been applied to obtain feature representations from the complex data in the tasks of data clustering or classification. In this paper, a graph embedding-based denoising extreme learning machine autoencoder (GDELM-AE) is proposed for capturing the structure of the inputs. Specifically, in GDELM-AE, a graph embedding framework that contains an intrinsic graph and a penalty graph constructed by local Fisher discrimination analysis is integrated into the autoencoder. So, it can exploit both local structure and global structure information in extreme learning machine (ELM) spaces. Further, we propose a stacked graph embedded denoising (SGD)-ELM by stacking several GDELM-AEs. The experimental results on several benchmarks validate that GDELM-AE can obtain efficient and robust feature representation of original data; moreover, the stacked GDELM-AE can obtain high-level and noise-robust representations. The comparative results with the state-of-the-art algorithms indicate that the proposed algorithm can obtain better accuracy as well as faster training speed.https://ieeexplore.ieee.org/document/8620205/Extreme learning machinestacked autoencoderdenoisinggraph embedding |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hongwei Ge Weiting Sun Mingde Zhao Yao Yao |
spellingShingle |
Hongwei Ge Weiting Sun Mingde Zhao Yao Yao Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature Representation IEEE Access Extreme learning machine stacked autoencoder denoising graph embedding |
author_facet |
Hongwei Ge Weiting Sun Mingde Zhao Yao Yao |
author_sort |
Hongwei Ge |
title |
Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature Representation |
title_short |
Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature Representation |
title_full |
Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature Representation |
title_fullStr |
Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature Representation |
title_full_unstemmed |
Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature Representation |
title_sort |
stacked denoising extreme learning machine autoencoder based on graph embedding for feature representation |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
Extreme learning machine is characterized by less training parameters, fast training speed, and strong generalization ability. It has been applied to obtain feature representations from the complex data in the tasks of data clustering or classification. In this paper, a graph embedding-based denoising extreme learning machine autoencoder (GDELM-AE) is proposed for capturing the structure of the inputs. Specifically, in GDELM-AE, a graph embedding framework that contains an intrinsic graph and a penalty graph constructed by local Fisher discrimination analysis is integrated into the autoencoder. So, it can exploit both local structure and global structure information in extreme learning machine (ELM) spaces. Further, we propose a stacked graph embedded denoising (SGD)-ELM by stacking several GDELM-AEs. The experimental results on several benchmarks validate that GDELM-AE can obtain efficient and robust feature representation of original data; moreover, the stacked GDELM-AE can obtain high-level and noise-robust representations. The comparative results with the state-of-the-art algorithms indicate that the proposed algorithm can obtain better accuracy as well as faster training speed. |
topic |
Extreme learning machine stacked autoencoder denoising graph embedding |
url |
https://ieeexplore.ieee.org/document/8620205/ |
work_keys_str_mv |
AT hongweige stackeddenoisingextremelearningmachineautoencoderbasedongraphembeddingforfeaturerepresentation AT weitingsun stackeddenoisingextremelearningmachineautoencoderbasedongraphembeddingforfeaturerepresentation AT mingdezhao stackeddenoisingextremelearningmachineautoencoderbasedongraphembeddingforfeaturerepresentation AT yaoyao stackeddenoisingextremelearningmachineautoencoderbasedongraphembeddingforfeaturerepresentation |
_version_ |
1724191233631322112 |