A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood Structure

Network embedding is a very important task to represent the high-dimensional network in a low-dimensional vector space, which aims to capture and preserve the network structure. Most existing network embedding methods are based on shallow models. However, actual network structures are complicated wh...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenmao Wu, Zhizhou Yu, Jieyue He
Format: Article
Language:English
Published: Tsinghua University Press 2019-09-01
Series:Big Data Mining and Analytics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2019.9020004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832568932365500416
author Wenmao Wu
Zhizhou Yu
Jieyue He
author_facet Wenmao Wu
Zhizhou Yu
Jieyue He
author_sort Wenmao Wu
collection DOAJ
description Network embedding is a very important task to represent the high-dimensional network in a low-dimensional vector space, which aims to capture and preserve the network structure. Most existing network embedding methods are based on shallow models. However, actual network structures are complicated which means shallow models cannot obtain the high-dimensional nonlinear features of the network well. The recently proposed unsupervised deep learning models ignore the labels information. To address these challenges, in this paper, we propose an effective network embedding method of Structural Labeled Locally Deep Nonlinear Embedding (SLLDNE). SLLDNE is designed to obtain highly nonlinear features through utilizing deep neural network while preserving the label information of the nodes by using a semi-supervised classifier component to improve the ability of discriminations. Moreover, we exploit linear reconstruction of neighborhood nodes to enable the model to get more structural information. The experimental results of vertex classification on two real-world network datasets demonstrate that SLLDNE outperforms the other state-of-the-art methods.
format Article
id doaj-art-a670ac7f9d984ab1b80ccd97db496e83
institution Kabale University
issn 2096-0654
language English
publishDate 2019-09-01
publisher Tsinghua University Press
record_format Article
series Big Data Mining and Analytics
spelling doaj-art-a670ac7f9d984ab1b80ccd97db496e832025-02-02T23:47:57ZengTsinghua University PressBig Data Mining and Analytics2096-06542019-09-012320521610.26599/BDMA.2019.9020004A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood StructureWenmao Wu0Zhizhou Yu1Jieyue He2<institution content-type="dept">School of Computer Science and Engineering, and also with MOE Key Laboratory of Computer Network and Information Integration</institution>, <institution>Southeast University</institution>, <city>Nanjing</city> <postal-code>211100</postal-code>, <country>China</country>.<institution content-type="dept">School of Computer Science and Engineering, and also with MOE Key Laboratory of Computer Network and Information Integration</institution>, <institution>Southeast University</institution>, <city>Nanjing</city> <postal-code>211100</postal-code>, <country>China</country>.<institution content-type="dept">School of Computer Science and Engineering, and also with MOE Key Laboratory of Computer Network and Information Integration</institution>, <institution>Southeast University</institution>, <city>Nanjing</city> <postal-code>211100</postal-code>, <country>China</country>.Network embedding is a very important task to represent the high-dimensional network in a low-dimensional vector space, which aims to capture and preserve the network structure. Most existing network embedding methods are based on shallow models. However, actual network structures are complicated which means shallow models cannot obtain the high-dimensional nonlinear features of the network well. The recently proposed unsupervised deep learning models ignore the labels information. To address these challenges, in this paper, we propose an effective network embedding method of Structural Labeled Locally Deep Nonlinear Embedding (SLLDNE). SLLDNE is designed to obtain highly nonlinear features through utilizing deep neural network while preserving the label information of the nodes by using a semi-supervised classifier component to improve the ability of discriminations. Moreover, we exploit linear reconstruction of neighborhood nodes to enable the model to get more structural information. The experimental results of vertex classification on two real-world network datasets demonstrate that SLLDNE outperforms the other state-of-the-art methods.https://www.sciopen.com/article/10.26599/BDMA.2019.9020004network embeddingdeep learningnetwork analysis
spellingShingle Wenmao Wu
Zhizhou Yu
Jieyue He
A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood Structure
Big Data Mining and Analytics
network embedding
deep learning
network analysis
title A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood Structure
title_full A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood Structure
title_fullStr A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood Structure
title_full_unstemmed A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood Structure
title_short A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood Structure
title_sort semi supervised deep network embedding approach based on the neighborhood structure
topic network embedding
deep learning
network analysis
url https://www.sciopen.com/article/10.26599/BDMA.2019.9020004
work_keys_str_mv AT wenmaowu asemisuperviseddeepnetworkembeddingapproachbasedontheneighborhoodstructure
AT zhizhouyu asemisuperviseddeepnetworkembeddingapproachbasedontheneighborhoodstructure
AT jieyuehe asemisuperviseddeepnetworkembeddingapproachbasedontheneighborhoodstructure
AT wenmaowu semisuperviseddeepnetworkembeddingapproachbasedontheneighborhoodstructure
AT zhizhouyu semisuperviseddeepnetworkembeddingapproachbasedontheneighborhoodstructure
AT jieyuehe semisuperviseddeepnetworkembeddingapproachbasedontheneighborhoodstructure