Extractive convolutional adversarial networks for network embedding

Xiaorui QIN; Yanghui RAO; Haoran XIE; Jian YIN; Fu Lee WANG

doi:10.1007/s11280-019-00740-7

Extractive convolutional adversarial networks for network embedding

Xiaorui QIN, Yanghui RAO, Haoran XIE, Jian YIN, Fu Lee WANG

Department of Computing and Decision Sciences

Research output: Journal Publications › Journal Article (refereed) › peer-review

3 Citations (Scopus)

Abstract

Network embedding plays an important role in various real-world applications. Most traditional algorithms focus on the topological structure while ignore the information from node attributes. The attributed information is potentially valuable to network embedding. To solve this problem, we propose a deep learning model named Extractive Convolutional Adversarial Network (ECAN) for network embedding. This model aims to extract the latent representations from the topological structure, the attributed information, and labels via three components. In the first part, ECAN extracts features from the topological structure and the attributed information of nodes separately. The second part is a prediction model, which aims to exploit labels of vertices. The third part is a convolutional adversarial model. We train it to distinguish the extractive features which are generated by the hidden layers in the extractive network from either the attributed information or the topological structure. Experiments on six real-world datasets demonstrate the effectiveness of ECAN when compared with state-of-the-art embedding algorithms.

Original language	English
Pages (from-to)	1925-1944
Number of pages	20
Journal	World Wide Web
Volume	23
Issue number	3
Early online date	23 Nov 2019
DOIs	https://doi.org/10.1007/s11280-019-00740-7
Publication status	Published - May 2020

Bibliographical note

This work was supported by Top-Up Fund (TFG-04) and Seed Fund (SFG-10) for General Research Fund / Early Career Scheme and Interdisciplinary Research Scheme of the Dean’s Research Fund 2018-19 (FLASS/DRF/IDS-3), Departmental Collaborative Research Fund 2019 (MIT/DCRF-R2/18-19), Funding Support to General Research Fund Proposal (RG 39/2019-2020R) and the Internal Research Grant (RG 90/2018-2019R) of The Education University of Hong Kong, and LEO Dr David P. Chan Institute of Data Science, Lingnan University, Hong Kong. This work was also supported by the National Key R&D Program of China (2018YFB1004404), Key R&D Program of Guangdong Province (2018B010107005), and National Natural Science Foundation of China (U1711262, U1501252, U1611264, U1711261). This article is an extended journal version of a conference paper published at BESC 2018 [5]. Some contents from the conference version are re-used in this journal article as this article is a follow-up work of the conference paper. The new contents of this article are more than 70% according to the regulation of the published journal. The new contents can be summarized in the following aspects: (1) To overcome the drawback that the training process of our basic method may be unstable, we propose a new method which exploits the idea of convolution in the network structure; (2) We add three metrics (i.e., Precision, Recall, and F1 score) to evaluate the effectiveness of different models comprehensively; (3) To test the influence of the kernel size in the hidden layers of the extractive model, the prediction model, and the convolutional adversarial model, we set this parameter to 1 and 3 for comparison; (4) Some recently developed approaches are included as baselines; (5) We conduct in-depth experiments on the proposed model to validate the effectiveness of the employed dimension reduction strategy and classifier.

Keywords

Attributed network
Convolutional neural network
Generative adversarial network
Network embedding

Access to Document

10.1007/s11280-019-00740-7

Cite this

@article{814876940bd04aa28318c129f72bb8c3,

title = "Extractive convolutional adversarial networks for network embedding",

abstract = "Network embedding plays an important role in various real-world applications. Most traditional algorithms focus on the topological structure while ignore the information from node attributes. The attributed information is potentially valuable to network embedding. To solve this problem, we propose a deep learning model named Extractive Convolutional Adversarial Network (ECAN) for network embedding. This model aims to extract the latent representations from the topological structure, the attributed information, and labels via three components. In the first part, ECAN extracts features from the topological structure and the attributed information of nodes separately. The second part is a prediction model, which aims to exploit labels of vertices. The third part is a convolutional adversarial model. We train it to distinguish the extractive features which are generated by the hidden layers in the extractive network from either the attributed information or the topological structure. Experiments on six real-world datasets demonstrate the effectiveness of ECAN when compared with state-of-the-art embedding algorithms.",

keywords = "Attributed network, Convolutional neural network, Generative adversarial network, Network embedding",

author = "Xiaorui QIN and Yanghui RAO and Haoran XIE and Jian YIN and WANG, {Fu Lee}",

note = "This work was supported by Top-Up Fund (TFG-04) and Seed Fund (SFG-10) for General Research Fund / Early Career Scheme and Interdisciplinary Research Scheme of the Dean{\textquoteright}s Research Fund 2018-19 (FLASS/DRF/IDS-3), Departmental Collaborative Research Fund 2019 (MIT/DCRF-R2/18-19), Funding Support to General Research Fund Proposal (RG 39/2019-2020R) and the Internal Research Grant (RG 90/2018-2019R) of The Education University of Hong Kong, and LEO Dr David P. Chan Institute of Data Science, Lingnan University, Hong Kong. This work was also supported by the National Key R&D Program of China (2018YFB1004404), Key R&D Program of Guangdong Province (2018B010107005), and National Natural Science Foundation of China (U1711262, U1501252, U1611264, U1711261). This article is an extended journal version of a conference paper published at BESC 2018 [5]. Some contents from the conference version are re-used in this journal article as this article is a follow-up work of the conference paper. The new contents of this article are more than 70% according to the regulation of the published journal. The new contents can be summarized in the following aspects: (1) To overcome the drawback that the training process of our basic method may be unstable, we propose a new method which exploits the idea of convolution in the network structure; (2) We add three metrics (i.e., Precision, Recall, and F1 score) to evaluate the effectiveness of different models comprehensively; (3) To test the influence of the kernel size in the hidden layers of the extractive model, the prediction model, and the convolutional adversarial model, we set this parameter to 1 and 3 for comparison; (4) Some recently developed approaches are included as baselines; (5) We conduct in-depth experiments on the proposed model to validate the effectiveness of the employed dimension reduction strategy and classifier.",

year = "2020",

month = may,

doi = "10.1007/s11280-019-00740-7",

language = "English",

volume = "23",

pages = "1925--1944",

journal = "World Wide Web",

issn = "1386-145X",

publisher = "Springer New York",

number = "3",

}

TY - JOUR

T1 - Extractive convolutional adversarial networks for network embedding

AU - QIN, Xiaorui

AU - RAO, Yanghui

AU - XIE, Haoran

AU - YIN, Jian

AU - WANG, Fu Lee

N1 - This work was supported by Top-Up Fund (TFG-04) and Seed Fund (SFG-10) for General Research Fund / Early Career Scheme and Interdisciplinary Research Scheme of the Dean’s Research Fund 2018-19 (FLASS/DRF/IDS-3), Departmental Collaborative Research Fund 2019 (MIT/DCRF-R2/18-19), Funding Support to General Research Fund Proposal (RG 39/2019-2020R) and the Internal Research Grant (RG 90/2018-2019R) of The Education University of Hong Kong, and LEO Dr David P. Chan Institute of Data Science, Lingnan University, Hong Kong. This work was also supported by the National Key R&D Program of China (2018YFB1004404), Key R&D Program of Guangdong Province (2018B010107005), and National Natural Science Foundation of China (U1711262, U1501252, U1611264, U1711261). This article is an extended journal version of a conference paper published at BESC 2018 [5]. Some contents from the conference version are re-used in this journal article as this article is a follow-up work of the conference paper. The new contents of this article are more than 70% according to the regulation of the published journal. The new contents can be summarized in the following aspects: (1) To overcome the drawback that the training process of our basic method may be unstable, we propose a new method which exploits the idea of convolution in the network structure; (2) We add three metrics (i.e., Precision, Recall, and F1 score) to evaluate the effectiveness of different models comprehensively; (3) To test the influence of the kernel size in the hidden layers of the extractive model, the prediction model, and the convolutional adversarial model, we set this parameter to 1 and 3 for comparison; (4) Some recently developed approaches are included as baselines; (5) We conduct in-depth experiments on the proposed model to validate the effectiveness of the employed dimension reduction strategy and classifier.

PY - 2020/5

Y1 - 2020/5

N2 - Network embedding plays an important role in various real-world applications. Most traditional algorithms focus on the topological structure while ignore the information from node attributes. The attributed information is potentially valuable to network embedding. To solve this problem, we propose a deep learning model named Extractive Convolutional Adversarial Network (ECAN) for network embedding. This model aims to extract the latent representations from the topological structure, the attributed information, and labels via three components. In the first part, ECAN extracts features from the topological structure and the attributed information of nodes separately. The second part is a prediction model, which aims to exploit labels of vertices. The third part is a convolutional adversarial model. We train it to distinguish the extractive features which are generated by the hidden layers in the extractive network from either the attributed information or the topological structure. Experiments on six real-world datasets demonstrate the effectiveness of ECAN when compared with state-of-the-art embedding algorithms.

AB - Network embedding plays an important role in various real-world applications. Most traditional algorithms focus on the topological structure while ignore the information from node attributes. The attributed information is potentially valuable to network embedding. To solve this problem, we propose a deep learning model named Extractive Convolutional Adversarial Network (ECAN) for network embedding. This model aims to extract the latent representations from the topological structure, the attributed information, and labels via three components. In the first part, ECAN extracts features from the topological structure and the attributed information of nodes separately. The second part is a prediction model, which aims to exploit labels of vertices. The third part is a convolutional adversarial model. We train it to distinguish the extractive features which are generated by the hidden layers in the extractive network from either the attributed information or the topological structure. Experiments on six real-world datasets demonstrate the effectiveness of ECAN when compared with state-of-the-art embedding algorithms.

KW - Attributed network

KW - Convolutional neural network

KW - Generative adversarial network

KW - Network embedding

UR - http://www.scopus.com/inward/record.url?scp=85075356200&partnerID=8YFLogxK

U2 - 10.1007/s11280-019-00740-7

DO - 10.1007/s11280-019-00740-7

M3 - Journal Article (refereed)

SN - 1386-145X

VL - 23

SP - 1925

EP - 1944

JO - World Wide Web

JF - World Wide Web

IS - 3

ER -

Extractive convolutional adversarial networks for network embedding

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this