The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Pembenaman rangkaian telah menarik perhatian yang semakin meningkat dalam beberapa tahun kebelakangan ini disebabkan oleh aplikasinya yang meluas dalam tugas perlombongan graf seperti klasifikasi puncak, pengesanan komuniti dan visualisasi rangkaian. Pembenaman rangkaian ialah kaedah penting untuk mempelajari perwakilan berdimensi rendah bagi bucu dalam rangkaian, bertujuan untuk menangkap dan memelihara struktur rangkaian. Hampir semua kaedah pembenaman rangkaian sedia ada menggunakan model Skip-gram yang dipanggil dalam Word2vec. Walau bagaimanapun, sebagai model beg-of-words, model langkau-gram menggunakan terutamanya maklumat struktur tempatan. Kekurangan metrik maklumat untuk bucu dalam rangkaian global membawa kepada gabungan bucu dengan label berbeza dalam ruang benam baharu. Untuk menyelesaikan masalah ini, dalam kertas kerja ini kami mencadangkan kaedah Pembelajaran Perwakilan Rangkaian dengan Pembelajaran Metrik Dalam, iaitu DML-NRL. Dengan menetapkan bucu sauh yang dimulakan dan menambah ukuran persamaan dalam kemajuan latihan, maklumat jarak antara label bucu yang berbeza dalam rangkaian disepadukan ke dalam perwakilan bucu, yang meningkatkan ketepatan algoritma pembenaman rangkaian dengan berkesan. Kami membandingkan kaedah kami dengan garis dasar dengan menerapkannya pada tugas klasifikasi berbilang label dan visualisasi data bucu. Keputusan percubaan menunjukkan bahawa kaedah kami mengatasi garis dasar dalam ketiga-tiga set data, dan kaedah tersebut telah terbukti berkesan dan teguh.
Xiaotao CHENG
National Digital Switching System Engineering & Technological R&D Center
Lixin JI
National Digital Switching System Engineering & Technological R&D Center
Ruiyang HUANG
National Digital Switching System Engineering & Technological R&D Center
Ruifei CUI
Radboud University Nijmegen
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Xiaotao CHENG, Lixin JI, Ruiyang HUANG, Ruifei CUI, "Network Embedding with Deep Metric Learning" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 3, pp. 568-578, March 2019, doi: 10.1587/transinf.2018EDP7233.
Abstract: Network embedding has attracted an increasing amount of attention in recent years due to its wide-ranging applications in graph mining tasks such as vertex classification, community detection, and network visualization. Network embedding is an important method to learn low-dimensional representations of vertices in networks, aiming to capture and preserve the network structure. Almost all the existing network embedding methods adopt the so-called Skip-gram model in Word2vec. However, as a bag-of-words model, the skip-gram model mainly utilized the local structure information. The lack of information metrics for vertices in global network leads to the mix of vertices with different labels in the new embedding space. To solve this problem, in this paper we propose a Network Representation Learning method with Deep Metric Learning, namely DML-NRL. By setting the initialized anchor vertices and adding the similarity measure in the training progress, the distance information between different labels of vertices in the network is integrated into the vertex representation, which improves the accuracy of network embedding algorithm effectively. We compare our method with baselines by applying them to the tasks of multi-label classification and data visualization of vertices. The experimental results show that our method outperforms the baselines in all three datasets, and the method has proved to be effective and robust.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7233/_p
Salinan
@ARTICLE{e102-d_3_568,
author={Xiaotao CHENG, Lixin JI, Ruiyang HUANG, Ruifei CUI, },
journal={IEICE TRANSACTIONS on Information},
title={Network Embedding with Deep Metric Learning},
year={2019},
volume={E102-D},
number={3},
pages={568-578},
abstract={Network embedding has attracted an increasing amount of attention in recent years due to its wide-ranging applications in graph mining tasks such as vertex classification, community detection, and network visualization. Network embedding is an important method to learn low-dimensional representations of vertices in networks, aiming to capture and preserve the network structure. Almost all the existing network embedding methods adopt the so-called Skip-gram model in Word2vec. However, as a bag-of-words model, the skip-gram model mainly utilized the local structure information. The lack of information metrics for vertices in global network leads to the mix of vertices with different labels in the new embedding space. To solve this problem, in this paper we propose a Network Representation Learning method with Deep Metric Learning, namely DML-NRL. By setting the initialized anchor vertices and adding the similarity measure in the training progress, the distance information between different labels of vertices in the network is integrated into the vertex representation, which improves the accuracy of network embedding algorithm effectively. We compare our method with baselines by applying them to the tasks of multi-label classification and data visualization of vertices. The experimental results show that our method outperforms the baselines in all three datasets, and the method has proved to be effective and robust.},
keywords={},
doi={10.1587/transinf.2018EDP7233},
ISSN={1745-1361},
month={March},}
Salinan
TY - JOUR
TI - Network Embedding with Deep Metric Learning
T2 - IEICE TRANSACTIONS on Information
SP - 568
EP - 578
AU - Xiaotao CHENG
AU - Lixin JI
AU - Ruiyang HUANG
AU - Ruifei CUI
PY - 2019
DO - 10.1587/transinf.2018EDP7233
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2019
AB - Network embedding has attracted an increasing amount of attention in recent years due to its wide-ranging applications in graph mining tasks such as vertex classification, community detection, and network visualization. Network embedding is an important method to learn low-dimensional representations of vertices in networks, aiming to capture and preserve the network structure. Almost all the existing network embedding methods adopt the so-called Skip-gram model in Word2vec. However, as a bag-of-words model, the skip-gram model mainly utilized the local structure information. The lack of information metrics for vertices in global network leads to the mix of vertices with different labels in the new embedding space. To solve this problem, in this paper we propose a Network Representation Learning method with Deep Metric Learning, namely DML-NRL. By setting the initialized anchor vertices and adding the similarity measure in the training progress, the distance information between different labels of vertices in the network is integrated into the vertex representation, which improves the accuracy of network embedding algorithm effectively. We compare our method with baselines by applying them to the tasks of multi-label classification and data visualization of vertices. The experimental results show that our method outperforms the baselines in all three datasets, and the method has proved to be effective and robust.
ER -