A Faster Converging Negative Sampling for the Graph Embedding Process in Community Detection and Link Prediction Tasks

被引：0

作者：

Loumponias, Kostas ^{[1
]}

Kosmatopoulos, Andreas ^{[1
]}

Tsikrika, Theodora ^{[1
]}

Vrochidis, Stefanos ^{[1
]}

Kompatsiaris, Ioannis ^{[1
]}

机构：

[1] Ctr Res & Technol Hellas CERTH, Informat Technol Inst, GR-54124 Thessaloniki, Greece

来源：

DELTA: PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON DEEP LEARNING THEORY AND APPLICATIONS | 2022年

基金：

欧盟地平线“2020”;

关键词：

Skipgram Algorithm; Negative Sampling; Graph Embedding; Community Detection; Link Prediction;

D O I：

10.5220/0011142000003277

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The graph embedding process aims to transform nodes and edges into a low dimensional vector space, while preserving the graph structure and topological properties. Random walk based methods are used to capture structural relationships between nodes, by performing truncated random walks. Afterwards, the SkipGram model with the negative sampling approach, is used to calculate the embedded nodes. In this paper, the proposed SkipGram model converges in fewer iterations than the standard one. Furthermore, the community detection and link prediction task is enhanced by the proposed method.

引用

页码：86 / 93

页数：8

共 20 条

[1] Exploring Alternatives to Softmax Function [J].

Banerjee, Kunal ;

Prasad, Vishak C. ;

Gupta, Rishi Raj ;

Vyas, Kartik ;

Anushree, H. ;

Mishra, Biswajit .

PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON DEEP LEARNING THEORY AND APPLICATIONS (DELTA), 2021, :81-86

[2] A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications [J].

Cai, HongYun ;

Zheng, Vincent W. ;

Chang, Kevin Chen-Chuan .

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2018, 30 (09) :1616-1637

[3] Learning Community Embedding with Community Detection and Node Embedding on Graphs [J].

Cavallari, Sandro ;

Zheng, Vincent W. ;

Cai, Hongyun ;

Chang, Kevin Chen-Chuan ;

Cambria, Erik .

CIKM'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2017, :377-386

[4]

Chowdhary K., 2020, FUNDAMENTALS ARTIFIC, P603, DOI DOI 10.1007/978-81-322-3972-7_19

[5] An introduction to ROC analysis [J].

Fawcett, Tom .

PATTERN RECOGNITION LETTERS, 2006, 27 (08) :861-874

[6] Graph embedding techniques, applications, and performance: A survey [J].

Goyal, Palash ;

Ferrara, Emilio .

KNOWLEDGE-BASED SYSTEMS, 2018, 151 :78-94

[7] node2vec: Scalable Feature Learning for Networks [J].

Grover, Aditya ;

Leskovec, Jure .

KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :855-864

[8]

Hartigan J. A., 1979, Applied Statistics, V28, P100, DOI 10.2307/2346830

[9] Bag of Tricks for Image Classification with Convolutional Neural Networks [J].

He, Tong ;

Zhang, Zhi ;

Zhang, Hang ;

Zhang, Zhongyue ;

Xie, Junyuan ;

Li, Mu .

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :558-567

[10] The vanishing gradient problem during learning recurrent neural nets and problem solutions [J].

Hochreiter, S .

INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS, 1998, 6 (02) :107-116

← 1 2 →