Conditional Variational Time-Series Graph Auto-Encoder

被引：0

作者：

Chen K. ^{[1
,2
]}

Lu H. ^{[1
]}

Zhang J. ^{[1
]}

机构：

[1] School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing

[2] Jiangsu Key Laboratory of Big Data Security & Intelligent Processing, Nanjing University of Posts and Telecommunications, Nanjing

来源：

Jisuanji Yanjiu yu Fazhan/Computer Research and Development | 2020年 / 57卷 / 08期

基金：

中国国家自然科学基金;

关键词：

Conditional variational auto-encoder; Dynamic network; Graph convolution; Link prediction; Network representation learning;

D O I：

10.7544/issn1000-1239.2020.20200202

中图分类号：

学科分类号：

摘要：

Network representation learning (also called graph embedding) is the basis for graph tasks such as link prediction, node classification, community discovery, and graph visualization. Most of the existing graph embedding algorithms are mainly developed for static graphs, which is difficult to capture the dynamic characteristics of the real-world networks that evolve over time. At present, research on dynamic network representation learning is still inadequate. This paper proposes a conditional variational time-series graph auto-encoder (TS-CVGAE), which can simultaneously learn the local structure and evolution pattern of a dynamic network. The model improves the traditional graph convolution to obtain time-series graph convolution and uses it to encode the network in the framework of conditional variational auto-encoder. After training, the middle layer of TS-CVGAE is the final network embedding. Experimental results show that the method performs better in link prediction task than the related static and dynamic network representation learning methods with all four real dynamic network datasets. © 2020, Science Press. All right reserved.

引用

页码：1663 / 1673

页数：10

共 29 条

[1] Sharan R, Ulitsky I, Shamir R., Network-based prediction of protein function, Molecular Systems Biology, 3, 1, pp. 88-101, (2007)
[2] Otte E, Rousseau R., Social network analysis: A powerful strategy, also for the information sciences, Journal of Information Science, 28, 6, pp. 441-453, (2002)
[3] Nerur S, Sikora R, Mangalaraj G, Et al., Assessing the relative influence of journals in a citation network, Communications of the ACM, 48, 11, pp. 71-74, (2005)
[4] Goyal P, Ferrara E., Graph embedding techniques, applications, and performance: A survey, Knowledge-Based Systems, 151, pp. 78-94, (2017)
[5] Tu Cunchao, Yang Cheng, Liu Zhiyuan, Et al., Network representation learning: An overview, Scientia Sinica Informationis, 47, 8, pp. 980-996, (2017)
[6] Perozzi B, Al-Rfou R, Skiena S., Deepwalk: Online learning of social representations, Proc of the 20th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, pp. 701-710, (2014)
[7] Grover A, Leskovec J., node2vec: Scalable feature learning for networks, Proc of the 22nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, pp. 855-864, (2016)
[8] Ribeiro L F R, Saverese P H P, Figueiredo D R., struc2vec: Learning node representations from structural identity, Proc of the 23rd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, pp. 385-394, (2017)
[9] O'malley S W, Peterson L., A dynamic network architecture, ACM Transactions on Computer Systems, 10, 2, pp. 110-143, (1994)
[10] Mahdavi S, Khoshraftar S, An A., dynnode2vec: Scalable dynamic network embedding, Proc of the 6th IEEE Int Conf on Big Data, pp. 3762-3765, (2018)

← 1 2 3 →