Journal Home > Volume 2 , issue 4

Network representation learning plays an important role in the field of network data mining. By embedding network structures and other features into the representation vector space of low dimensions, network representation learning algorithms can provide high-quality feature input for subsequent tasks, such as network link prediction, network vertex classification, and network visualization. The existing network representation learning algorithms can be trained based on the structural features, vertex texts, vertex tags, community information, etc. However, there exists a lack of algorithm of using the future evolution results of the networks to guide the network representation learning. Therefore, this paper aims at modeling the future network evolution results of the networks based on the link prediction algorithm, introducing the future link probabilities between vertices without edges into the network representation learning tasks. In order to make the network representation vectors contain more feature factors, the text features of the vertices are also embedded into the network representation vectors. Based on the above two optimization approaches, we propose a novel network representation learning algorithm, Network Representation learning algorithm based on the joint optimization of Three Features (TFNR). Based on Inductive Matrix Completion (IMC), TFNR algorithm introduces the future probabilities between vertices without edges and text features into the procedure of modeling network structures, which can avoid the problem of the network structure sparse. Experimental results show that the proposed TFNR algorithm performs well in network vertex classification and visualization tasks on three real citation network datasets.


menu
Abstract
Full text
Outline
About this article

Network Representation Based on the Joint Learning of Three Feature Views

Show Author's information Zhonglin YeHaixing Zhao( )Ke ZhangZhaoyang WangYu Zhu
Key Laboratory of Tibetan Information Processing, the College of Computer, Qinghai Normal University, Xining 810008, China.
College of Mathematics and Statistics, Qinghai Normal University, Xining 810008, China.

Abstract

Network representation learning plays an important role in the field of network data mining. By embedding network structures and other features into the representation vector space of low dimensions, network representation learning algorithms can provide high-quality feature input for subsequent tasks, such as network link prediction, network vertex classification, and network visualization. The existing network representation learning algorithms can be trained based on the structural features, vertex texts, vertex tags, community information, etc. However, there exists a lack of algorithm of using the future evolution results of the networks to guide the network representation learning. Therefore, this paper aims at modeling the future network evolution results of the networks based on the link prediction algorithm, introducing the future link probabilities between vertices without edges into the network representation learning tasks. In order to make the network representation vectors contain more feature factors, the text features of the vertices are also embedded into the network representation vectors. Based on the above two optimization approaches, we propose a novel network representation learning algorithm, Network Representation learning algorithm based on the joint optimization of Three Features (TFNR). Based on Inductive Matrix Completion (IMC), TFNR algorithm introduces the future probabilities between vertices without edges and text features into the procedure of modeling network structures, which can avoid the problem of the network structure sparse. Experimental results show that the proposed TFNR algorithm performs well in network vertex classification and visualization tasks on three real citation network datasets.

Keywords:

network representation learning, network feature mining, embedding learning, link prediction, matrix factorization
Received: 13 November 2018 Revised: 15 April 2019 Accepted: 16 April 2019 Published: 05 August 2019 Issue date: December 2019
References(35)
[1]
G. Tsoumakas and I. Katakis, Multi-label classification: An overview, International Journal of Data Warehousing and Mining, vol. 3, no. 3, pp. 1-13, 2007.
[2]
D. Liben-Nowell and J. Kleinberg, The link-prediction problem for social networks, J. Assoc. Inform. Sci. Technol., vol. 58, no. 7, pp. 1019-1031, 2007.
[3]
C. C. Tu, Z. Y. Liu, and M. S. Sun, Inferring correspondences from multiple sources for microblog user tags, in Proc. 3rd Chinese National Conf. Social Media Processing, Beijing, China, 2014, pp. 1-12.
[4]
L. G. Préz, F. Chiclana, and S. Ahmadi, A social network representation for collaborative filtering recommender systems, in Proc. 11th Int. Conf. Intelligent Systems Design and Applications, Cordoba, Spain, 2012, pp. 438-443.
[5]
B. Perozzi, R. Al-Rfou, and S. Skien, DeepWalk: Online learning of social representations, in Proc. 20th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, New York, NY, USA, 2014, pp. 701-710.
[6]
T. Mikolov, I. Sutskever, K. Chen, G. Corrado, and J. Dean, Distributed representations of words and phrases and their compositionality, in Proc. 26th Int. Conf. Neural Information Processing Systems, Lake Tahoe, NV, USA, 2013, pp. 3111-3119.
[7]
J. Tang, M. Qu, M. Z. Wang, M. Zhang, J. Yan, and Q. Z. Mei, LINE: Large-scale information network embedding, in Proc. 24th Int. Conf. World Wide Web, Florence, Italy, 2015, pp. 1067-1077.
[8]
S. S. Cao, W. Lu, and Q. K. Xu, GraRep: Learning graph representations with global structural information, in Proc. 24th ACM Int. Conf. Information and Knowledge Management, Melbourne, Australia, 2015, pp. 891-900.
[9]
D. X. Wang, P. Cui, and W. W. Zhu, Structural deep network embedding, in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 1225-1234.
[10]
A. Grover and J. Leskovec, node2vec: Scalable feature learning for networks, in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 855-864.
[11]
J. Tang, M. Qu, and Q. Z. Mei, PTE: Predictive text embedding through large-scale heterogeneous text networks, in Proc. 12th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, Sydney, Australia, 2015, pp. 1165-1174.
[12]
X. F. Sun, J. Guo, X. Ding, and T. Liu, A general framework for content-enhanced network representation learning, , 2018.
[13]
C. C. Tu, H. Wang, X. K. Zeng, Z. Y. Liu, and M. S. Sun, Community-enhanced network representation learning for network analysis, , 2017.
[14]
S. R. Pan, J. Wu, X. Q. Zhu, C. Q. Zhang, and Y. Wang, Tri-party deep network representation, in Proc. 25th Int. Joint Conf. Artificial Intelligence, New York, NY, USA, 2016, pp. 1895-1901.
[15]
A. Garcia-Duran and M. Niepert, Learning graph representations with embedding propagation, , 2017.
[16]
X. Wang, P. Cui, J. Wang, J. Pei, W. W. Zhu, and S. Q. Yang, Community preserving network embedding, in Proc. 21st AAAI Conf. Artificial Intelligence, San Francisco, CA, USA, 2017.
[17]
D. K. Zhang, J. Yin, X. Q. Zhu, and C. Q. Zhang, User profile preserving social network embedding, in Proc. 26th Int. Joint Conf. Artificial Intelligence, Melbourne, Australia, 2017, pp. 3378-3384.
[18]
C. Z. Li, S. Z. Wang, D. J. Yang, Z. J. Li, Y. Yang, X. M. Zhang, and J. S. Zhou, PPNE: Property preserving network embedding, in Database Systems for Advanced Applications, S. Candan, L. Chen, T. B. Pedersen, L. J. Chang, and W. Hua, eds. Springer, 2017, pp. 163-179.
[19]
X. Huang, J. D. Li, and X. Hu, Accelerated attributed network embedding, in Proc. 2017 SIAM Int. Conf. Data Mining, Houston, TX, USA, 2017.
[20]
Z. P. Huang and N. Mamoulis, Heterogeneous information network embedding for meta path based proximity, , 2018.
[21]
K. Tu, P. Cui, X. Wang, F. Wang, and W. W. Zhu, Structural deep embedding for hyper-networks, , 2018.
[22]
O. Levy and Y. Goldberg, Neural word embedding as implicit matrix factorization, in Proc. 27th Int. Conf. Neural Information Processing Systems, Montreal, Canada, 2014, pp. 2177-2185.
[23]
H. F. Yu, P. Jain, P. Kar, and I. S. Dhillon, Large-scale multi-label learning with missing labels, in Proc. 31st Int. Conf. Machine Learning, Beijing, China, 2014, pp. 593-601.
[24]
C. Yang and Z. Y. Liu. Comprehend DeepWalk as matrix factorization, , 2015.
[25]
C. Yang, Z. Y. Liu, D. L. Zhao, M. S. Sun, and E. Y. Chang, Network representation learning with rich text information, in Proc. 24th Int. Conf. Artificial Intelligence, Buenos Aires, Argentina, 2015, pp. 2111-2117.
[26]
C. C. Tu, W. C. Zhang, Z. Y. Liu, and M. S. Sun, Max-margin deepwalk: Discriminative learning of network representation, in Proc. 25th Int. Joint Conf. Artificial Intelligence, New York, NY, USA, 2016, pp. 3889-3895.
[27]
N. Natarajan and I. S. Dhillon, Inductive matrix completion for predicting gene-disease associations, Bioinformatics, vol. 30, no. 12, pp. i60-i68, 2014.
[28]
M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, Support vector machines, IEEE Intell. Syst. Their Appl., vol. 13, no. 4, pp. 18-28, 1998.
[29]
J. Zhu, A. Ahmed, and E. P. Xing, MedLDA: Maximum margin supervised topic models, in Proc. 26th Int. Conf. Machine Learning, Montreal, Canada, 2009, pp. 1257-1264.
[30]
S. Aouay, S. Jamoussi, and F. Gargouri, Feature based link prediction, in Proc. 11th IEEE/ACS Int. Conf. Computer Systems and Applications, Doha, Qatar, 2014, pp. 523-527.
[31]
E. M. Dong, J. P. Li, and Z. Xie, Link prediction via convex nonnegative matrix factorization on multiscale blocks, J. Appl. Math., vol. 2014, pp. 1-9, 2014.
[32]
D. Li, Z. M. Xu, S. Li, and X. Sun, Link prediction in social networks based on hypergraph, in Proc. 22nd Int. Conf. World Wide Web, Rio de Janeiro, Brazil, 2013, pp. 41-42.
[33]
A. Farasat, A. Nikolaev, S. N. Srihari, R. H. Blair, Probabilistic graphical models in modern social network analysis, Social Network Analysis and Mining, vol. 5, no. 1, p. 62, 2015.
[34]
R. E. Fan, K. W. Chang, C. J. Hsieh, X. R. Wang, and C. J. Lin, LIBLINEAR: A library for large linear classification, J. Mach. Learn. Res., vol. 9, pp. 1871-1874, 2008.
[35]
L. Y. Lv and T. Zhou, Link Prediction. Beijing, China: Higher Education Press, 2013.
Publication history
Copyright
Rights and permissions

Publication history

Received: 13 November 2018
Revised: 15 April 2019
Accepted: 16 April 2019
Published: 05 August 2019
Issue date: December 2019

Copyright

© The author(s) 2019

Rights and permissions

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Reprints and Permission requests may be sought directly from editorial office.

Return