Journal of Social Computing 2023, 4(4): 326-336 https://doi.org/10.23919/JSC.2023.0018

Open Access | Issue | Published: 31 December 2023

Improving Link Prediction Accuracy of Network Embedding Algorithms via Rich Node Attribute Information

Show Author's Information Hide Author's Information Weiwei Gu^¹, Jinqiang Hou^¹, Weiyi Gu^²(

)

1College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China

2School of Computing, China University of Geosciences, Wuhan 430074, China

Keywords:

link prediction, network embedding, attributive network

Cite this article:

Gu W, Hou J, Gu W. Improving Link Prediction Accuracy of Network Embedding Algorithms via Rich Node Attribute Information. Journal of Social Computing, 2023, 4(4): 326-336. https://doi.org/10.23919/JSC.2023.0018

Download citation

EndNote(RIS)

BibTeX

180

Views

Downloads

Citations

Crossref

N/A

WoS

Scopus

N/A

CSCD

Abstract Full text About this article

Abstract

Complex networks are widely used to represent an abundance of real-world relations ranging from social networks to brain networks. Inferring missing links or predicting future ones based on the currently observed network is known as the link prediction task. Recent network embedding based link prediction algorithms have demonstrated ground-breaking performance on link prediction accuracy. Those algorithms usually apply node attributes as the initial feature input to accelerate the convergence speed during the training process. However, they do not take full advantage of node feature information. In this paper, besides applying feature attributes as the initial input, we make better utilization of node attribute information by building attributable networks and plugging attributable networks into some typical link prediction algorithms and name this algorithm Attributive Graph Enhanced Embedding (AGEE). AGEE is able to automatically learn the weighting trades-off between the structure and the attributive networks. Numerical experiments show that AGEE can improve the link prediction accuracy by around 3% compared with SEAL, Variational Graph AutoEncoder (VGAE), and node2vec.

Full text

Abstract

Full text

Outline

About this article

Improving Link Prediction Accuracy of Network Embedding Algorithms via Rich Node Attribute Information

Show Author's information Hide Author's Information Weiwei Gu^¹, Jinqiang Hou^¹, Weiyi Gu^²(

)

1College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China

2School of Computing, China University of Geosciences, Wuhan 430074, China

Abstract

Keywords: link prediction, network embedding, attributive network

References(36)

[1]

A. Barabási and J. Frangos, Linked: The New Science of Networks Perseus Publishing. Cambridge, MA, USA: Perseus Books Group, 2002.

[2]

A. Theocharidis, S. V. Dongen, A. J. Enright, and T. C. Freeman, Network visualization and analysis of gene expression data using BioLayout Express (3D), Nat. Protoc., vol. 4, no. 10, pp. 1535–1550, 2009.

DOI Google Scholar

[3]

W. Gu, J. D. Luo, and J. Liu, Exploring small-world network with an elite-clique: Bringing embeddedness theory into the dynamic evolution of a venture capital network, Soc. Netw., vol. 57, pp. 70–81, 2019.

DOI Google Scholar

[4]

R. Li, J. Liang, C. Cheng, X. Zhang, L. Zhao, C. Zhao, and H. E. Stanley, The evolution of k-shell in syndication networks reveals financial performance of venture capital institutions, Soc. Netw., vol. 76, pp. 191–202, 2024.

DOI Google Scholar

[5]

Q. Yao, S. Ma, J. Liang, and R. Li, Syndication network associates with specialisation and performance of venture capital firms, J. Phys. Complex., vol. 4, no. 2, p. 025016, 2023.

DOI Google Scholar

[6]

M. D. Domenico, Multilayer modeling and analysis of human brain networks, GigaScience, vol. 6, no. 5, p. gix004, 2017.

DOI Google Scholar

[7]

M. Craven, D. DiPasquo, D. Freitag, A. McCallum, T. Mitchell, K. Nigam, and S. Slattery, Learning to construct knowledge bases from the World Wide Web, Artif. Intell., vol. 118, nos. 1&2, pp. 69–113, 2000.

DOI Google Scholar

[8]

A. Popescul and L. H. Ungar, Statistical relational learning for link prediction, presented at IJCAI Workshop on Learning Statistical Models from Relational Data, Acapulco, Mexico, 2003.

[9]

D. Liben-Nowell and J. Kleinberg, The link-prediction problem for social networks, J. Am. Soc. Inf. Sci. Technol., vol. 58, no. 7, pp. 1019–1031, 2007.

DOI Google Scholar

[10]

A. L. Barabasi and R. Albert, Emergence of scaling in random networks, Science, vol. 286, no. 5439, pp. 509–512, 1999.

DOI Google Scholar

[11]

T. Zhou, L. Lü, and Y. -C. Zhang, Predicting missing links via local information, Eur. Phys. J. B, vol. 71, no. 4, pp. 623–630, 2009.

DOI Google Scholar

[12]

H. Liu, Z. Hu, H. Haddadi, and H. Tian, Hidden link prediction based on node centrality and weak ties, EPL Europhys. Lett., vol. 101, no. 1, p. 18004, 2013.

DOI Google Scholar

[13]

G. Rücker, Network meta-analysis, electrical networks and graph theory, Res. Synth. Meth., vol. 3, no. 4, pp. 312–324, 2012.

DOI Google Scholar

[14]

F. Shang, B. Chen, P. Expert, L. Lü, A. Yang, H. E. Stanley, R. Lambiotte, T. S. Evans, and R. Li, Local dominance unveils clusters in networks, arXiv preprint arXiv: 2209.15497, 2022.

[15]

B. Perozzi, R. Al-Rfou, and S. Skiena, DeepWalk: Online learning of social representations, in Proc. 20^th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, New York, NY, USA, 2014, pp. 701–710.

DOI

[16]

A. Grover and J. Leskovec, Node2vec: Scalable feature learning for networks, in Proc. 22^nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 855–864.

DOI

[17]

M. Ou, P. Cui, J. Pei, Z. Zhang, and W. Zhu, Asymmetric transitivity preserving graph embedding, in Proc. 22^nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 1105–1114.

DOI

[18]

J. Tang, M. Qu, M. Wang, M. Zhang, J. Yan, and Q. Mei, LINE: Large-scale information network embedding, in Proc. 24^th Int. Conf. World Wide Web, Florence, Italy, 2015, pp. 1067–1077.

DOI

[19]

L. F. R. Ribeiro, P. H. P. Saverese, and D. R. Figueiredo, Struc2vec: Learning node representations from structural identity, in Proc. 23^rd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, Halifax, Canada, 2017, pp. 385–394.

[20]

T. N. Kipf and M. Welling, Semi-supervised classification with graph convolutional networks, arXiv preprint arXiv: 1609.02907, 2016.

[21]

W. Gu, F. Gao, X. Lou, and J. Zhang, Discovering latent node Information by graph attention network, Sci. Rep., vol. 11, no. 1, p. 6967, 2021.

DOI Google Scholar

[22]

T. N. Kipf and M. Welling, Variational graph auto-encoders, arXiv preprint arXiv: 1611.07308, 2016.

[23]

W. Gu, L. Gong, X. Lou, and J. Zhang, The hidden flow structure and metric space of network embedding algorithms based on random walks, Sci. Rep., vol. 7, no. 1, p. 13114, 2017.

DOI Google Scholar

[24]

W. L. Hamilton, R. Ying, and J. Leskovec, Inductive representation learning on large graphs, in Proc. 31^st Int. Conf. Neural Information Processing Systems, Long Beach, CA, USA, 2017, pp. 1025–1035.

[25]

K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770–778.

DOI

[26]

J. Gehring, M. Auli, D. Grangier, and Y. N. Dauphin, A convolutional encoder model for neural machine translation, arXiv preprint arXiv: 1611.02344, 2016.

DOI

[27]

M. Zhang and Y. Chen, Link prediction based on graph neural networks, arXiv preprint arXiv: 1802.09691, 2018.

[28]

A. K. McCallum, K. Nigam, J. Rennie, and K. Seymore, Automating the construction of Internet portals with machine learning, Inf. Retr., vol. 3, no. 2, pp. 127–163, 2000.

DOI Google Scholar

[29]

L. Getoor, Link-based classification, in Advanced Methods for Knowledge Discovery from Complex Data, S. Bandyopadhyay, U. Maulik, L. B. Holder, and D. J. Cook, eds. London, UK: Springer, 2005, pp. 189–207.

DOI

[30]

F. Papadopoulos, M. Kitsak, M. Á. Serrano, M. Boguñá, and D. Krioukov, Popularity versus similarity in growing networks, Nature, vol. 489, no. 7417, pp. 537–540, 2012.

DOI Google Scholar

[31]

T. Mikolov, K. Chen, G. Corrado, and J. Dean, Efficient estimation of word representations in vector space, arXiv preprint arXiv: 1301.3781, 2013.

[32]

D. P. Kingma and M. Welling, An introduction to variational autoencoders, Found. Trends® Mach. Learn., vol. 12, no. 4, pp. 307–392, 2019.

DOI Google Scholar

[33]

M. Kim, S. H. Baek, and M. Song, Relation extraction for biological pathway construction using node2vec, BMC Bioinform., vol. 19, no. Suppl8, p. 206, 2018.

DOI Google Scholar

[34]

G. Rosenthal, F. Váša, A. Griffa, P. Hagmann, E. Amico, J. Goñi, G. Avidan, and O. Sporns, Mapping higher-order relations between brain structure and function with embedded vector representations of connectomes, Nat. Commun., vol. 9, no. 1, p. 2178, 2018.

DOI Google Scholar

[35]

T. Mikolov, I. Sutskever, K. Chen, G. Corrado, and J. Dean, Distributed representations of words and phrases and their compositionality, in Proc. 26^th Int. Conf. Neural Information Processing Systems - Volume 2, Lake Tahoe, Nevada, 2013, pp. 3111–3119.

[36]

S. Pan, R. Hu, G. Long, J. Jiang, L. Yao, and C. Zhang, Adversarially regularized graph autoencoder for graph embedding, arXiv preprint arXiv: 1802.04407, 2018.

DOI

About this article

Publication history

Rights and permissions

Publication history

Received: 22 July 2023

Revised: 24 October 2023

Accepted: 28 October 2023

Published: 31 December 2023

Issue date: December 2023

Copyright

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/).