Centrality and Latent Semantic Feature Random Walk (CSRW) in Large Network Embedding

Taherparvar, M.; Ahmadi Abkenari, F.; Bayat, P.

doi:10.22061/jecei.2023.9279.600

Document Type : Original Research Paper

Authors

¹ Department of Computer Engineering, Rasht Branch, Islamic Azad University, Rasht, Iran.

² Department of Computer Engineering, Rasht Branch, Islamic Azad University, Rasht, Iran, and Faculty of Computer Engineering and Information Technology, Payam Noor University, Tehran, Iran.

³ Department of Computer Engineering, Rasht Branch, Islamic Azad,University, Rasht, Iran.

https://doi.org/10.22061/jecei.2023.9279.600

Abstract

Background and Objectives: Embedding social networks has attracted researchers’ attention so far. The aim of network embedding is to learn a low-dimensional representation of each network vertex while maintaining the structure and characteristics of the network. Most of these existing network embedding methods focus on only preserving the structure of networks, but they mostly ignore the semantic and centrality-based information. Moreover, the vertices selection has been done blindly (greedy) in the existing methods.
Methods: In this paper, a comprehensive algorithm entitled CSRW stands for centrality, and a semantic-based random walk is proposed for the network embedding process based on the main criteria of the centrality concept as well as the semantic impact of the textual information of each vertex and considering the impact of neighboring nodes. in CSRW, textual analysis based on the BTM topic modelling approach is investigated and the final display is performed using the Skip-Gram model in the network.
Results: The conducted experiments have shown the robustness of the proposed method of this paper in comparison to other existing classical approaches such as DeepWalk, CARE, CONE, COANE, and DCB in terms of vertex classification, and link prediction. And in the criterion of link prediction in a Subgraph with 5000 members, an accuracy of 0.91 has been reached for the criterion of closeness centrality and is better than other methods.
Conclusion: The CSRW algorithm is scalable and has achieved higher accuracy on larger datasets.

Keywords

20.1001.1.23223952.2023.11.2.7.9

Main Subjects

Deep Learning

Open Access

This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit: http://creativecommons.org/licenses/by/4.0/

Publisher’s Note

JECEI Publisher remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Publisher

Shahid Rajaee Teacher Training University

References

[1] B. Perozzi, R. Al-Rfou, S. Skiena, “Deepwalk: Online learning of social representations,” in Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: 701–710, 2014.

[2] A. Grover, J. Leskovec, “Node2vec: Scalable feature learning for networks,” in Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: 855–864, 2016.

[3] S. Bhagat, G. Cormode, S. Muthukrishnan, “Node classification in social networks,” Social Network Data Analytics (Springer) Ed. Charu Aggarwal, 2011.

[4] A. Faroughi, R. Javidan, “CANF: Clustering and anomaly detection method using nearest and farthest neighbor,” Future Gener. Comput. Syst., 89: 166–177, 2018.

[5] S. Aslan, M. Kaya, “Topic recommendation for authors as a link prediction problem,” Future Gener. Comput. Syst., 89: 249–264, 2018.

[6] T. Mikolov, K. Chen, G. Corrado, J. Dean, “Efficient estimation of word representations in vector space,” arXiv:1301.3781, 2013.

[7] J. Tang, M. Qu, M. Wang, M. Zhang, J. Yan, Q. Mei, “Line: Large-scale information network embedding,” in Proc. International Conference on World Wide Web: 1067–1077, 2015.

[8] H. Gao, H. Huang, “Deep attributed network embedding,” in Proc. International Joint Conference on Artificial Intelligence: 3364–3370, 2018.

[9] X. Huang, J. Li, X. Hu, “Label informed attributed network embedding,” in Proc. ACM International Conference on Web Search and Data Mining: 731–739, 2017.

[10] J. Butepage, M. J. Black, D. Kragic, H. Kjellstrom, “Deep representation learning for human motion prediction and classification,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition: 1591–1599, 2017.

[11] X. Du, J. J. Y. Wang, “Support image set machine: Jointly learning representation and classifier for image set classification,” Knowledge-Based Syst., 78: 51–58, 2015.

[12] J. Li, J. Li, X. Fu, M. A. Masud, J. Z. Huang, “Learning distributed word representation with multi-contextual mixed embedding,” Knowledge-Based Syst., 106: 220–230, 2016.

[13] M. Janner, K. Narasimhan, R. Barzilay, "Representation learning for grounded spatial reasoning," Trans. Assoc. Computer. Ling., 6: 49–61, 2018.

[14] Z. Chen, T. Cai, C. Chen, Z. Zheng, G. Ling, “SINE: Side information network embedding,” in Proc. International Conference on Database Systems for Advanced Applications: 692–708, 2019.

[15] D. Wang, P. Cui, W. Zhu, “Structural deep network embedding,” in Proc. International Conference on Knowledge Discovery and Data Mining: 1225–1234, 2016.

[16] M. Li, J. Liu, P. Wu, X. Teng, “Evolutionary network embedding preserving both local proximity and community structure,” IEEE Trans. Evol. Comput., 24(3): 523-535, 2019.

[17] J. Chen, Q. Zhang, X. Huang, “Incorporate group information to enhance network embedding,” in Proc. International Conference on Information and Knowledge Management: 1901–1904, 2016.

[18] M. M. Keikha, M. Rahgozar, M. Asadpour, “Community aware random walk for network embedding,” Knowl. Based Syst., 47–54, 2018.

[19] J. Wang, j. Cao, W. Li, S. Wang, “CANE: community-aware network embedding via adversarial training,” Knowl. Inf. Syst., 63: 411-438, 2020.

[20] Y. Shi, M. Lei, H. Yang, L. Niu, “Diffusion network embedding,” Pattern Recognit., 88: 518–531, 2019.

[21] H. Chen, H. Yin, T. Chen, Q.V.H. Nguyen, W.-C. Peng, X. Li, “Exploiting centrality information with graph convolutions for network representation learning,” in Proc. IEEE International Conference on Data Engineering: 590–601, 2019.

[22] W. Zhao, H. Ma, Z. Li, X. Ao, N. Li, “SBRNE: An improved unified framework for social and behavior recommendations with network embedding,” in Proc. International Conference on Database Systems for Advanced Applications: 555–571, 2019.

[23] Q. Li, J. Zhong, Q. Li, Z. Cao, C. Wang, “Enhancing network embedding with implicit clustering,” in Proc. International Conference on Database Systems for Advanced Applications: 452–467, 2019.

[24] M. RosenZvi, T. Griffiths, M. Steyvers, P. Smyth, “The author-topic model for authors and documents,” in Proc. Uncertainty in Artificial Intelligence: 487–494, 2004.

[25] Q. Mei, D. Cai, D. Zhang, C. Zhai, “Topic modeling with network regularization,” in Proc: International Conference on World Wide Web: 101–110, 2008.

[26] L. Wu, D. Wang, S. Feng, Y. Zhang, G. Yu, MDAL: “Multi-task Dual Attention LSTM Model for Semi-supervised Network Embedding,” in Proc: International Conference on Database Systems for Advanced Applications: 468–483, 2019.

[27] Y. Gao, M. Gong, Y. Xie, H. Zhong, “Community-oriented attributed network embedding,” Knowledge-Based Systems, 193: 105418, 2019.

[28] M. Taherparvar, F. Ahmadi Abkenari, P. Bayat, “Attribute network embedding based on maintaining the structure and semantic features of the graphs,” in Proc: International Conference on The New Horizons in The Electrical Engineering, Computer and Mechanical, 2022.

[29] L. Chen, Y. Li, X. Deng, Z. Liu, M. Lv, T. He, “Semantic-aware network embedding via optimized random walk and paragaraph2vec,” J. Comput. Sci., 63: 101825, 2022.

[30] J. Zhang, Yu. Luo, “Degree centrality, betweenness centrality, and closeness centrality in social network,” in proc. International Conference on Modelling, Simulation and Applied Mathematics, 2017.

[31] P. Bonacich, “Some unique properties of eigenvector centrality,” Social Network, 29(4): 555-564, 2007.

[32] L. Maccari, L. Ghiro, A. Guerrieri, A. Montresor, R. Lo Cigno, “On the distributed computation of load centrality and its application to DV routing,” in proc. IEEE Conference on Computer Communications, 2018.

[33] M. Taherparvar, F. Ahmadi Abkenari, P. Bayat, “Conformance evaluation of topic modeling approaches on web-based short text dynamic graph databases,” in proc. International Conference on Web Research, 2021.

[34] J. Tang, Z. Meng, X. Nguyen, Q. Mei, M. Zhang, “Understanding the limiting factors of topic modeling via posterior contraction analysis,” in Proc. International Conference on Machine Learning: 190–198, 2014.

[35] A. K. McCallum, K. Nigam, J. Rennie, K. Seymore, “Automating the construction of internet portals with machine learning,” Information Retrieval: 127–163, 2000.

[36] https://www.aminer.org/citation, last access June 17, 2023.

LETTERS TO EDITOR

Journal of Electrical and Computer Engineering Innovations (JECEI) welcomes letters to the editor for the post-publication discussions and corrections which allows debate post publication on its site, through the Letters to Editor. Letters pertaining to manuscript published in JECEI should be sent to the editorial office of JECEI within three months of either online publication or before printed publication, except for critiques of original research. Following points are to be considering before sending the letters (comments) to the editor.

[1] Letters that include statements of statistics, facts, research, or theories should include appropriate references, although more than three are discouraged.

[2] Letters that are personal attacks on an author rather than thoughtful criticism of the author’s ideas will not be considered for publication.

[3] Letters can be no more than 300 words in length.

[4] Letter writers should include a statement at the beginning of the letter stating that it is being submitted either for publication or not.

[5] Anonymous letters will not be considered.

[6] Letter writers must include their city and state of residence or work.

[7] Letters will be edited for clarity and length.

Name *

Email Address *

Affiliation *

Comments *

Security Code *

Journal of Electrical and Computer Engineering Innovations (JECEI)

Centrality and Latent Semantic Feature Random Walk (CSRW) in Large Network Embedding

References

References

Send comment about this article

Volume 11, Issue 2
July 2023
Pages 311-326

Centrality and Latent Semantic Feature Random Walk (CSRW) in Large Network Embedding

References

References

Send comment about this article

Volume 11, Issue 2July 2023Pages 311-326

Volume 11, Issue 2
July 2023
Pages 311-326