Dynamic Multi-Path Relationship: Preserved Embedding for Social Network

Jiarong Liu

doi:10.54254/2753-8818/2026.HZ27845

Theoretical and Natural ScienceOpen access

Dynamic Multi-Path Relationship: Preserved Embedding for Social Network

Research Article

Open Access

Dynamic Multi-Path Relationship: Preserved Embedding for Social Network

Jiarong Liu ^1*

¹ Shenzhen College of International Education

^*Corresponding author: s24801.liu@stu.scie.com.cn

Published on 2 October 2025

TNS Vol.143

ISSN (Print): 2753-8826

ISSN (Online): 2753-8818

ISBN (Print): 978-1-80590-407-6

ISBN (Online): 978-1-80590-408-3

Download Cover

Abstract

In the contemporary era, human beings are living in a digital era, in which the issue of social network analysis has been constantly scrutinized and discussed. While the research regarding static embedding approaches has made significant progress, these approaches fail to deliver comprehensive solutions to circumstances with respect to dynamic embedding. This is a major defect, as the social network is constantly changing and evolving in a world that is developing rapidly and totally unpredictably. Therefore, this research paper focuses on dynamic social network embedding and investigates how to preserve multi-path relationships in dynamic social networks efficiently under rapidly changing topologies. The research is conducted through systematic and critical reviews of different varieties of dynamic embedding algorithms and models, followed by a comprehensive comparison. This research paper figured out that dynamic models and algorithms excel in the analysis of network users’ connections in so many ways, which is mainly because of their ability to capture fleeting information and leverage information as social networks change and evolve continuously over time.

Keywords:

Dynamic network embedding, scenario-specific optimization, structure evolution.

View PDF

References

[1]. L. Wu, B. Li, K. Guo, and Q. Zhang, "Capturing Global Structural Features and Temporal Dependencies in Dynamic Social Networks Using Graph Convolutional Networks, " Journal of Social Computing, vol. 6, no. 2, pp. 126-144, Jun. 2025. doi: 10.23919/JSC.2025.0008.

[2]. J. Lin, Y. Zhang, R. Wang, H. Chen, and M. Zhou, "Multi-Path Relationship Preserved Social Network Embedding, " IEEE Access, vol. 7, pp. 26507-26518, 2019. doi: 10.1109/ACCESS.2019.2900920.

[3]. G. Xue, M. Zhong, J. Li, J. Chen, C. Zhai, and R. Kong, "Dynamic Network Embedding Survey, " Neurocomputing, vol. 472, pp. 212-223, Jan. 2022. doi: 10.1016/j.neucom.2021.03.138.

[4]. S. Jeong, J. Park, and S. Lim, "mr2vec: Multiple Role-Based Social Network Embedding, " Pattern Recognition Letters, vol. 176, pp. 140-146, Dec. 2023. doi: 10.1016/j.patrec.2023.11.002.

[5]. Y. Peng et al., "DECTUIL: Cross-Social Network User Identity Linkage via Dynamic Embedding and Clustering Model Driven by Three-Way Decision, " Expert Systems with Applications, vol. 296, no. Part B, p. 129026, Jul. 2026. doi: 10.1016/j.eswa.2025.129026.

[6]. C. Ji, T. Zhao, Q. Sun, X. Fu, and J. Li, "Higher-Order Memory Guided Temporal Random Walk for Dynamic Heterogeneous Network Embedding, " Pattern Recognition, vol. 143, p. 109766, Nov. 2023. doi: 10.1016/j.patcog.2023.109766.

[7]. J. Tang, Y. Li, J. Qu, X. Li, and Y. Yao, "Probing for High Influential Nodes in Social Networks via a Co-Evolutionary Memetic Algorithm, " Physica A: Statistical Mechanics and its Applications, vol. 675, p. 130828, Sep. 2025. doi: 10.1016/j.physa.2025.130828.

[8]. H. Kaur, N. Hooda, and H. Singh, "K-Anonymization of Social Network Data Using Neural Network and SVM: K-NeuroSVM, " Journal of Information Security and Applications, vol. 72, p. 103382, Mar. 2023. doi: 10.1016/j.jisa.2022.103382.

References

[2]. J. Lin, Y. Zhang, R. Wang, H. Chen, and M. Zhou, "Multi-Path Relationship Preserved Social Network Embedding, " IEEE Access, vol. 7, pp. 26507-26518, 2019. doi: 10.1109/ACCESS.2019.2900920.

[3]. G. Xue, M. Zhong, J. Li, J. Chen, C. Zhai, and R. Kong, "Dynamic Network Embedding Survey, " Neurocomputing, vol. 472, pp. 212-223, Jan. 2022. doi: 10.1016/j.neucom.2021.03.138.

[4]. S. Jeong, J. Park, and S. Lim, "mr2vec: Multiple Role-Based Social Network Embedding, " Pattern Recognition Letters, vol. 176, pp. 140-146, Dec. 2023. doi: 10.1016/j.patrec.2023.11.002.

Cite this article

Liu,J. (2025). Dynamic Multi-Path Relationship: Preserved Embedding for Social Network. Theoretical and Natural Science,143,70-78.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of CONF-CIAP 2026 Symposium: International Conference on Atomic Magnetometer and Applications

ISBN: 978-1-80590-407-6(Print) / 978-1-80590-408-3(Online)

Editor: Marwan Omar , Jixi Lu , Mao Ye

Conference website: https://2026.confciap.org/hangzhou.html

Conference date: 30 January 2026

Series: Theoretical and Natural Science

Volume number: Vol.143

ISSN: 2753-8818(Print) / 2753-8826(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).