Skip to main content

Advertisement

Springer Nature Link
Log in

A hybrid optimization approach for graph embedding: leveraging Node2Vec and grey wolf optimization

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

A Correction to this article was published on 24 March 2025

This article has been updated

Abstract

Node2Vec, an advanced graph analysis technique rooted in graph-based learning principles, excels at node feature extraction. However, it faces significant challenges, particularly in parameter optimization and maintaining efficiency in large-scale networks. To address these issues, this paper proposes a novel integration of Node2Vec with the Grey Wolf Optimization algorithm. This hybrid approach systematically explores the parameter space to identify optimal configurations for Node2Vec, enhancing the quality of embeddings for diverse graph and network analyses. Experimental results demonstrate that the proposed method significantly improves Node2Vec's performance, outperforming the original implementation, grid search variants, and other leading algorithms. Comprehensive evaluations on benchmark datasets, including both synthetic and real-world networks, confirm that our approach achieves superior performance metrics compared to existing solutions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Algorithm 1
Fig. 2
Algorithm 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

Data availability

The datasets used in this study include: Karate Club dataset: Publicly available and can be accessed from https://networkrepository.com/soc-karate.php?utm_source=chatgpt.com. Dolphin Network dataset: Publicly available and can be accessed from https://networkrepository.com/dolphins.php. Facebook Ego Network dataset: Publicly available and can be accessed from https://snap.stanford.edu/data/egonets-Facebook.html. Real Dataset (The network of drug gangs active in cyberspace in Iran): This dataset contains sensitive organizational data and is subject to ethical restrictions. While it cannot be shared publicly, it is available upon reasonable request from the corresponding author, M.R., with appropriate permissions and under relevant ethical considerations.

Change history

  • 20 March 2025

    The original online version of this article was revised: In this article the author’s name Mehdi Fartash was incorrectly written as Mahdi Fartash

  • 24 March 2025

    A Correction to this paper has been published: https://doi.org/10.1007/s11227-025-07168-z

References

  1. Grover, A., & Leskovec, J. (2016). Node2Vec: Scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. https://doi.org/10.1145/2939672.2939754

  2. Palumbo E, Rizzo G, Troncy R, Baralis E, Osella M, Ferro E (2018) Knowledge graph embeddings with Node2Vec for item recommendation. Lect Notes Comput Sci 11155:117–120. https://doi.org/10.1007/978-3-319-98192-5_22

    Article  Google Scholar 

  3. Jin D, Kim S, Rossi R, Koutra D (2022) On generalizing static node embedding to dynamic settings. Proc Fifteenth ACM Int Conf Web Search Data Min. https://doi.org/10.1145/3488560.3498428

    Article  Google Scholar 

  4. Hamilton, W. L., Ying, R., & Leskovec, J. (2017). Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems (NeurIPS), 30. https://arxiv.org/abs/1706.02216

  5. Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61. https://doi.org/10.1016/j.advengsoft.2013.12.007

    Article  MATH  Google Scholar 

  6. Cui P, Wang X, Pei J, Zhu W (2017) A survey on network embedding. IEEE Trans Knowl Data Eng 31(4):833–852. https://doi.org/10.1109/TKDE.2018.2849727

    Article  MATH  Google Scholar 

  7. Mo Z, Xie Z, Zhang X, Luo Q, Zheng Y, Yu D (2022) Network representation learning based on social similarities. Front Environ Sci 10:974246. https://doi.org/10.3389/fenvs.2022.974246

    Article  Google Scholar 

  8. Meng L, Masuda N (2020) Analysis of Node2Vec random walks on networks. Proc. R. Soc. A 476(2243):20200447. https://doi.org/10.1098/rspa.2020.0447

    Article  MathSciNet  MATH  Google Scholar 

  9. Goyal P, Ferrara E (2017) Graph embedding techniques, applications, and performance: a survey. Knowl-Based Syst 151:78–94. https://doi.org/10.1016/j.knosys.2018.03.022

    Article  MATH  Google Scholar 

  10. Belkin M, Niyogi P (2001) Laplacian Eigenmaps and spectral techniques for embedding and clustering. Adv Neural Inf Process Syst 14:585–591

    MATH  Google Scholar 

  11. Cao S, Lu W, Xu Q (2015) GraRep: learning graph representations with global structural information. In: Proceedings of the 24th ACM International Conference on Information and Knowledge Management. https://doi.org/10.1145/2806416.2806512

  12. Perozzi, B., Al-Rfou, R., & Skiena, S. (2014). DeepWalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/2623330.2623732

  13. Liu X, Kim K (2018) A comparative study of network embedding based on matrix factorization. Lect Notes Comput Sci 11198:89–101. https://doi.org/10.1007/978-3-319-93803-5_9

    Article  MATH  Google Scholar 

  14. Davison A, Morgan S, Ward O (2023) Community detection and classification guarantees using embeddings learned by Node2Vec. arXiv preprint, arXiv:2310.17712. https://doi.org/10.48550/arXiv.2310.17712

  15. Wang D, Cui P, Zhu W (2016) Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD International Conference On Knowledge Discovery and Data Mining. https://doi.org/10.1145/2939672.2939753

  16. Kipf T, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv preprint, arXiv:1609.02907. https://doi.org/10.48550/arXiv.1609.02907

  17. Jiang X, Zhu R, Ji P, Li S (2020) Co-embedding of nodes and edges with graph neural networks. IEEE Trans Pattern Anal Mach Intell 45(7):7075–7086. https://doi.org/10.1109/TPAMI.2020.3029762

    Article  MATH  Google Scholar 

  18. Ou M, Cui P, Pei J, Zhang Z, Zhu W (2016) Asymmetric transitivity preserving graph embedding. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/2939672.2939751

  19. Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) LINE: large-scale information network embedding. In: Proceedings of the 24th International Conference on World Wide Web. https://doi.org/10.1145/2736277.2741093

  20. Zhang Y, Xiong Y, Kong X, Zhu Y (2017) Learning node embeddings in interaction graphs. In: Proceedings of the 2017 ACM Conference on Information and Knowledge Management. https://doi.org/10.1145/3132847.3132918

  21. Zhang L (2022) Graph sampling for node embedding. arXiv preprint, arXiv:2210.10520. https://doi.org/10.48550/arXiv.2210.10520

  22. Rozemberczki B, Allen C, Sarkar R (2019) Multi-scale attributed node embedding. J Complex Netw 9(5):cnab014. https://doi.org/10.1093/comnet/cnab014

  23. Shen X, Chung K (2019) Network embedding for cross-network node classification. arXiv preprint, arXiv:1901.07264

  24. Nguyen H, Zerr S, Hoang T (2020) On node embedding of uncertain networks. IEEE Int Conf Big Data (Big Data) 2020:5792–5794. https://doi.org/10.1109/BigData50022.2020.9378022

    Article  MATH  Google Scholar 

  25. Wang X, Cui P, Wang J, Pei J, Zhu W, Yang S (2017) Community preserving network embedding. Proc Thirty-First AAAI Conf Artif Intell 31(1):203–209. https://doi.org/10.1609/aaai.v31i1.10488

    Article  MATH  Google Scholar 

  26. Xu M (2020) Understanding graph embedding methods and their applications. SIAM Rev 63(4):825–853. https://doi.org/10.1137/20m1386062

    Article  MathSciNet  MATH  Google Scholar 

  27. Song G, Zhang L, Li Z, Li Y (2022) Large scale network embedding: a separable approach. IEEE Trans Knowl Data Eng 34(4):1829–1842. https://doi.org/10.1109/TKDE.2020.3002700

    Article  MATH  Google Scholar 

  28. Li Y, Yang B (2024) Quantitative study of random walk parameters in Node2Vec model. Phys Scr 99(6):065208. https://doi.org/10.1088/1402-4896/ad3eea

    Article  MATH  Google Scholar 

  29. Dalmia A, Jawahar G, Gupta M (2018) Towards interpretation of node embeddings. In: Companion Proceedings of the Web Conference 2018. https://doi.org/10.1145/3184558.3191523

  30. Zhang Y, Tang M (2021) Consistency of random-walk based network embedding algorithms. arXiv preprint, arXiv:2101.07354. https://doi.org/10.48550/arXiv.2101.07354

  31. Zeng H, Zhou H, Srivastava A, Kannan R, Prasanna V (2020) GraphSAINT: graph sampling based inductive learning method. In: Proceedings of the International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1907.04931

  32. Dang Q, Zhang G, Wang L, Yang S, Zhan T (2024) A generative adversarial networks model based evolutionary algorithm for multimodal multi-objective optimization. IEEE Trans Emerg Top Comput Intell. https://doi.org/10.1109/TETCI.2024.3397996

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

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

    Mahdi Rabiei, Mehdi Fartash & Sara Nazari

Authors
  1. Mahdi Rabiei
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Mehdi Fartash
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Sara Nazari
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

M.R. conceptualized the research idea, developed the methodology, supervised the project, and implemented the proposed algorithms, including data collection and computational experiments. M.F. analyzed and interpreted the results, drafted the manuscript, and prepared visual content (e.g., tables and figures). S.N. reviewed and edited the manuscript, ensured adherence to academic and ethical standards, and provided technical feedback. All authors reviewed and approved the final version of the manuscript and are accountable for its accuracy and integrity.

Corresponding author

Correspondence to Mehdi Fartash.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethical statement

This research utilizes a dataset comprising real-world data from a narcotics trafficking network, obtained through formal authorization from authorized law enforcement agencies while maintaining strict adherence to ethical guidelines and legal frameworks. All personally identifiable information has been systematically encoded through comprehensive data sanitization protocols. The dataset utilization was exclusively restricted to academic research objectives. This investigation was conducted under the supervision and approval of an Institutional Review Board, ensuring comprehensive compliance with established ethical research standards and protocols.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The original online version of this article was revised: In this article the author’s name Mehdi Fartash was incorrectly written as Mahdi Fartash.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rabiei, M., Fartash, M. & Nazari, S. A hybrid optimization approach for graph embedding: leveraging Node2Vec and grey wolf optimization. J Supercomput 81, 514 (2025). https://doi.org/10.1007/s11227-025-07022-2

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-025-07022-2

Keywords