Abstract
Structural properties in a network have mostly been defined in terms of their microscopic level and macroscopic level. Many existing studies focus mainly on learning representations for vertices in similar local proximity such as the direct neighborhood (microscopic level), while some other studies describe the global network connectivity and characteristics (macroscopic level). It is, however, important to understand the substructures between the vertex and network levels so as to capture the structural identities exhibited by vertices. In this paper, we present a novel and flexible approach for learning representations for structural identities of vertices in a network, such that set of vertices with similar structural identity are mapped closely in the low-latent embedding space. Our approach applies the Poisson distribution-based measure and a divergence estimation score to capture nodes’ structural similarities at k-hop proximity via a guided walk. Then, using the Skipgram model, we learn embeddings for nodes with similar structural identity captured in the walk. Experiments with real-life datasets validate our approach, as well as gave superior performance when compared with existing models on link prediction, node classification, and learning-to-rank tasks.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Wen, Y., Guo, L., Chen, Z., Ma, J.: Network embedding based recommendation method in social networks. In: Companion Proceedings of The Web Conference WWW’18, pp. 11–12 (2018). https://doi.org/10.1145/3184558.3186904
Cai, H., Zheng, V.W., Chang, K.C.-C.: A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE Trans. Knowl. Data Eng. 30, 1616–1637 (2017)
Leonardo, R., Pedro, S., Daniel, F.: struc2vec: Learning node representations from structural identity. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining KDD ’17, pp. 385–394 (2017). ACM. https://doi.org/10.1145/3097983.3098061
Francois, L., Harrison, W.: Structural equivalence of individuals in social networks. J. Math. Sociol. 1, 49 (1971)
Narciso, P.: Structural identity and equivalence of individuals in social networks beyond duality. J. Int. Sociol. 22, 767 (2007)
van der Hofstad, R., van Leeuwaarden, J., Stegehuis, C.: Hierarchical configuration model. arXiv:1512.08397 (2015)
Jian, T., Meng, Q., Mingzhe, W., Ming, Z., Jun, Y., Qiaozhu, M.: Line: Large-scale information network embedding. In: Proceedings of the 24th International Conference on World Wide Web, pp. 1067–1077 (2015)
Grover, A., Leskovec, J.: node2vec: Scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–864 (2016). ACM
Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701–710 (2014). ACM
Chen, H., Perozzi, B., Hu, Y., Skiena, S.: Harp: Hierarchical representation learning for networks. In: AAAI (2018)
Mikolov, T., Chen, K., Corrado, G.S., Dean, J.: Efficient estimation of word representations in vector space. Computing Research Repository (CoRR) arXiv:1301.3781 (2013)
Adhikari, B., Zhang, Y., Ramakrishnan, N., Prakash, B.A.: Sub2vec: feature learning for subgraphs. In: PAKDD (2018)
van der Hofstad, R.W., van Leeuwaarden, J.S.H., Stegehuis, C.: Mesoscopic scales in hierarchical configuration models. ArXiv arXiv:1612.02668 (2016)
Pan, S., Wu, J., Zhu, X., Zhang, C., Wang, Y.: Tri-party deep network representation. Networks 11(9), 12–18 (2016)
Dong, Y., Chawla, N., Swami, A.: metapath2vec: Scalable representation learning for heterogeneous networks. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2017)
Perozzi, B., Kulkarni, V., Chen, H., Skiena, S.: Don’t walk, skip!: online learning of multi-scale network embeddings. In: Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining ASONAM ’17, pp. 258–265 (2017). ACM. https://doi.org/10.1145/3110025.3110086
Hanyin, F., Fei, W., Zhou, Z., Xinyu, D., Yueting, Z., Martin, E.: Community-based question answering via heterogeneous social network learning. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence AAAI’16, pp. 122–128 (2016). ACM
Li, C., Ma, J., Guo, X., Mei, Q.: Deepcas: an end-to-end predictor of information cascades. In: Proceedings of the 26th International Conference on World Wide Web (2017)
Sandro, C., Vincent, Z., Hongyun, C., Kevin, C., Erik, C.: Learning community embedding with community detection and node embedding on graphs. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management CIKM ’17, pp. 377–386 (2017). ACM. https://doi.org/10.1145/3132847.3132925
Narayanan, A., Chandramohan, M., Chen, L., Liu, Y., Saminathan, S.: subgraph2vec: learning distributed representations of rooted sub-graphs from large graphs. ArXiv arXiv:1606.08928 (2016)
Rossi, R.A., Ahmed, N.K.: The network data repository with interactive graph analytics and visualization. In: AAAI (2015). https://networkrepository.com
Palmisano, A.: Poisson and binomial distribution. In: Lopez, V. (ed.) The Encyclopedia of Archaeological Sciences, pp. 1–4 (2018)
Belov, D., Armstrong, R.: Distributions of the kullback-leibler divergence with applications. Br. J. Math. Stat. Psychol. 64(2), 291–309 (2011)
Feng, R., Yang, Y., Hu, W., Wu, F., Zhuang, Y.: Representation learning for scale-free networks. ArXiv arXiv:1711.10755 (2018)
Li, J., Zhu, J., Zhang, B.: Discriminative deep random walk for network classification. In: ACL (2016)
Funding
For the research leading to these results, Hamida Seba and Mohammed Haddad received funding from Agence National de la Recherche (ANR) under Grant Agreement No. ANR-20-CE23-0002 and Ikenna Oluigbo was supported by Petroleum Technology Development Fund, Nigeria, with grant number PTDF/GFC/035.
Author information
Authors and Affiliations
Contributions
All authors participated to the study conception and design. Implementation and analysis were performed by IO. The first draft of the manuscript was written by IO and revised by HS. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.
Ethical approval
All authors declare that they adhere to the ethical principles of the journal.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
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.
About this article
Cite this article
Oluigbo, I.V., Seba, H. & Haddad, M. Identity2Vec: learning mesoscopic structural identity representations via Poisson probability metric. Int J Data Sci Anal 17, 249–260 (2024). https://doi.org/10.1007/s41060-023-00390-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41060-023-00390-z