Abstract
Network embedding, a technique that transforms the nodes and edges of a network into low-dimensional vector representations while preserving relevant structural and semantic information, has gained prominence in recent years. Community structure is one of the most prevalent features of networks, and ensuring its preservation is crucial to represent the network in a lower-dimensional space accurately. While the core objective of network embedding is to bring related nodes in the original network close together in a lower-dimensional space, common classification metrics overlook community structure preservation. This work addresses the need for a comprehensive analysis of network embedding algorithms at the community level. On a set of synthetic networks that span strong to weak community structure strengths, we showcase the variability in the performance of network embedding techniques across mesoscopic metrics. Additionally, we highlight that the mesoscopic metrics are not highly correlated with the classification metrics. The community structure can further diminish the correlation as its strength weakens.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The embedding algorithms were run on the American University of Beirut (AUB)’s high-performance computers using Intel Xeon E5-2665 CPUs in parallel. The runtime of these algorithms is reported in https://github.com/JasonBarbour-2002/ExploringNetworkEmbeddings in Fig. 1 of the supplementary material.
- 2.
Since most methods rely on a stochastic process, we run each method 30 times and take the average and standard deviation of the score for each measure.
References
Girvan, M., Newman, M.E.J.: Community structure in social and biological networks. PNAS 99(12), 7821–7826 (2002)
Cherifi, H., Palla, G., Szymanski, B.K., Lu, X.: On community structure in complex networks: challenges and opportunities. Appl. Netw. Sci. 4(1), 1–35 (2019)
Orman, K., Labatut, V., Cherifi, H.: An empirical study of the relation between community structure and transitivity. In: Menezes, R., Evsukoff, A., González, M. (eds.) Complex Networks. Studies in Computational Intelligence, vol. 424, pp. 99–110. Springer, Cham (2013). https://doi.org/10.1007/978-3-642-30287-9_11
Gupta, N., Singh, A., Cheri, H.: Community-based immunization strategies for epidemic control. In: 2015 7th International Conference on Communication Systems and Networks (COMSNETS), pp. 1–6. IEEE (2015)
Chakraborty, D., Singh, A., Cherifi, H.: Immunization strategies based on the overlapping nodes in networks with community structure. In: Nguyen, H., Snasel, V. (eds.) Computational Social Networks: 5th International Conference, CSoNet 2016, Ho Chi Minh City, Vietnam, 2–4 August 2016, Proceedings 5, pp. 62–73. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-42345-6_6
Kumar, M., Singh, A., Cheri, H.: An efficient immunization strategy using overlapping nodes and its neighborhoods. In: Companion Proceedings of the Web Conference 2018, pp. 1269–1275 (2018)
Ghalmane, Z., Cheri, C., Cheri, H., El Hassouni, M.: Extracting backbones in weighted modular complex networks. Sci. Rep. 10(1), 15539 (2020)
Rajeh, S., Savonnet, M., Leclercq, E., Cheri, H.: Interplay between hierarchy and centrality in complex networks. IEEE Access 8, 129717–129742 (2020)
Rajeh, S., Savonnet, M., Leclercq, E., Cheri, H.: Characterizing the interactions between classical and community-aware centrality measures in complex networks. Sci. Rep. 11(1), 10088 (2021)
Rajeh, S., Savonnet, M., Leclercq, E., Cheri, H.: Comparative evaluation of community-aware centrality measures. Qual. Quant. 57(2), 1273–1302 (2023)
Hou, M., Ren, J., Zhang, D., Kong, X., Zhang, D., Xia, F.: Network embedding: taxonomies, frameworks and applications. Comput. Sci. Rev. 38, 100296 (2020)
Goyal, P., Ferrara, E.: Graph embedding techniques, applications, and performance: a survey. Knowl.-Based Syst. 151, 78–94 (2018)
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)
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)
Rozemberczki, B., Sarkar, R.: Fast sequence-based embedding with diffusion graphs. In: Cornelius, S., Coronges, K., Goncalves, B., Sinatra, R., Vespignani, A. (eds.) Complex Networks IX: Proceedings of the 9th Conference on Complex Networks CompleNet 2018 9, pp. 99–107. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-73198-8_9
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 2017, pp. 258–265 (2017)
Wang, X., Cui, P., Wang, J., Pei, J., Zhu, W., Yang, S.: Community preserving network embedding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)
Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. In: Advances in Neural Information Processing Systems, vol. 14 (2001)
Zhang, Z., Cui, P., Li, H., Wang, X., Zhu, W.: Billion-scale network embedding with iterative random projection. In: ICDM, pp. 787–796. IEEE (2018)
Li, J., Wu, L., Guo, R., Liu, C., Liu, H.: Multi-level network embedding with boosted low-rank matrix approximation. In: Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, pp. 49–56 (2019)
Qiu, J., Dong, Y., Ma, H., Li, J., Wang, K., Tang, J.: Network embedding as matrix factorization: unifying DeepWalk, LINE, PTE, and node2vec. In: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 459–467 (2018)
Salha-Galvan, G., Lutzeyer, J.F., Dasoulas, G., Hennequin, R., Vazirgiannis, M.: Modularity-aware graph autoencoders for joint community detection and link prediction. Neural Networks 153, 474–495 (2022)
Xuan Vinh, N., Epps, J., Bailey, J.: Information theoretic measures for clusterings comparison: is a correction for chance necessary? In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 1073–1080 (2009)
Kamiński, B., Prałat, P., Théberge, F.: Artificial benchmark for community detection (ABCD)-fast random graph model with community structure. Netw. Sci. 9(2), 153–178 (2021)
Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Math. Stat. 22(1), 79–86 (1951)
Schulze, M.: A new monotonic, clone-independent, reversal symmetric, and condorcet-consistent single-winner election method. Soc. Choice Welfare 36, 267–303 (2011)
Strang, G.: Linear algebra and learning from data. SIAM (2019)
Acknowledgment
S.N and J.B would like to acknowledge support from the Center for Advanced Mathematical Science (CAMS) at the American University of Beirut (AUB).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Barbour, J., Rajeh, S., Najem, S., Cherifi, H. (2024). Evaluating Network Embeddings Through the Lens of Community Structure. In: Cherifi, H., Rocha, L.M., Cherifi, C., Donduran, M. (eds) Complex Networks & Their Applications XII. COMPLEX NETWORKS 2023. Studies in Computational Intelligence, vol 1141. Springer, Cham. https://doi.org/10.1007/978-3-031-53468-3_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-53468-3_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53467-6
Online ISBN: 978-3-031-53468-3
eBook Packages: EngineeringEngineering (R0)