Abstract
Role-oriented network embedding has become a powerful technique for solving real-world problems, because it can capture the structures of nodes and make node embeddings better reflect the functions or behaviors of entities in the network. At present, various role-oriented network embedding methods have been proposed. However, most of the methods ignore degree distribution and the commonalities among local structures, resulting in insufficient information of node embeddings, and some methods that preserve commonality always have high time complexity. To address the above challenges, we propose a novel model ReVaC from two aspects of extracting higher-quality local structural features and strengthening the commonalities among local structures in node embeddings. In detail, the degree distribution from node’s 1-hop egonet is incorporated into the extraction process of local structural features to improve traditional ReFeX firstly, and the Variational Auto-Encoder is used to map those features to the local structural embedding space. Then, in the embedding space, we cluster nodes to model the commonalities among local structures. Finally, local structural embeddings and commonalities are fused to get node embeddings. We conduct extensive comparative experiments on real-word networks, and results show that ReVaC has better performance than other state-of-the-art approaches and adapts well to network scale.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Jin, J., Heimann, M., Jin, D., Koutra, D.: Toward understanding and evaluating structural node embeddings. ACM Trans. Knowl. Discov. Data 16(3), 1–32 (2022)
Ribeiro, L., Saverese, P., Figueiredo, D.: struc2vec: Learning node representations from structural identity, vol. 129685, pp. 385–394. ACM (2017)
Heimann, M., Shen, H., Safavi, T., Koutra, D.: Regal: representation learning-based graph alignment, pp. 117–126. ACM (2018)
Henderson, K., Gallagher, B., Li, L., Akoglu, L., Eliassi-Rad, T., Tong, H., Faloutsos, C.: It’s who you know: graph mining using recursive structural features, pp. 663–671. ACM (2011)
Henderson, K., et al.: Rolx: structural role extraction mining in large graphs, pp. 1231–1239. ACM (2012)
Gilpin, S., Eliassi-Rad, T., Davidson, I.: Guided learning for role discovery (glrd): framework, algorithms, and applications. vol. 128815, pp. 113–121. ACM (2013)
Zhang, W., Guo, X., Wang, W., Tian, Q., Pan, L., Jiao, P.: Role-based network embedding via structural features reconstruction with degree-regularized constraint. Knowl.-Based Syst. 218, 106872 (2021)
Jiao, P., Tian, Q., Zhang, W., Guo, X., Jin, D., Wu, H.: Role discovery-guided network embedding based on autoencoder and attention mechanism. IEEE Trans. Cybern. PP, 1–14 (2021)
Guo, X., Zhang, W., Wang, W., Yu, Y., Wang, Y., Jiao, P.: Role-oriented graph auto-encoder guided by structural information 12113, 466–481 (2020)
Joaristi, M., Serra, E.: Sir-gn: a fast structural iterative representation learning approach for graph nodes. ACM Trans. Knowl. Discov. Data 15(6), 1–39 (2021)
Liang, Q., et al.: Rolne: improving the quality of network embedding with structural role proximity, vol. 12342, pp. 16–28 (2020)
Rossi, R., Ahmed, N., Koh, E., Kim, S., Rao, A., Abbasi-Yadkori, Y.: A structural graph representation learning framework, pp. 483–491. ACM (2020)
Donnat, C., Zitnik, M., Hallac, D., Leskovec, J.: Learning structural node embeddings via diffusion wavelets, pp. 1320–1329. ACM (2018;2017;)
Tu, K., Cui, P., Wang, X., Yu, P., Zhu, W.: Deep recursive network embedding with regular equivalence, pp. 2357–2366. ACM (2018)
Jin, Y., Song, G., Shi, C.: Gralsp: graph neural networks with local structural patterns, pp. 4361–4368 (2020)
Nikolentzos, G., Vazirgiannis, M.: Learning structural node representations using graph kernels. IEEE Trans. Knowl. Data Eng. 33(5), 2045–2056 (2021, 2019)
Pei, Y., Fletcher, G., Pechenizkiy, M.: Joint role and community detection in networks via l2,1 norm regularized nonnegative matrix tri-factorization, pp. 168–175. ACM (2019)
Jin, R., Lee, V., Hong, H.: Axiomatic ranking of network role similarity, pp. 922–930. ACM (2011)
Pei, Y., Du, X., Zhang, J., Fletcher, G., Pechenizkiy, M.: struc2gauss: structural role preserving network embedding via gaussian embedding. Data Min. Knowl. Disc. 34(4), 1072–1103 (2020)
Shi, B., Zhou, C., Qiu, H., Xu, X., Liu, J.: Unifying structural proximity and equivalence for network embedding. IEEE access 7, 106124–106138 (2019)
Ahmed, N.K., et al.: Role-based graph embeddings. IEEE Trans. Knowl. Data Eng. 34(5), 2401–2415 (2022, 2020)
Rossi, R.A., Ahmed, N.K.: The network data repository with interactive graph analytics and visualization. 6, 4292–4293 (2015)
Leskovec, J., Huttenlocher, D., Kleinberg, J.: Predicting positive and negative links in online social networks, pp. 641–650. ACM (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ge, L., Ye, X., Jia, Y., Li, Q. (2022). Role-Oriented Network Embedding Method Based on Local Structural Feature and Commonality. In: Khanna, S., Cao, J., Bai, Q., Xu, G. (eds) PRICAI 2022: Trends in Artificial Intelligence. PRICAI 2022. Lecture Notes in Computer Science, vol 13630. Springer, Cham. https://doi.org/10.1007/978-3-031-20865-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-20865-2_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20864-5
Online ISBN: 978-3-031-20865-2
eBook Packages: Computer ScienceComputer Science (R0)