Abstract
In recent years, aligning users across different social networks receives a significant attention. Previous studies solve the problem based on attributes or topology structure approximation. However, most of them suffer from error propagation or the noise from diverse neighbors. To address the drawback, we design intra and inter attention mechanisms to model the influence of neighbors in local and across networks. In addition, to effectively incorporate the topology structure information, we leverage neighbors from labeled pairs instead of these in original networks, which are termed as matched neighbors. Then we treat the user alignment problem as a classification task and predict it upon a deep neural network. We conduct extensive experiments on six real-world datasets, and the results demonstrate the superiority of the proposed method against state-of-the-art competitors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Kong, X., Zhang, J., Yu, P.S.: Inferring anchor links across multiple heterogeneous social networks. In: ACM International Conference on Information & Knowledge Management, pp. 179–188 (2013)
Liu, J., Zhang, F., Song, X., Song, Y.I., Lin, C.Y., Hon, H.W.: What’s in a name?: An unsupervised approach to link users across communities. In: ACM International Conference on Web Search & Data Mining, pp. 495–504 (2013)
Liu, L., Cheung, W.K., Li, X., Liao, L.: Aligning users across social networks using network embedding. In: International Joint Conference on Artificial Intelligence, pp. 1774–1780 (2016)
Man, T., Shen, H., Liu, S., Jin, X., Cheng, X.: Predict anchor links across social networks via an embedding approach. In: International Joint Conference on Artificial Intelligence, pp. 1823–1829 (2016)
Mu, X., Zhu, F., Lim, E.P., Xiao, J., Wang, J., Zhou, Z.H.: User identity linkage by latent user space modelling. In: ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1775–1784 (2016)
Zafarani, R., Liu, H.: Connecting users across social media sites: a behavioral-modeling approach. In: ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 41–49 (2013)
Zhang, J., et al.: Mego2vec: embedding matched ego networks for user alignment across social networks. In: ACM International Conference on Information & Knowledge Management, pp. 327–336 (2018)
Zhang, S., Tong, H.: Final: fast attributed network alignment. In: ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1345–1354 (2016)
Zhong, Z., Cao, Y., Guo, M., Nie, Z.: Colink: an unsupervised framework for user identity linkage. In: AAAI Conference on Artificial Intelligence, pp. 5714–5721 (2018)
Zhou, G., et al.: Deep interest network for click-through rate prediction. In: ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1059–1068 (2018)
Acknowledgments
This research was supported in part by the National Key R&D Program of China, 2018YFB2101100, 2018YFB2101101 and NSFC under Grant Nos. 61972111, U1836107, 61602132 and 61572158.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, Z., Li, X., Ye, Y. (2020). Aligning Users Across Social Networks via Intra and Inter Attentions. In: Wang, X., Zhang, R., Lee, YK., Sun, L., Moon, YS. (eds) Web and Big Data. APWeb-WAIM 2020. Lecture Notes in Computer Science(), vol 12317. Springer, Cham. https://doi.org/10.1007/978-3-030-60259-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-60259-8_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60258-1
Online ISBN: 978-3-030-60259-8
eBook Packages: Computer ScienceComputer Science (R0)