Abstract
User identity linkage has important implications in many cross-network applications, such as user profile modeling, recommendation and link prediction across social networks. To discover accurate cross-network user correspondences, it is a critical prerequisite to find effective user representations. While structural and content information describe users from different perspectives, there is a correlation between the two aspects of information. For example, a user who follows a celebrity tends to post content about the celebrity as well. Therefore, the projections of structural and content information of a user should be as close to each other as possible, which inspires us to fuse the two aspects of information in a unified space. However, owing to the information heterogeneity, most existing methods extract features from content and structural information respectively, instead of describing them in a unified way. In this paper, we propose a Linked Heterogeneous Network Embedding model (LHNE) to learn the comprehensive representations of users by collectively leveraging structural and content information in a unified framework. We first model the topics of user interests from content information to filter out noise. Next, cross-network structural and content information are embedded into a unified space by jointly capturing the friend-based and interest-based user co-occurrence in intra-network and inter-network, respectively. Meanwhile, LHNE learns user transfer and topic transfer for enhancing information exchange across networks. Empirical results show LHNE outperforms the state-of-the-art methods on both real social network and synthetic datasets and can work well even with little or no structural information.









Similar content being viewed by others
Notes
The features include extended common neighbors, extended Jaccard’s coefficient, extended Adamic/Adar Measure and users’ topic distribution.
Actually, the anchor links between users and topic links between topics are regarded as virtual links by user and topic transfer. The cross-network bridge nodes can be regarded as the same nodes with the help of virtual links. Therefore, the user-topic inter-network is a bipartite network, because there are only real edges between source and target nodes like user-topic intra-network.
Note that, if it is known that the two social networks are fully aligned, then for any user \({u_{i}^{x}}\) with no corresponding user \({u_{j}^{y}}\) such that \(rel({u_{i}^{x}}, {u_{j}^{y}})>w\), we simply return the user \({u_{j}^{y}}\) with the maximum similarity value.
References
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
Cai, H., Zheng, V.W., Chang, K.C.C.: A comprehensive survey of graph embedding: Problems, techniques and applications. arXiv:1709.07604 (2017)
Cao, X., Yu, Y.: Bass: a bootstrapping approach for aligning heterogenous social networks. In: ECML PKDD, pp. 459–475 (2016)
Cao, X., Yu, Y.: Joint user modeling across aligned heterogeneous sites. In: Recsys, pp. 83–90 (2016)
Chen, W., Yin, H., Wang, W., Zhao, L., Hua, W., Zhou, X.: Exploiting spatio-temporal user behaviors for user linkage. In: CIKM, pp. 517–526 (2017)
Dong, Y., Tang, J., Wu, S., Tian, J., Chawla, N.V., Rao, J., Cao, H.: Link prediction and recommendation across heterogeneous social networks. In: ICDM, pp. 181–190 (2012)
Kong, X., Zhang, J., Yu, P.S.: Inferring anchor links across multiple heterogeneous social networks. In: CIKM, pp. 179–188 (2013)
Korula, N., Lattanzi, S.: An efficient reconciliation algorithm for social networks. pp. 377–388 (2014)
Liu, S., Wang, S., Zhu, F., Zhang, J., Krishnan, R.: Hydra: large-scale social identity linkage via heterogeneous behavior modeling. In: ACM SIGMOD, pp. 51–62 (2014)
Liu, L., Cheung, W. K., Li, X., Liao, L.: Aligning users across social networks using network embedding. In: IJCAI, pp. 1774–1780 (2016)
Malhotra, A., Totti, L., Meira, Jr, W., Kumaraguru, P., Almeida, V.: Studying user footprints in different online social networks. In: ASONAM, pp. 1065–1070 (2012)
Man, T., Shen, H., Huang, J., Cheng, X.: Context-adaptive matrix factorization for multi-context recommendation. In: CIKM, pp. 901–910 (2015)
Man, T., Shen, H., Liu, S., Jin, X., Cheng, X.: Predict anchor links across social networks via an embedding approach. In: IJCAI, vol. 16, pp. 1823–1829 (2016)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Mu, X., Zhu, F., Lim, E.P., Xiao, J., Wang, J., Zhou, Z.H.: User identity linkage by latent user space modelling. In: KDD, pp. 1775–1784 (2016)
Narayanan, A., Shmatikov, V.: De-anonymizing social networks. In: ISSP, pp. 173–187 (2009)
Nie, Y., Jia, Y., Li, S., Zhu, X., Li, A., Zhou, B.: Identifying users across social networks based on dynamic core interests. Neurocomputing 210, 107–115 (2016)
Phan, M.C., Sun, A., Tay, Y.: Cross-device user linking: url, session, visiting time, and device-log embedding. In: SIGIR, pp. 933–936 (2017)
Recht, B., Re, C., Wright, S., Niu, F.: Hogwild: a lock-free approach to parallelizing stochastic gradient descent. In: NIPS, pp. 693–701 (2011)
Riederer, C., Kim, Y., Chaintreau, A., Korula, N., Lattanzi, S.: Linking users across domains with location data: theory and validation. In: WWW, pp. 707–719 (2016)
Shu, K., Wang, S., Tang, J., Zafarani, R., Liu, H.: User identity linkage across online social networks: a review. ACM SIGKDD Explorations Newsletter 18(2), 5–17 (2017)
Tan, S., Guan, Z., Cai, D., Qin, X., Bu, J., Chen, C.: Mapping users across networks by manifold alignment on hypergraph. In: AAAI, vol. 14, pp. 159–165 (2014)
Tang, J., Qu, M., Mei, Q.: Pte: predictive text embedding through large-scale heterogeneous text networks. In: KDD, pp. 1165–1174 (2015)
Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: Line: large-scale information network embedding. In: WWW, pp. 1067–1077 (2015)
Xie, M., Yin, H., Wang, H., Xu, F., Chen, W., Wang, S.: Learning graph-based Poi embedding for location-based recommendation. In: CIKM, pp. 15–24 (2016)
Yan, M., Sang, J., Mei, T., Xu, C.: Friend transfer: cold-start friend recommendation with cross-platform transfer learning of social knowledge. In: ICME, pp. 1–6 (2013)
Yan, M., Sang, J., Xu, C., Hossain, M.S.: Youtube video promotion by cross-network association:@ britney to advertise gangnam style. TMM 17(8), 1248–1261 (2015)
Yan, M., Sang, J., Xu, C., Hossain, M.S.: A unified video recommendation by cross-network user modeling. TOMM 12(4), 53 (2016)
Yang, D., Xiao, Y., Tong, H., Cui, W., Wang, W.: Towards topic following in heterogeneous information networks. In: ASONAM, pp. 363–366 (2015)
Zafarani, R., Liu, H.: Connecting corresponding identities across communities. pp 354–357 (2009)
Zhang, J., Philip, S. Y.: Integrated anchor and social link predictions across social networks. In: IJCAI, pp. 2125–2132 (2015)
Zhang, J., Kong, X., Philip, S.Y.: Predicting social links for new users across aligned heterogeneous social networks. In: ICDM, pp. 1289–1294 (2013)
Zhang, J., Kong, X., Yu, P. S.: Transferring heterogeneous links across location-based social networks. In: WSDM, pp. 303–312 (2014)
Zhang, J., Yu, P.S., Zhou, Z.H.: Meta-path based multi-network collective link prediction. In: KDD, pp. 1286–1295 (2014)
Author information
Authors and Affiliations
Corresponding author
Additional information
This article belongs to the Topical Collection: Special Issue on Web and Big Data
Guest Editors: Junjie Yao, Bin Cui, Christian S. Jensen, and Zhe Zhao
Rights and permissions
About this article
Cite this article
Wang, Y., Feng, C., Chen, L. et al. User identity linkage across social networks via linked heterogeneous network embedding. World Wide Web 22, 2611–2632 (2019). https://doi.org/10.1007/s11280-018-0572-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11280-018-0572-3