Abstract
Unsupervised NRL (Network Representation Learning) methods only consider the network structure information, which makes their learned node representations less discriminative. To utilize the label information of the partially labeled network, several semi-supervised NRL methods are proposed. The key idea of these methods is to merge the representation learning step and the classifier training step together. However, it is not flexible enough and their parameters are often hard to tune. In this paper, we provide a new point of view for semi-supervised NRL and present a novel model named Predictive Network Embedding (PNE). Briefly, we embed nodes and labels into the same latent space instead of training a classifier in the representation learning process. Thus the discriminability of node representations is enhanced by incorporating the label information. We conduct node classification task on four real world datasets. The experimental results demonstrate that our model significantly outperforms the state-of-the-art baselines.
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
References
Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. NIPS 14, 585–591 (2001)
Bourigault, S., Lagnier, C., Lamprier, S., Denoyer, L., Gallinari, P.: Learning social network embeddings for predicting information diffusion. In: WSDM, pp. 393–402. ACM (2014)
Cao, S., Lu, W., Xu, Q.: GraRep: learning graph representations with global structural information. In: CIKM, pp. 891–900. ACM (2015)
Chen, M., Yang, Q., Tang, X.: Directed graph embedding. In: IJCAI, pp. 2707–2712 (2007)
Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., Lin, C.-J.: Liblinear: a library for large linear classification. J. Mach. Learn. Res. 9, 1871–1874 (2008)
Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: SIGKDD, pp. 855–864. ACM, New York (2016)
Jacob, Y., Denoyer, L., Gallinari, P.: Learning latent representations of nodes for classifying in heterogeneous social networks. In: WSDM, pp. 373–382. ACM (2014)
Ji, M., Sun, Y., Danilevsky, M., Han, J., Gao, J.: Graph regularized transductive classification on heterogeneous information networks. In: Balcázar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010. LNCS (LNAI), vol. 6321, pp. 570–586. Springer, Heidelberg (2010). doi:10.1007/978-3-642-15880-3_42
Kullback, S., Leibler, R.A.: On information and sufficiency. Annals Math. Stat. 22(1), 79–86 (1951)
Lim, K.W., Buntine, W.L.: Bibliographic analysis with the citation network topic model. In: ACML (2014)
McCallum, A.K., Nigam, K., Rennie, J., Seymore, K.: Automating the construction of internet portals with machine learning. Inf. Retr. 3(2), 127–163 (2000)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS, pp. 3111–3119 (2013)
Pan, S., Wu, J., Zhu, X., Zhang, C., Wang, Y.: Tri-party deep network representation. In: IJCAI-2016, pp. 1895–1901 (2016)
Perozzi, B., Al-Rfou, R., Skiena, S.: DeepWalk: online learning of social representations. In: SIGKDD, pp. 701–710. ACM, New York (2014)
Perozzi, B., Kulkarni, V., Skiena, S.: Walklets: multiscale graph embeddings for interpretable network classification. arXiv preprint arXiv:1605.02115 (2016)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Sen, P., Namata, G., Bilgic, M., Getoor, L., Galligher, B., Eliassi-Rad, T.: Collective classification in network data. AI Mag. 29(3), 93 (2008)
Tang, J., Qu, M., Mei, Q.: PTE: predictive text embedding through large-scale heterogeneous text networks. In: SIGKDD, pp. 1165–1174. ACM, New York (2015)
Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: LINE: large-scale information network embedding. In: WWW, pp. 1067–1077. ACM, New York (2015)
Tu, C., Zhang, W., Liu, Z., Sun, M.: Max-margin DeepWalk: discriminative learning of network representation. In: IJCAI, pp. 3889–3895 (2016)
Walker, A.J.: New fast method for generating discrete random numbers with arbitrary frequency distributions. Electron. Lett. 8(10), 127–128 (1974)
Yang, C., Liu, Z., Zhao, D., Sun, M., Chang, E.Y.: Network representation learning with rich text information. In: IJCAI, pp. 2111–2117. AAAI Press (2015)
Yang, Y., Chawla, N., Sun, Y., Hani, J.: Predicting links in multi-relational and heterogeneous networks. In: ICDM, pp. 755–764. IEEE (2012)
Yang, Z., Cohen, W., Salakhutdinov, R.: Revisiting semi-supervised learning with graph embeddings. arXiv preprint arXiv:1603.08861 (2016)
Acknowledgments
This work is supported by 973 Program with Grant No. 2014CB340400. Yan Zhang is supported by NSFC with Grant No. 61532001 and No. 61370054, and MOE-RCOE with Grant No. 2016ZD201. And we also thank the three anonymous reviewers for their valuable comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Chen, W., Mao, X., Li, X., Zhang, Y., Li, X. (2017). PNE: Label Embedding Enhanced Network Embedding. In: Kim, J., Shim, K., Cao, L., Lee, JG., Lin, X., Moon, YS. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2017. Lecture Notes in Computer Science(), vol 10234. Springer, Cham. https://doi.org/10.1007/978-3-319-57454-7_43
Download citation
DOI: https://doi.org/10.1007/978-3-319-57454-7_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57453-0
Online ISBN: 978-3-319-57454-7
eBook Packages: Computer ScienceComputer Science (R0)