SLICE: Structural and Label Information Combined Embedding for Networks

  • Yiqi Chen
  • Tieyun QianEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10635)


This paper studies the problem of learning representations for network. Existing approaches embed vertices into a low dimensional continuous space which encodes local or global network structures. While these methods show improvements over traditional representations on node classification tasks, they ignore label information until the learnt embeddings are used for training classifier. That is, the process of representation learning is separated from the labels and lacks such information.

In this paper, we propose a novel method which learns the embeddings for vertices under the supervision of labels. Motivated by the idea of label propagation, our approach extends the traditional label propagation to the deep neural network field. The embedding of a node could contain the structural and label information by broadcasting the label information during the training process. We conduct extensive experiments on two real network datasets. Results demonstrate that our approach outperforms both the state-of-the-art graph embedding and label propagation approaches by a large margin.


Representation learning Node classification Label propagation Deep neural network 



The work described in this paper has been supported in part by the NSFC projects (61572376), and the 111 project (B07037).


  1. 1.
    Ahmed, A., Shervashidze, N., Narayanamurthy, S., Josifovski, V., Smola, A.J.: Distributed large-scale natural graph factorization. In: Proceedings of WWW, pp. 37–48 (2013)Google Scholar
  2. 2.
    Angelova, R., Weikum, G.: Graph-based text classification: learn from your neighbors. In: Proceedings of SIGIR, pp. 485–492 (2006)Google Scholar
  3. 3.
    Balasubramanian, M., Schwartz, E.L.: The isomap algorithm and topological stability. Science 295(5552), 7 (2002)CrossRefGoogle Scholar
  4. 4.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. In: Proceedings of NIPS: Natural and Synthetic, pp. 585–591 (2001)Google Scholar
  5. 5.
    Bottou, L.: Stochastic gradient learning in neural networks. In: Neuro-Nîmes (1991)Google Scholar
  6. 6.
    Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Proceedings of NIPS, pp. 3837–3845 (2016)Google Scholar
  7. 7.
    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)zbMATHGoogle Scholar
  8. 8.
    Grover, A., Leskovec, J.: node2vec: scalable feature learning for networks. In: Proceedings of ACM SIGKDD, pp. 855–864 (2016)Google Scholar
  9. 9.
    Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks (2016). arXiv preprint: arXiv:1609.02907
  10. 10.
    Macskassy, S.A., Provost, F.: A simple relational classier. In: Proceedings of the Second Workshop on Multi-Relational Data Mining (MRDM) at KDD-2003, pp. 64–76 (2003)Google Scholar
  11. 11.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. CoRR abs/1301.3781 (2013)Google Scholar
  12. 12.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean., J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of NIPS, pp. 3111–3119 (2013)Google Scholar
  13. 13.
    Perozzi, B., Al-Rfou, R., Skiena., S.: Deepwalk: online learning of social representations. In: Proceedings of ACM SIGKDD, pp. 701–710 (2014)Google Scholar
  14. 14.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)CrossRefGoogle Scholar
  15. 15.
    Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: Line: Large-scale information network embedding. In: Proceedings of WWW, pp. 1067–1077 (2015)Google Scholar
  16. 16.
    Tang, L., Liu, H.: Relational learning via latent social dimensions. In: Proceedings of ACM SIGKDD, pp. 817–826 (2009)Google Scholar
  17. 17.
    Tang, L., Liu, H.: Scalable learning of collective behavior based on sparse social dimensions. In: Proceedings of ACM CIKM, pp. 1107–1116 (2009)Google Scholar
  18. 18.
    Tang, L., Liu, H.: Leveraging social media networks for classification. Data Min. Knowl. Discov. 23(3), 447–478 (2011)CrossRefzbMATHMathSciNetGoogle Scholar
  19. 19.
    Wu, X.M., Li, Z., So, A.M., Wright, J., Chang, S.F.: Learning with partially absorbing random walks. In: Proceedings of NIPS, pp. 3077–3085 (2012)Google Scholar
  20. 20.
    Yamaguchi, Y., Faloutsos, C., Kitagawa, H.: Omni-prop: seamless node classification on arbitrary label correlation. In: Proceedings of AAAI, pp. 3122–3128 (2015)Google Scholar
  21. 21.
    Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Schölkopf, B.: Learning with local and global consistency. In: Proceedings of NIPS, pp. 321–328 (2004)Google Scholar
  22. 22.
    Zhu, X., Ghahramani, Z., Lafferty, J.D.: Semi-supervised learning using gaussian fields and harmonic functions. In: Proceedings of ICML, pp. 912–919 (2003)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.State Key Laboratory of Software EngineeringWuhan UniversityHubeiChina

Personalised recommendations