Gaussian mixture embedding of multiple node roles in networks

  • Yujun Chen
  • Juhua Pu
  • Xingwu Liu
  • Xiangliang ZhangEmail author
Part of the following topical collections:
  1. Special Issue on Graph Data Management in Online Social Networks


Network embedding is a classical topic in network analysis. Current network embedding methods mostly focus on deterministic embedding, which maps each node as a low-dimensional vector. Thus, the network uncertainty and the possible multiple roles of nodes cannot be well expressed. In this paper, we propose to embed a single node as a mixture of Gaussian distribution in a low-dimensional space. Each Gaussian component corresponds to a latent role that the node plays. The proposed approach thus can characterize network nodes in a comprehensive representation, especially bridging nodes, which are relevant to different communities. Experiments on real-world network benchmarks demonstrate the effectiveness of our approach, outperforming the state-of-the-art network embedding methods. Also, we demonstrate that the number of components learned for each node is highly related to its topology features, such as node degree, centrality and clustering coefficient.


Network embedding Gaussian mixture distribution Energy based learning Graph mining 



This work was partially supported and funded by King Abdullah University of Science and Technology (KAUST), under award number FCC/1/1976-19-01, and NSFC No 61828302, the National Key Research and Development Program of China (2017YFB1002000), Science Technology and Innovation Commission of Shenzhen Municipality (JCYJ20180307123659504), and the State Key Laboratory of Software Development Environment in Beihang University.


  1. 1.
    Ahmed, A., Shervashidze, N., Narayanamurthy, S., Josifovski, V., Smola, A.J.: Distributed large-scale natural graph factorization. In: WWW, pp 37–48. ACM (2013)Google Scholar
  2. 2.
    Akujuobi, U., Yufei, H., Zhang, Q., Zhang, X.: Collaborative graph walk for semi-supervised multi-label node classification. In: ICDM (2019)Google Scholar
  3. 3.
    Athiwaratkun, B., Wilson, A.G.: Multimodal word distributions. In: Conference of the Association for Computational Linguistics (ACL) (2017)Google Scholar
  4. 4.
    Balafar, M.: Gaussian mixture model based segmentation methods for brain mri images. Artif. Intell. Rev. 41(3), 429–439 (2014)CrossRefGoogle Scholar
  5. 5.
    Belkin, M., Niyogi, P: Laplacian eigenmaps and spectral techniques for embedding and clustering. In: NIPS, pp 585–591 (2002)Google Scholar
  6. 6.
    Bengio, Y., Courville, A., Vincent, P.: Representation learning: A review and new perspectives. IEEE TPAMI 35(8), 1798–1828 (2013)CrossRefGoogle Scholar
  7. 7.
    Bojchevski, A., Günnemann, S.: Deep Gaussian embedding of attributed graphs: Unsupervised inductive learning via ranking ICLR (2018)Google Scholar
  8. 8.
    Boureau, Y.-l., Cun, Y.L., et al.: Sparse feature learning for deep belief networks. In: NIPS, pp 1185–1192 (2008)Google Scholar
  9. 9.
    Bouveyron, C., Brunet-Saumard, C.: Model-based clustering of high-dimensional data: A review. Comput. Stat. Data Anal. 71, 52–78 (2014)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Breitkreutz, B.-J., Stark, C., Reguly, T., Boucher, L., Breitkreutz, A., Livstone, M., Oughtred, R., Lackner, D.H., Bähler, J., Wood, V., et al.: The biogrid interaction database. Nucleic Acids Res. 36(suppl_1), D637–D640 (2008)Google Scholar
  11. 11.
    Cai, H., Zheng, V.W., Chang, K.: A comprehensive survey of graph embedding: Problems, techniques and applications TKDE (2018)Google Scholar
  12. 12.
    Cao, S., Lu, W., Xu, Q.: Deep neural networks for learning graph representations. In: AAAI, pp 1145–1152 (2016)Google Scholar
  13. 13.
    Chen, X., Qiu, X., Jiang, J., Huang, X.: Gaussian mixture embeddings for multiple word prototypes. arXiv:1511.06246 (2015)
  14. 14.
    Chen, X., Yu, G., Wang, J., Domeniconi, C., Li, Z., Zhang, X.: ActiveHNE: Active heterogeneous network embedding. In: IJCAI (2019)Google Scholar
  15. 15.
    Cui, P., Wang, X., Pei, J., Zhu, W.: A survey on network embedding. IEEE Transactions on Knowledge and Data Engineering (2018)Google Scholar
  16. 16.
    Dos Santos, L., Piwowarski, B., Gallinari, P.: Multilabel classification on heterogeneous graphs with gaussian embeddings. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp 606–622. Springer (2016)Google Scholar
  17. 17.
    Durrieu, J.-L., Thiran, J.-P., Kelly, F.: Lower and upper bounds for approximation of the kullback-leibler divergence between gaussian mixture models. In: ICASSP, pp 4833–4836 (2012)Google Scholar
  18. 18.
    Epasto, A., Perozzi, B.: Is a single embedding enough? Learning node representations that capture multiple social contexts in the Web conference (2019)Google Scholar
  19. 19.
    Gao, X., Carroll, R.J.: Data integration with high dimensionality. Biometrika 104(2), 251–272 (2017)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Grover, A., Leskovec, J.: node2vec: Scalable feature learning for networks. In: SIGKDD, pp 855–864. ACM (2016)Google Scholar
  21. 21.
    Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR, vol. 2, pp 1735–1742. IEEE (2006)Google Scholar
  22. 22.
    Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS (2017)Google Scholar
  23. 23.
    Hamilton, W.L., Ying, R., Leskovec, J.: Representation learning on graphs: Methods and applications. arXiv:1709.05584 (2017)
  24. 24.
    He, S., Liu, K., Ji, G., Zhao, J.: Learning to represent knowledge graphs with gaussian embedding. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pp 623–632. ACM (2015)Google Scholar
  25. 25.
    Hershey, J.R., Olsen, P.A.: Approximating the Kullback Leibler divergence between gaussian mixture models. ICASSP 4, IV–317–IV–320 (2007)Google Scholar
  26. 26.
    Higuchi, T., Ito, N., Araki, S., Yoshioka, T., Delcroix, M., Nakatani, T.: Online mvdr beamformer based on complex gaussian mixture model with spatial prior for noise robust asr. IEEE/ACM Trans. Audio Speech Language Process. 25(4), 780–793 (2017)CrossRefGoogle Scholar
  27. 27.
    Jebara, T., Kondor, R.: Bhattacharyya and expected likelihood kernels. In: Learning Theory and Kernel Machines, pp 57–71. Springer (2003)Google Scholar
  28. 28.
    Jebara, T., Kondor, R.I., Howard, A.: Probability product kernels. JMLR 5, 819–844 (2004)MathSciNetzbMATHGoogle Scholar
  29. 29.
    Jiang, J., Yang, D., Xiao, Y., Shen, C.: Convolutional Gaussian embeddings for personalized recommendation with uncertainty. In: IJCAI (2019)Google Scholar
  30. 30.
    Knuth, D.E.: The Stanford GraphBase: A Platform for Combinatorial Computing, vol. 37. Addison-Wesley, Reading (1993)zbMATHGoogle Scholar
  31. 31.
    Li, L., Zheng, K., Wang, S., Zhou, X.: Go slow to go fast: Minimal On-road time route scheduling with parking facilities using historical trajectory. VLDB J. 27 (3), 321–345 (2018)CrossRefGoogle Scholar
  32. 32.
    Lian, D., Zheng, K., Ge, Y., Cao, L., Chen, E., Xie, X.: GeoMF++: Scalable location recommendation via joint geographical modeling and matrix factorization. ACM Trans. Inf. Syst. 36(3), 33:1–33:29 (2018)CrossRefGoogle Scholar
  33. 33.
    LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., Huang, F.: A tutorial on energy-based learning. Predict. Struct. Data 1, 0 (2006)Google Scholar
  34. 34.
    Levy, O., Goldberg, Y., Dagan, I.: Improving distributional similarity with lessons learned from word embeddings. Trans. Assoc. Comput. Linguist. 3, 211–225 (2015)CrossRefGoogle Scholar
  35. 35.
    Liang, S., Zhang, X., Ren, Z., Kanoulas, E.: Dynamic embeddings for user profiling in Twitter. In: KDD (2018)Google Scholar
  36. 36.
    Liu, G., Zheng, K., Liu, A., Li, Z., Wang, Y., Zhou, X.: MCS-GPM: Multi-constrained simulation based graph pattern matching in contextual social graphs. TKDE 30(6), 1050–1064 (2018)Google Scholar
  37. 37.
    Liu, X., Murata, T., Kim, K., Kotarasu, C, Zhuang, C: A general view for network embedding as matrix factorization in WSDM (2019)Google Scholar
  38. 38.
    Ma, Y., Ren, Z., Jiang, Z., Tang, J., Yin, D.: Multi-dimensional network embedding with hierarchical structure WSDM (2018)Google Scholar
  39. 39.
    Mahoney, M.: Large text compression benchmark, (2011)
  40. 40.
    Meng, Z., Liang, S., Bao, H., Zhang, X.: Co-embedding attributed networks. In: WSDM (2019)Google Scholar
  41. 41.
    Mueller, J., Thyagarajan, A.: Siamese recurrent architectures for learning sentence similarity. In: AAAI, pp 2786–2792 (2016)Google Scholar
  42. 42.
    Neculoiu, P., Versteegh, M., Rotaru, M.: Learning text similarity with siamese recurrent networks. In: Proceedings of the 1st Workshop on Representation Learning for NLP, pp 148–157 (2016)Google Scholar
  43. 43.
    Paulik, M: Lattice-based training of bottleneck feature extraction neural networks. In: Interspeech, pp 89–93 (2013)Google Scholar
  44. 44.
    Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: Online learning of social representations. In: SIGKDD, pp 701–710. ACM (2014)Google Scholar
  45. 45.
    Perozzi, B., Kulkarni, V., Chen, H., Skiena, S.: Don’t walk, skip!: Online learning of multi-scale network embeddings. In: Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017, pp 258–265. ACM (2017)Google Scholar
  46. 46.
    Qiu, J., Dong, Y., Ma, H., Li, J., Wang, K., Tang, J.: Network embedding as matrix factorization unifying DeepWalk, LINE, PTE, and node2vec. In: WSDM (2018)Google Scholar
  47. 47.
    Qu, M., Tang, J., Shang, J., Ren, X., Zhang, M., Han, J.: An attention-based collaboration framework for multi-view network representation learning. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp 1767–1776. ACM (2017)Google Scholar
  48. 48.
    Reynolds, D.: Gaussian mixture models. Encycloped. Biom., 827–832 (2015)Google Scholar
  49. 49.
    Ribeiro, L.F., Saverese, P.H., Figueiredo, D.R.: struc2vec: Learning node representations from structural identity. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 385–394. ACM (2017)Google Scholar
  50. 50.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)CrossRefGoogle Scholar
  51. 51.
    Sun, G., Zhang, X.: A novel framework for node/edge attributed graph embedding. In: PAKDD (2019)CrossRefGoogle Scholar
  52. 52.
    Tang, L., Liu, H.: Leveraging social media networks for classification. Data Min. Knowl. Disc. 23(3), 447–478 (2011)MathSciNetCrossRefGoogle Scholar
  53. 53.
    Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: LINE: Large-scale information network embedding. WWW, pp. 1067–1077. [Online]. Available: 1503.03578 (2015)
  54. 54.
    Tang, J., Qu, M., Mei, Q.: Identity-sensitive word embedding through heterogeneous networks. arXiv:1611.09878 (2016)
  55. 55.
    Tao, R., Gavves, E., Smeulders, A.W.: Siamese instance search for tracking. In: CVPR, pp 1420–1429. IEEE (2016)Google Scholar
  56. 56.
    Tsitsulin, A., Mottin, D., Karras, P., Müller, E.: Verse: Versatile graph embeddings from similarity measures. In: Proceedings of the 2018 World Wide Web Conference, ser WWW, pp 539–548 (2018)Google Scholar
  57. 57.
    Vilnis, L., Mccallum, A.: Word representations via gaussian embedding. In: ICLR, pp 1–12 (2015)Google Scholar
  58. 58.
    Yang, C., Liu, Z., Zhao, D., Sun, M., Chang, E.Y.: Network representation learning with rich text information. IJCAI 2015-Janua, 2111–2117 (2015)Google Scholar
  59. 59.
    Yang, Z., Cohen, W., Salakhutdinov, R.: Revisiting semi-supervised learning with graph embeddings. ICML, vol. 48. [Online]. Available: 1603.08861(2016)
  60. 60.
    Yang, X., Huang, K., Goulermas, J.Y., Zhang, R.: Joint learning of unsupervised dimensionality reduction and gaussian mixture model. Neural. Process. Lett. 45, 791–806 (2017)CrossRefGoogle Scholar
  61. 61.
    Yang, R., Shi, J., Xiao, X., Bhowmick, S.S., Yang, Y.J.: Homogeneous network embedding for massive graphs via personalized pagerank. ArXiv (2019)Google Scholar
  62. 62.
    Zhang, M.-L., Zhou, Z.-H.: Ml-knn: A lazy learning approach to multi-label learning. Pattern Recogn. 40(7), 2038–2048 (2007)CrossRefGoogle Scholar
  63. 63.
    Zhang, C., Woodland, P.: Joint optimisation of tandem systems using gaussian mixture density neural network discriminative sequence training. In: ICASSP, pp 5015–5019. IEEE (2017)Google Scholar
  64. 64.
    Zhang, D., Yin, J., Zhu, X., Zhang, C.: User profile preserving social network embedding. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp 3378–3384. AAAI Press (2017)Google Scholar
  65. 65.
    Zhang, J., Dong, Y., Wang, Y., Tang, J., Ding, M.: ProNE: Fast and scalable network representation learning in IJCAI (2019)Google Scholar
  66. 66.
    Zheng, K., Zheng, Y., Yuan, N.J., Shang, S., Zhou, X.: Online discovery of gathering patterns over trajectories. IEEE Trans. Knowl. Data Eng. 26(8), 1974–1988 (2014)CrossRefGoogle Scholar
  67. 67.
    Zheng, B., Su, H., Hua, W., Zheng, K., Zhou, X., Li, G.: Efficient clue-based route search on road networks. TKDE 29(9), 1846–1859 (2017)Google Scholar
  68. 68.
    Zheng, K., Zhao, Y., Lian, D., Zheng, B., Liu, G., Zhou, X.: Reference-based framework for spatio-temporal trajectory compression and query processing in TKDE (2019)Google Scholar
  69. 69.
    Zhou, X.: Destination-aware task assignment in spatial crowdsourcing: A worker decomposition approach. In: IEEE Trans. Knowl. Data Eng., (2019)
  70. 70.
    Zhu, D., Cui, P., Wang, D., Zhu, W: Deep variational network embedding in Wasserstein space. In: KDD (2018)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Yujun Chen
    • 1
  • Juhua Pu
    • 1
  • Xingwu Liu
    • 2
  • Xiangliang Zhang
    • 3
    Email author
  1. 1.Research Institute of Beihang University in ShenZhen, Beihang UniversityBeijingChina
  2. 2.Institute of Computating TechnologyChinese Academy of SciencesBeijingChina
  3. 3.King Abdullah University of Science and Technology (KAUST)ThuwalSaudi Arabia

Personalised recommendations