Advertisement

Fine-Grained Semantics-Aware Heterogeneous Graph Neural Networks

Conference paper
  • 469 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12342)

Abstract

Designing a graph neural network for heterogeneous graph which contains different types of nodes and links have attracted increasing attention in recent years. Most existing methods leverage meta-paths to capture the rich semantics in heterogeneous graph. However, in some applications, meta-path fails to capture more subtle semantic differences among different pairs of nodes connected by the same meta-path. In this paper, we propose Fine-grained Semantics-aware Graph Neural Networks (FS-GNN) to learn the node representations by preserving both meta-path level and fine-grained semantics in heterogeneous graph. Specifically, we first use multi-layer graph convolutional networks to capture meta-path level semantics via convolution on edge type-specific weighted adjacent matrices. Then we use the learned meta-path level semantics-aware node representations as guidance to capture the fine-grained semantics via the coarse-to-fine grained attention mechanism. Experimental results semi-supervised node classification show that FS-GNN achieves state-of-the-art performance.

Keywords

Graph neural network Heterogeneous graph Fine-grained semantics Meta-path 

Notes

Acknowledgment

This work is supported by the National Key Research and Development Program of China (grant No. 2016YFB0801003) and the Strategic Priority Research Program of Chinese Academy of Sciences (grant No. XDC02040400).

References

  1. 1.
    Bangcharoensap, P., Murata, T., Kobayashi, H., Shimizu, N.: Transductive classification on heterogeneous information networks with edge betweenness-based normalization. In: WSDM, pp. 437–446 (2016)Google Scholar
  2. 2.
    Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and locally connected networks on graphs. In: ICLR (2013)Google Scholar
  3. 3.
    Dong, Y., Chawla, N.V., Swami, A.: metapath2vec: scalable representation learning for heterogeneous networks. In: KDD, pp. 135–144 (2017)Google Scholar
  4. 4.
    Fu, T.Y., Lee, W.C., Lei, Z.: HIN2Vec: explore meta-paths in heterogeneous information networks for representation learning. In: CIKM, pp. 1797–1806 (2017)Google Scholar
  5. 5.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feed for leveraging graph wavelet transform to address the short-comings of previous spectral graphrd neural networks. In: AISTATS, pp. 249–256 (2010)Google Scholar
  6. 6.
    Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS, pp. 1024–1034 (2017)Google Scholar
  7. 7.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  8. 8.
    Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)Google Scholar
  9. 9.
    Li, J., Dani, H., Hu, X., Tang, J., Chang, Y., Liu, H.: Attributed network embedding for learning in a dynamic environment. In: CIKM, pp. 387–396 (2017)Google Scholar
  10. 10.
    Li, R., Wang, S., Zhu, F., Huang, J.: Adaptive graph convolutional neural networks. In: AAAI (2018)Google Scholar
  11. 11.
    Liao, L., He, X., Zhang, H., Chua, T.S.: Attributed social network embedding. TKDE 30(12), 2257–2270 (2018)Google Scholar
  12. 12.
    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)Google Scholar
  13. 13.
    Perozzi, B., Al-Rfou, R., Skiena, S.: DeepWalk: online learning of social representations. In: KDD, pp. 701–710 (2014)Google Scholar
  14. 14.
    Schütt, K., Kindermans, P.J., Felix, H.E.S., Chmiela, S., Tkatchenko, A., Müller, K.R.: SchNet: a continuous-filter convolutional neural network for modeling quantum interactions. In: NIPS, pp. 991–1001 (2017)Google Scholar
  15. 15.
    Seongjun, Y., Jeong, M., Kim, R., Kang, J., Kim, H.: Graph transformer networks. In: NIPS, pp. 11960–11970 (2019)Google Scholar
  16. 16.
    Shi, C., et al.: Deep collaborative filtering with multi-aspect information in heterogeneous networks. TKDE (2019)Google Scholar
  17. 17.
    Shi, C., Hu, B., Zhao, W.X., Philip, S.Y.: Heterogeneous information network embedding for recommendation. TKDE 31(2), 357–370 (2018)Google Scholar
  18. 18.
    Shi, C., Li, Y., Zhang, J., Sun, Y., Philip, S.Y.: A survey of heterogeneous information network analysis. TKDE 29(1), 17–37 (2016)Google Scholar
  19. 19.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  20. 20.
    Sun, Y., Han, J., Yan, X., Yu, P.S., Wu, T.: PathSim: meta path-based top-k similarity search in heterogeneous information networks. VLDB 4(11), 992–1003 (2011)Google Scholar
  21. 21.
    Veličković P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)Google Scholar
  22. 22.
    Wang, D., Cui, P., Zhu, W.: Structural deep network embedding. In: KDD, pp. 1225–1234 (2016)Google Scholar
  23. 23.
    Wang, X., Cui, P., Wang, J., Pei, J., Zhu, W., Yang, S.: Community preserving network embedding. In: AAAI (2017)Google Scholar
  24. 24.
    Wang, X., et al.: Heterogeneous graph attention network. In: WWW, pp. 2022–2032 (2019)Google Scholar
  25. 25.
    Zhang, C., Swami, A., Chawla, N.V.: SHNE: representation learning for semantic-associated heterogeneous networks. In: WSDM, pp. 690–698 (2019)Google Scholar
  26. 26.
    Zhang, M., Cui, Z., Neumann, M., Chen, Y.: An end-to-end deep learning architecture for graph classification. In: AAAI (2018)Google Scholar
  27. 27.
    Zhang, Y., Xiong, Y., Kong, X., Li, S., Mi, J., Zhu, Y.: Deep collective classification in heterogeneous information networks. In: WWW, pp. 399–408 (2018)Google Scholar
  28. 28.
    Zhang, Y., Tang, J., Yang, Z., Pei, J., Yu, P.S.: COSNET: connecting heterogeneous social networks with local and global consistency. In: KDD, pp. 1485–1494 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Institute of Information Engineering, Chinese Academy of SciencesBeijingChina
  2. 2.School of Cyber SecurityUniversity of Chinese Academy of SciencesBeijingChina

Personalised recommendations