Advertisement

A-GNN: Anchors-Aware Graph Neural Networks for Node Embedding

  • Chao Liu
  • Xinchuan Li
  • Dongyang Zhao
  • Shaolong Guo
  • Xiaojun KangEmail author
  • Lijun Dong
  • Hong Yao
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 300)

Abstract

With the rapid development of information technology, it has become increasingly popular to handle and analyze complex relationships of various information network applications, such as social networks and biological networks. An unsolved primary challenge is to find a way to represent the network structure to efficiently compute, process and analyze network tasks. Graph Neural Network (GNN) based node representation learning is an emerging learning paradigm that embeds network nodes into a low dimensional vector space through preserving the network topology as possible. However, existing GNN architectures have limitation in distinguishing the position of nodes with the similar topology, which is crucial for many network prediction and classification tasks. Anchors are defined as special nodes which are in the important positions, and carries a lot of interactive information with other normal nodes. In this paper, we propose Anchors-aware Graph Neural Networks (A-GNN), which can make the vectors of node embedding contain location information by introducing anchors. A-GNN first selects the set of anchors, computes the distance of any given target node to each anchor, and afterwards learns a non-linear distance-weighted aggregation scheme over the anchors. Therefore A-GNN can obtain global position information of nodes regarding the anchors. A-GNN are applied to multiple prediction tasks including link prediction and node classification. Experimental results show that our model is superior to other GNN architectures on six datasets, in terms of the ROC, AUC accuracy score.

Keywords

Graph Neural Network Node embedding Link prediction Node classification Global structure information 

Notes

Acknowledgements

This work was supported in part by the National Key R&D Program of China (Grant No. 2018YFB1004600), the National Science and Technology Major Project of China (Grant No. 2017ZX05036-001) and the National Natural Science Foundation of China (NSFC) (Grant No. 61972365, 61772480, 61672474, 61673354, 61501412).

References

  1. 1.
    Damian, S., John, H., Helen, C.: quality-controlled protein–protein association networks, made broadly accessible. Nucleic Acid Res., 937 (2016)Google Scholar
  2. 2.
    Ying, R., He, R., Chen, K.: Graph convolutional neural networks for web-scale recommender systems. In: 2018 International Proceedings on ACM SIGKDD Knowledge Discovery and Data Mining, pp. 1576–1585 (2018)Google Scholar
  3. 3.
    Zitnik, M., Leskovec, J.: Predicting multicellular function through multi-layer tissue networks. Bioinformatics 33(14), i190–i198 (2017)CrossRefGoogle Scholar
  4. 4.
    Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 2017 International Proceedings on Learning Representation (2017)Google Scholar
  5. 5.
    Grover, A., Leskovec, J.: node2vec: Scalable feature learning for networks. In: 22th International Proceedings on ACM SIGKDD, pp. 855–864 (2016)Google Scholar
  6. 6.
    Sun, G., Zhang, X.: A novel framework for node/edge attributed graph embedding. In: Yang, Q., Zhou, Z.-H., Gong, Z., Zhang, M.-L., Huang, S.-J. (eds.) PAKDD 2019. LNCS (LNAI), vol. 11441, pp. 169–182. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-16142-2_14CrossRefGoogle Scholar
  7. 7.
    Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61–80 (2009)CrossRefGoogle Scholar
  8. 8.
    Sun, M., Tang, J., Li, H.: Data poisoning attack against unsupervised node embedding methods. arXiv preprint arXiv:1810.12881 (2018)
  9. 9.
    Grover, A., Leskovec, J.: node2vec: scalable feature learning for networks. In: 22nd International Proceedings on ACM SIGKDD Knowledge Discovery and Data Mining, pp. 855–864 (2016)Google Scholar
  10. 10.
    Cheng, Y., Zhi, L., Deli, Z.: Network representation learning with rich text information. In: 2015 International Proceedings on IJCAI (2015)Google Scholar
  11. 11.
    Jiaxuan, Y., Rex, Y., Jure, L.: Position-aware graph neural networks. In: 36th International Proceedings on International Conference on Machine Learning (2019)Google Scholar
  12. 12.
    Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 2017 International Proceedings on International Conference Learning Representations, pp. 1–14 (2017)Google Scholar
  13. 13.
    Velickovic, P., Cucurull, G., Casanova, A.: Graph attention networks (2018)Google Scholar
  14. 14.
    Battaglia, P.W., Hamrick, J.B., Bapst, V.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)
  15. 15.
    Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, pp. 1024–1034 (2017)Google Scholar
  16. 16.
    Zhang, M., Chen, Y.: Link prediction based on graph neural networks. Advances in Neural Information Processing Systems (2018)Google Scholar
  17. 17.
    Qin, Q., Wang, D.: Evaluation method for node importance in complex networks based on eccentricity of node. In: Advances in Neural Information Processing Systems, pp. 1324–1334 (2019)Google Scholar
  18. 18.
    Watts, D.J.: Networks, dynamics, and the small-world phenomenon. Am. J. Sociol. 105(2), 493–527 (1999)CrossRefGoogle Scholar
  19. 19.
    Leskovec, J., Kleinberg, J., Faloutsos, C.: Graph evolution: densification and shrinking diameters. ACM Trans. Knowl. Discov. Data (TKDD) 1(1), 2 (2007)CrossRefGoogle Scholar
  20. 20.
    Borgwardt, K.M., Ong, C.S., Schonauer, S.: Protein function prediction via graph kernels. Bioinformatics 21(suppl 1), i47–i56 (2005)CrossRefGoogle Scholar
  21. 21.
    Xiqing, S., Shoukui, S.: Complex Network Algorithms and Applications, 2nd edn. National Defense Industry Press (2016)Google Scholar
  22. 22.
    Xinbo, A.: New metrics for node importance evaluation in occupational injury network. IEEE Access 7, 61874–61882 (2019)CrossRefGoogle Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2020

Authors and Affiliations

  1. 1.School of Computer ScienceChina University of GeosciencesWuhanChina
  2. 2.Hubei Key Laboratory of Intelligent Geo-Information ProcessingChina University of GeosciencesWuhanChina
  3. 3.Sinopec Exploration CompanyChengduChina

Personalised recommendations