Skip to main content
SpringerLink
Log in

Graph Neural Networks with Information Anchors for Node Representation Learning

  • Published:
Mobile Networks and Applications Aims and scope Submit manuscript

Abstract

In the era of big data, the large-scale information network applications need to process and analyze increasingly complex graph structure relationships. However, traditional methods of representing network structures are difficult to reflect potential relationships between massive nodes. Graph Neural Network (GNN) based node representation learning is an emerging learning paradigm that embeds network nodes into a low dimensional vector space by retaining as much the information of network topology and node content as possible. However, existing GNN approaches ignore the distinction among the positions of nodes with similar topologies, which is usually crucial for many network prediction and classification tasks. In this paper, we propose a novel Graph Neural Network model based on information anchors, called A-GNN, where these anchors are defined as the important nodes that have a lot of interactive information with other ordinary nodes. In our model, the vectors obtained by the node representation learning contain the location information of ordinary nodes related to anchors. In A-GNN, we first designed the selection strategy of the set of anchors. Then the distance computation process was defined for any given target node to each anchor. Finally, we proposed the learning schema of a non-linear distance-weighted aggregation over the anchors. Therefore A-GNN can obtain global position information of all ordinary nodes relative to the anchors. Our proposed A-GNN is suitable for various network prediction tasks such as link prediction and node classification. We have conducted comparative experiments on five datasets. Experimental results show that A-GNN outperforms current state-of-the-art models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Szklarczyk D, Morris JH, Cook H, Kuhn M, Wyder S, Simonovic M, Santos A, Doncheva NT, Roth A, Bork P, et al. (2016) The string database in 2017: quality-controlled protein–protein association networks, made broadly accessible. Nucleic acids research 45(1):362–368

    Google Scholar 

  2. Ying R, He R, Chen K, Eksombatchai P, Hamilton WL, Leskovec J (2018) Graph convolutional neural networks for web-scale recommender systems. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining ACM, pp 974–983

  3. Zitnik M, Leskovec J (2017) Predicting multicellular function through multi-layer tissue networks. Bioinformatics 33(14):190–198

    Article  Google Scholar 

  4. Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907

  5. Grover A, Leskovec J (2016) node2vec: Scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining ACM, pp 855–864

  6. Sun M, Tang J, Li H, Li B, Xiao C, Chen Y, Song D (2018) Data poisoning attack against unsupervised node embedding methods. arXiv:1810.12881

  7. Viviana AP, Cerquitelli T (2020) Modeling urban traffic data through graph-based neural networks Springer. In: INNS Big Data and Deep Learning conference, pp 216–225

  8. Changbo Z, Zhang Q, Gao Z, Niu Z, Zheng N, Wang L, Hua G (2020) Action co-localization in an untrimmed video by graph neural networks Springer. In: INNS Big Data and Deep Learning conference, pp 555–567

  9. Haddad PLDBM, Bothorel C (2020) Temporalnode2vec: Temporal node embedding in temporal networks Springer. In: International Conference on Complex Networks and Their Applications, pp 891–902

  10. Sun G, Zhang X (2019) A novel framework for node/edge attributed graph embedding Springer. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp 169–182

  11. Yang C, Liu Z, Zhao D, Sun M, Chang E (2015) Network representation learning with rich text information. In: Twenty-Fourth International Joint Conference on Artificial Intelligence

  12. Chen Y, Zou L, Qin Z (2019) Gated relational graph neural network for semi-supervised learning on knowledge graphs. In: International Conference on Web Information Systems Engineering Springer, pp 617–629

  13. Nasrullah Sheikh Z TK, Montresor A (2020) A simple approach to attributed graph embedding via enhanced autoencoder. In: International Conference on Complex Networks and Their Applications Springer, pp 797–809

  14. Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2008) The graph neural network model. IEEE Transactions on Neural Networks 20(1):61–80

    Article  Google Scholar 

  15. Xu N, Wang P, Chen L, Tao J, Zhao J (2019) Mr-gnn: Multi-resolution and dual graph neural network for predicting structured entity interactions. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19), pp 3968–3974

  16. Jaume G, Nguyen A-, Martínez MR, Thiran J-P, Gabrani M (2019) edgnn: a simple and powerful gnn for directed labeled graphs. arXiv:1904.08745

  17. Zheng Y, Jiang B, Shi J, Zhang H, Xie F (2019) Encoding histopathological wsis using gnn for scalable diagnostically relevant regions retrieval. In: International Conference on Medical Image Computing and Computer-Assisted Intervention Springer, pp 550–558

  18. You J, Ying R, Leskovec J (2019) Position-aware graph neural networks. In: International Conference on Machine Learning, pp 7134–7143

  19. Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. In: Sixth International Conference on Learning Representations (ICLR-18), pp 1–12

  20. Battaglia PW, Hamrick JB, Bapst V, Sanchez-Gonzalez A, Zambaldi V, Malinowski M, Tacchetti A, Raposo D, Santoro A, Faulkner R et al (2018) Relational inductive biases, deep learning, and graph networks. arXiv:1806.01261

  21. Li J-H, Wang C-D, Huang L, Huang D, Lai J-H, Chen P (2018) Attributed network embedding with micro-meso structure. In: International Conference on Database Systems for Advanced Applications Springer, pp 20–36

  22. Manessi F, Rozza A, Manzo M (2020) Dynamic graph convolutional networks. Pattern Recogn 97:107000

    Article  Google Scholar 

  23. Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, pp 1024–1034

  24. Zhang M, Chen Y (2018) Link prediction based on graph neural networks. In: Advances in Neural Information Processing Systems, pp 5165–5175

  25. Zheng C, Pan L, Wu P (2019) Multimodal deep network embedding with integrated structure and attribute information. IEEE Transactions on Neural Networks 31(5):1437–1449

    Article  Google Scholar 

  26. Liu XF, Tse CK (2015) A general framework for complex network applications. In: 2015 International Symposium on Nonlinear Theory and Its Applications (NOLTA2015), pp 2–5

  27. Ai X (2019) New metrics for node importance evaluation in occupational injury network. IEEE Access 7:61874–61882

    Article  Google Scholar 

  28. Qiong Q, Dongxia W (2016) Evaluation method for node importance in complex networks based on eccentricity of node. In: 2016 2nd IEEE International Conference on Computer and Communications (ICCC) IEEE , pp 2499–2502

  29. Zhao J, Liu X, Guo J (2018) Evaluation method for node importance of communication network based on complex network analysis. In: International Conference in Communications, Signal Processing, and Systems Springer, pp 342–349

  30. Liu F, Wang Z, Deng Y (2020) Gmm: A generalized mechanics model for identifying the importance of nodes in complex networks. Knowledge Based Systems 193:105464

    Article  Google Scholar 

  31. Moayedikia A (2018) Multi-objective community detection algorithm with node importance analysis in attributed networks. Appl Soft Comput 67:434–451

    Article  Google Scholar 

  32. Zhou J, Yu X, Lu J (2019) Node importance in controlled complex networks. IEEE Transactions on Circuits and Systems Ii-express Briefs 66(3):437–441

    Article  Google Scholar 

  33. Zhang Y, Xiong Y, Kong X, Li S, Mi J, Zhu Y (2018) Deep collective classification in heterogeneous information networks. In: Proceedings of the 2018 World Wide Web Conference International World Wide Web Conferences Steering Committee, pp 399–408

  34. Beck D, Haffari G, Cohn T (2018) Graph-to-sequence learning using gated graph neural networks. In: Annual Meeting of the Association for Computational Linguistics 2018 Association for Computational Linguistics (ACL), pp 273–283

  35. Xie Y, Xu H, Li J, Yang C, Gao K (2020) Heterogeneous graph neural networks for noisy few-shot relation classification. Knowledge Based Systems 194:105548

    Article  Google Scholar 

  36. Schlichtkrull M, Kipf TN, Bloem P, Van Den Berg R, Titov I, Welling M (2018) Modeling relational data with graph convolutional networks. In: European Semantic Web Conference Springer, pp 593–607

  37. Duvenaud DK, Maclaurin D, Iparraguirre J, Bombarell R, Hirzel T, Aspuru-Guzik A, Adams RP (2015) Convolutional networks on graphs for learning molecular fingerprints. In: Advances in neural information processing systems, pp 2224–2232

  38. Leskovec J, Kleinberg J, Faloutsos C (2007) Graph evolution: Densification and shrinking diameters. ACM Transactions on Knowledge Discovery from Data (TKDD) 1(1):2

    Article  Google Scholar 

  39. Borgwardt KM, Ong CS, Schönauer S, Vishwanathan SVN, Smola AJ, Kriegel H-P (2005) Protein function prediction via graph kernels. Bioinformatics 21:47–56

    Article  Google Scholar 

  40. Watts DJ (1999) Networks, dynamics, and the small-world phenomenon. American Journal of sociology 105(2):493–527

    Article  Google Scholar 

  41. Xu K, Hu W, Leskovec J, Jegelka S (2019) How powerful are graph neural networks?. In: International Conference on Learning Representations, pp 1–17

Download references

Acknowledgments

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).

Author information

Authors and Affiliations

  1. School of Computer Science, China University of Geosciences, Wuhan, 430074, China

    Chao Liu, Xinchuan Li, Dongyang Zhao, Xiaojun Kang, Lijun Dong & Hong Yao

  2. Hubei Key Laboratory of Intelligent Geo Information Processing, China University of Geosciences, Wuhan, 430074, China

    Chao Liu, Xinchuan Li, Dongyang Zhao, Xiaojun Kang, Lijun Dong & Hong Yao

  3. College of Marine Science and Technology, China University of Geosciences, Wuhan, 430074, China

    Chao Liu

  4. Sinopec Exploration Company, Chengdu, 610041, Sichuan, China

    Shaolong Guo

Authors
  1. Chao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xinchuan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dongyang Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shaolong Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiaojun Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Lijun Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Hong Yao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaojun Kang.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

An earlier version of this paper was presented at the 15th EAI International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness (Qshine 2019), DOI:10.1007/978-3-030-38819-5_9

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, C., Li, X., Zhao, D. et al. Graph Neural Networks with Information Anchors for Node Representation Learning. Mobile Netw Appl 27, 315–328 (2022). https://doi.org/10.1007/s11036-020-01633-0

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11036-020-01633-0

Keywords

Search

Navigation