Skip to main content
SpringerLink
Log in

Visualizing and understanding graph convolutional network

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The graph convolutional network (GCN), which can handle graph-structured data, is enjoying great interest in recent years. However, while GCN achieved remarkable results for different kinds of tasks, the source of its performance and the underlying decision process remain poorly understood. In this paper, we propose a visual analytics system that supports progressive analysis of GCN executing process and the effect of graph convolution operation. Multiple coordinated views are designed to show the influence of hidden layer parameters, the change of loss/accuracy and activation distributions, and the diffusion process of correctly predicted nodes. In particular, since the traditional t-SNE and force-directed layout methods are unable to show the graph-structured data well, we propose to utilize ‘graphTSNE’, a novel visualization technique for graph-structured data, to present the node layout in a clearer way. The real-world graph dataset is used to demonstrate the usability and effectiveness of our system through case studies. The results manifest that our system can provide sufficient guidance for understanding the working principle of graph convolutional network.

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
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Bruna J, Zaremba W, Szlam A, et al. (2014) Spectral networks and locally connected networks on graphs. In: Proceedings of International Conference on Learning Representations.

  2. Cui Z, Henrickson K, Ke R, et al. (2018) Traffic graph convolutional recurrent neural network: a deep learning framework for network-scale traffic learning and forecasting. arXiv preprint arXiv:1802.07007.

  3. Defferrard M, Bresson X, Vandergheynst P. (2016) Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems: 3844-3852.

  4. Glorot X, Bengio Y. (2010) Understanding the difficulty of training deep feedforward neural networks. In: proceedings of the thirteenth international conference on artificial intelligence and statistics: 249-256.

  5. Greydanus S, Koul A, Dodge J, et al. (2018) Visualizing and understanding atari agents. In: Proceedings of the 35th International Conference on Machine Learning: 1792--1801.

  6. Henaff M, Bruna J, LeCun Y. (2015) Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163.

  7. Hohman F, Kahng M, Pienta R et al (2018) Visual analytics in deep learning: an interrogative survey for the next frontiers. IEEE transactions on visualization and computer graphics 25(8):2674–2693

  8. Holten D, Van Wijk JJ (2009) Force-directed edge bundling for graph visualization. Computer graphics forum 28(3):983–990

    Article  Google Scholar 

  9. Karpathy A, Johnson J, Fei-Fei L. (2015) Visualizing and understanding recurrent networks. arXiv preprint arXiv:1506.02078.

  10. Kingma D P, Ba J. (2015) Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations.

  11. Kipf T N, Welling M. (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of the International Conference on Learning Representations.

  12. Leow Y Y, Laurent T, Bresson X. (2019) GraphTSNE: a visualization technique for graph-structured data. arXiv preprint arXiv:1904.06915.

  13. Li Y, Yu R, Shahabi C, et al. (2018) Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: Proceedings of the International Conference on Learning Representations.

  14. Liu M, Shi J, Li Z, Li C, Zhu J, Liu S (2016) Towards better analysis of deep convolutional neural networks. IEEE Trans Vis Comput Graph 23(1):91–100

    Article  Google Scholar 

  15. Liu M, Shi J, Cao K, Zhu J, Liu S (2017) Analyzing the training processes of deep generative models. IEEE Trans Vis Comput Graph 24(1):77–87

    Article  Google Scholar 

  16. Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(Nov):2579–2605

    MATH  Google Scholar 

  17. Monti F, Bronstein M, Bresson X. (2017) Geometric matrix completion with recurrent multi-graph neural networks. Adv Neural Inf Proces Syst: 3697–3707.

  18. Seo Y, Defferrard M, Vandergheynst P, et al. (2018) Structured sequence modeling with graph convolutional recurrent networks. International Conference on Neural Information Processing: 362-373.

  19. Strobelt H, Gehrmann S, Pfister H, Rush AM (2017) Lstmvis: a tool for visual analysis of hidden state dynamics in recurrent neural networks. IEEE Trans Vis Comput Graph 24(1):667–676

    Article  Google Scholar 

  20. Veličković P, Cucurull G, Casanova A et al (2018) Graph attention networks. In: Proceedings of the International Conference on Learning Representations.

  21. Wang J, Gou L, Yang H, Shen HW (2018) Ganviz: a visual analytics approach to understand the adversarial game. IEEE Trans Vis Comput Graph 24(6):1905–1917

    Article  Google Scholar 

  22. Wu Z, Pan S, Chen F, et al. (2019) A comprehensive survey on graph neural networks. arXiv preprint arXiv:1901.00596.

  23. Yi L, Su H, Guo X, et al. (2017) Syncspeccnn: synchronized spectral cnn for 3d shape segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition: 2282-2290.

  24. Ying R, He R, Chen K, et al. (2018) Graph convolutional networks for web-scale recommender systems. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining: 974-983.

  25. Yu B, Yin H, Zhu Z. (2018) Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence: 3634-3640.

  26. Zahavy T, Ben-Zrihem N, Mannor S. (2016) Graying the black box: understanding dqns. International Conference on Machine Learning: 1899-1908.

  27. Zeiler M D, Fergus R. (2014) Visualizing and understanding convolutional networks. European conference on computer vision: 818–833.

  28. Zhang Q, Zhu SC (2018) Visual interpretability for deep learning: a survey. Frontiers of Information Technology & Electronic Engineering 19(1):27–39

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported in part by the National Natural Science Foundation of China under Grants 61903109 and 61703127, and in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LY19F020047.

Author information

Authors and Affiliations

  1. Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China

    Xiaoying Shi, Fanshun Lv, Dewen Seng, Jiaming Zhang, Jing Chen & Baixi Xing

Authors
  1. Xiaoying Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fanshun Lv
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dewen Seng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jiaming Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jing Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Baixi Xing
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dewen Seng.

Additional information

Publisher’s note

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

Electronic supplementary material

ESM 1

(MP4 54,133 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shi, X., Lv, F., Seng, D. et al. Visualizing and understanding graph convolutional network. Multimed Tools Appl 80, 8355–8375 (2021). https://doi.org/10.1007/s11042-020-09885-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-09885-4

Keywords

Search

Navigation