Skip to main content
SpringerLink
Log in

An Image-Based Representation for Graph Classification

  • Conference paper
  • First Online:
Structural, Syntactic, and Statistical Pattern Recognition (S+SSPR 2018)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 11004))

  • 1205 Accesses

Abstract

This paper proposes to study the relevance of image representations to perform graph classification. To do so, the adjacency matrix of a given graph is reordered using several matrix reordering algorithms. The resulting matrix is then converted into an image thumbnail, that is used to represent the graph. Experimentation on several chemical graph data sets and an image data set show that the proposed graph representation performs as well as the state-of-the-art methods.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://brunl01.users.greyc.fr/CHEMISTRY/index.html.

  2. 2.

    http://rfai.li.univ-tours.fr/PublicData/gxlviewer/.

  3. 3.

    https://www.boost.org/doc/libs/1_58_0/libs/graph/doc/sparse_matrix_ordering.html.

  4. 4.

    https://CRAN.R-project.org/package=seriation.

  5. 5.

    http://yann.lecun.com/exdb/mnist/.

  6. 6.

    https://gdc2016.greyc.fr/.

References

  1. Abu-Aisheh, Z., et al.: Graph edit distance contest. Pattern Recogn. Lett. 100(C), 96–103 (2017)

    Article  Google Scholar 

  2. Barnes, J., Harary, F.: Graph theory in network analysis. Soc. Netw. 5(2), 235–244 (1983)

    Article  MathSciNet  Google Scholar 

  3. Behrisch, M., Bach, B., Riche, N.H., Schreck, T., Fekete, J.: Matrix reordering methods for table and network visualization. Comput. Graph. Forum 35(3), 693–716 (2016)

    Article  Google Scholar 

  4. Borgwardt, K.M., Kriegel, H.P.: Shortest-path kernels on graphs. In: Proceedings of the Fifth IEEE International Conference on Data Mining, pp. 74–81. IEEE Computer Society (2005)

    Google Scholar 

  5. Chacko, E., Ranganathan, S.: Graphs in Bioinformatics, pp. 191–219. Wiley, Hoboken (2010). Chap. 10

    Google Scholar 

  6. Cuthill, E., McKee, J.: Reducing the bandwidth of sparse symmetric matrices. In: Proceedings of the 1969 24th National Conference, pp. 157–172. ACM (1969)

    Google Scholar 

  7. Fruchterman, T.M.J., Reingold, E.M.: Graph drawing by force-directed placement. Softw. Pract. Exper. 21(11), 1129–1164 (1991)

    Article  Google Scholar 

  8. Gao, X., Xiao, B., Tao, D., Li, X.: A survey of graph edit distance. Pattern Anal. Appl. 13(1), 113–129 (2010)

    Article  MathSciNet  Google Scholar 

  9. Gaüzère, B., Brun, L., Villemin, D.: Graph kernel encoding substituents’ relative positioning. In: International Conference on Pattern Recognition (2014)

    Google Scholar 

  10. George, A., Liu, J.W.: The evolution of the minimum degree ordering algorithm. SIAM Rev. 31(1), 1–19 (1989)

    Article  MathSciNet  Google Scholar 

  11. George, J.A.: Computer implementation of the finite element method. Ph.D. thesis. Stanford, CA, USA (1971)

    Google Scholar 

  12. Ghoniem, M., Fekete, J.D., Castagliola, P.: On the readability of graphs using node-link and matrix-based representations: a controlled experiment and statistical analysis. Inf. Vis. 4(2), 114–135 (2005)

    Article  Google Scholar 

  13. Ghosh, S., Das, N., Gonçalves, T., Quaresma, P., Kundu, M.: The journey of graph kernels through two decades. Comput. Sci. Rev. 27, 88–111 (2018)

    Article  MathSciNet  Google Scholar 

  14. Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–864. ACM (2016)

    Google Scholar 

  15. Hofmann, T., Schölkopf, B., Smola, A.J.: Kernel methods in machine learning. Anna. Stat. 36(3), 1171–1220 (2008)

    Article  MathSciNet  Google Scholar 

  16. Ihm, P.: A contribution to the history of seriation in archaeology. In: Weihs, C., Gaul, W. (eds.) Classification - the Ubiquitous Challenge, pp. 307–316. Springer, Heidelberg (2005). https://doi.org/10.1007/3-540-28084-7_34

    Chapter  Google Scholar 

  17. Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)

  18. Luo, B., Wilson, R.C., Hancock, E.R.: Spectral embedding of graphs. Pattern Recogn. 36(10), 2213–2230 (2003)

    Article  Google Scholar 

  19. Mueller, C., Martin, B., Lumsdaine, A.: A comparison of vertex ordering algorithms for large graph visualization. In: 2007 6th International Asia-Pacific Symposium on Visualization, pp. 141–148 (2007)

    Google Scholar 

  20. Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. CoRR abs/1605.05273 (2016). http://arxiv.org/abs/1605.05273

  21. Rayar, F., Abu-Aisheh, Z.: Photo(Graph) Gallery: An “exhibition ” of graph classification. In: International Conference on Information Visualisation (2017)

    Google Scholar 

  22. Riesen, K., Bunke, H.: IAM graph database repository for graph based pattern recognition and machine learning. Pattern Recogn. Lett. 5342, 287–297 (2008)

    Google Scholar 

  23. Riesen, K., Bunke, H.: Graph Classification and Clustering Based on Vector Space Embedding. World Scientific Publishing Co., Inc., Singapore (2010)

    Book  Google Scholar 

  24. 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)

    Article  Google Scholar 

  25. Shervashidze, N., Vishwanathan, S., Petri, T., Mehlhorn, K., Borgwardt, K.: Efficient graphlet kernels for large graph comparison. In: International Conference on Artificial Intelligence and Statistics, vol. 5, pp. 488–495. PMLR (2009)

    Google Scholar 

  26. Sidere, N., Heroux, P., Ramel, J.Y.: A vectorial representation for the indexation of structural informations. In: da Vitoria Lobo, N., et al. (eds.) Structural, Syntactic, and Statistical Pattern Recognition, pp. 45–54. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-89689-0_9

    Chapter  Google Scholar 

  27. Sloan, S.W.: An algorithm for profile and wavefront reduction of sparse matrices. Int. J. Numer. Methods Eng. 23(2), 239–251 (1986)

    Article  MathSciNet  Google Scholar 

  28. Tixier, A.J., Nikolentzos, G., Meladianos, P., Vazirgiannis, M.: Classifying graphs as images with convolutional neural networks. CoRR abs/1708.02218 (2017). http://arxiv.org/abs/1708.02218

  29. Tsuda, K., Saigo, H.: Graph classification. In: Aggarwal, C., Wang, H. (eds.) Managing and Mining Graph Data, pp. 337–363. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  30. Vento, M.: A long trip in the charming world of graphs for pattern recognition. Pattern Recogn. 48(2), 291–301 (2015)

    Article  Google Scholar 

  31. Vishwanathan, S.V.N., Borgwardt, K.M., Schraudolph, N.N.: Fast computation of graph kernels. In: Proceedings of the 19th International Conference on Neural Information Processing Systems, pp. 1449–1456. MIT Press (2006)

    Google Scholar 

  32. Yanardag, P., Vishwanathan, S.V.N.: Deep graph kernels. In: KDD (2015)

    Google Scholar 

Download references

Acknowledgement

The authors would like to give credits to the organisers of the Graph Distance Contest, who provided the challenge data sets and the results of the second challenge. This research was partially supported by MEXT-Japan (Grant No. 17H06100).

Author information

Authors and Affiliations

  1. Kyushu University, Fukuoka, 819-0395, Japan

    Frédéric Rayar & Seiichi Uchida

Authors
  1. Frédéric Rayar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Seiichi Uchida
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Frédéric Rayar .

Editor information

Editors and Affiliations

  1. Beihang University, Beijing, China

    Xiao Bai

  2. University of York, York, United Kingdom

    Edwin R. Hancock

  3. IBM Research – Thomas J. Watson Research, Yorktown Heights, New York, USA

    Tin Kam Ho

  4. University of York, Heslington, York, United Kingdom

    Richard C. Wilson

  5. University of Cagliari, Cagliari, Italy

    Battista Biggio

  6. Data 61 - CSIRO, Canberra, Aust Capital Terr, Australia

    Antonio Robles-Kelly

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Rayar, F., Uchida, S. (2018). An Image-Based Representation for Graph Classification. In: Bai, X., Hancock, E., Ho, T., Wilson, R., Biggio, B., Robles-Kelly, A. (eds) Structural, Syntactic, and Statistical Pattern Recognition. S+SSPR 2018. Lecture Notes in Computer Science(), vol 11004. Springer, Cham. https://doi.org/10.1007/978-3-319-97785-0_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-97785-0_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-97784-3

  • Online ISBN: 978-3-319-97785-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation