Skip to main content
Springer Nature Link
Log in

Bridging Distinct Spaces in Graph-Based Machine Learning

  • Conference paper
  • First Online:
Pattern Recognition (ACPR 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14407))

Included in the following conference series:

Abstract

Graph-based machine learning, encompassing Graph Edit Distances (GEDs), Graph Kernels, and Graph Neural Networks (GNNs), offers extensive capabilities and exciting potential. While each model possesses unique strengths for graph challenges, interrelations between their underlying spaces remain under-explored. In this paper, we introduce a novel framework for bridging these distinct spaces via GED cost learning. A supervised metric learning approach serves as an instance of this framework, enabling space alignment through pairwise distances and the optimization of edit costs. Experiments reveal the framework’s potential for enhancing varied tasks, including regression, classification, and graph generation, heralding new possibilities in these fields.

Supported by Swiss National Science Foundation (SNSF) Project No. 200021_188496.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://github.com/jajupmochi/ged-cost-learn-framework/tree/master/.

  2. 2.

    We thank the COBRA lab (Chimie Organique Bioorganique : Réactivité et Analyse) and the ITODYS lab (Le laboratoire Interfaces Traitements Organisation et DYnamique des Systèmes) for providing this dataset.

References

  1. Trinajstic, N.: Chemical Graph Theory. Routledge, New York (2018)

    Google Scholar 

  2. Yi, H.C., You, Z.H., Huang, D.S., Kwoh, C.K.: Graph representation learning in bioinformatics: trends, methods and applications. Brief. Bioinform. 23(1), bbab340 (2022)

    Google Scholar 

  3. Tabassum, S., Pereira, F.S., Fernandes, S., Gama, J.: Social network analysis: an overview. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. 8(5), e1256 (2018)

    Article  Google Scholar 

  4. Jiao, L., et al.: Graph representation learning meets computer vision: a survey. IEEE Trans. Artif. Intell. 4(1), 2–22 (2022)

    Article  Google Scholar 

  5. Goyal, P., Ferrara, E.: Graph embedding techniques, applications, and performance: a survey. Knowl.-Based Syst. 151, 78–94 (2018)

    Article  Google Scholar 

  6. Kriege, N.M., Johansson, F.D., Morris, C.: A survey on graph kernels. Appl. Netw. Sci. 5(1), 1–42 (2020)

    Article  Google Scholar 

  7. Jia, L., Gaüzère, B., Honeine, P.: Graph kernels based on linear patterns: theoretical and experimental comparisons. Expert Syst. Appl. 189, 116095 (2022)

    Article  Google Scholar 

  8. Zhou, J., et al.: Graph neural networks: a review of methods and applications. AI Open 1, 57–81 (2020)

    Article  Google Scholar 

  9. Grattarola, D., Zambon, D., Livi, L., Alippi, C.: Change detection in graph streams by learning graph embeddings on constant-curvature manifolds. IEEE Trans. Neural Netw. Learn. Syst. 31(6), 1856–1869 (2019)

    Article  Google Scholar 

  10. Bunke, H., Allermann, G.: Inexact graph matching for structural pattern recognition. Pattern Recogn. Lett. 1(4), 245–253 (1983)

    Article  MATH  Google Scholar 

  11. Fuchs, M., Riesen, K.: A novel way to formalize stable graph cores by using matching-graphs. Pattern Recogn. 131, 108846 (2022)

    Article  Google Scholar 

  12. Neuhaus, Michel, Bunke, Horst: A random walk kernel derived from graph edit distance. In: Yeung, Dit-Yan., Kwok, James T.., Fred, Ana, Roli, Fabio, de Ridder, Dick (eds.) SSPR /SPR 2006. LNCS, vol. 4109, pp. 191–199. Springer, Heidelberg (2006). https://doi.org/10.1007/11815921_20

    Chapter  Google Scholar 

  13. Neuhaus, M., Bunke, H.: Bridging the Gap Between Graph Edit Distance and Kernel Machines, vol. 68. World Scientific, Singapore (2007)

    Google Scholar 

  14. Gaüzère, B., Brun, L., Villemin, D.: Graph kernels: crossing information from different patterns using graph edit distance. In: Gimel’farb, G., et al. (eds.) SSPR /SPR 2012. LNCS, vol. 7626, pp. 42–50. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-34166-3_5

    Chapter  Google Scholar 

  15. Jia, L., Gaüzère, B., Honeine, P.: A graph pre-image method based on graph edit distances. In: Proceedings of the IAPR Joint International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (S+SSPR), Venice, Italy, 21–22 January 2021

    Google Scholar 

  16. Riba, P., Fischer, A., Lladós, J., Fornés, A.: Learning graph edit distance by graph neural networks. Pattern Recogn. 120, 108132 (2021)

    Article  Google Scholar 

  17. Feng, A., You, C., Wang, S., Tassiulas, L.: KerGNNs: interpretable graph neural networks with graph kernels. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 6614–6622 (2022)

    Google Scholar 

  18. Du, S.S., Hou, K., Salakhutdinov, R.R., Poczos, B., Wang, R., Xu, K.: Graph neural tangent kernel: fusing graph neural networks with graph kernels. In: Advances in Neural Information Processing Systems, vol. 32 (2019)

    Google Scholar 

  19. Morris, C., et al.: Weisfeiler and leman go neural: higher-order graph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4602–4609 (2019)

    Google Scholar 

  20. Riesen, K., Bunke, H.: IAM graph database repository for graph based pattern recognition and machine learning. In: da Vitoria Lobo, N., et al. (eds.) SSPR /SPR 2008. LNCS, vol. 5342, pp. 287–297. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-89689-0_33

    Chapter  Google Scholar 

  21. Jia, L.: Bridging graph and kernel spaces: a pre-image perspective. Ph.D. thesis, Normandie (2021)

    Google Scholar 

  22. Neuhaus, M., Bunke, H.: A probabilistic approach to learning costs for graph edit distance. Proc. ICPR 3(C), 389–393 (2004)

    Google Scholar 

  23. Bellet, A., Habrard, A., Sebban, M.: Good edit similarity learning by loss minimization. Mach. Learn. 89(1–2), 5–35 (2012)

    Article  MathSciNet  MATH  Google Scholar 

  24. Cortés, X., Conte, D., Cardot, H.: Learning edit cost estimation models for graph edit distance. Pattern Recogn. Lett. 125, 256–263 (2019). https://doi.org/10.1016/j.patrec.2019.05.001

    Article  Google Scholar 

  25. Jia, L., Gaüzère, B., Yger, F., Honeine, P.: A metric learning approach to graph edit costs for regression. In: Torsello, A., Rossi, L., Pelillo, M., Biggio, B., Robles-Kelly, A. (eds.) S+SSPR 2021. LNCS, vol. 12644, pp. 238–247. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-73973-7_23

    Chapter  Google Scholar 

  26. Garcia-Hernandez, C., Fernández, A., Serratosa, F.: Learning the edit costs of graph edit distance applied to ligand-based virtual screening. Curr. Top. Med. Chem. 20(18), 1582–1592 (2020)

    Article  Google Scholar 

  27. Abu-Aisheh, Z., et al.: Graph edit distance contest: results and future challenges. Pattern Recogn. Lett. 100, 96–103 (2017)

    Article  Google Scholar 

  28. Riesen, K.: Structural Pattern Recognition with Graph Edit Distance. ACVPR, Springer, Cham (2015). https://doi.org/10.1007/978-3-319-27252-8

    Book  MATH  Google Scholar 

  29. Lawson, C.L., Hanson, R.J.: Solving Least Squares Problems. SIAM, Philadelphia (1995)

    Book  MATH  Google Scholar 

  30. Diamond, S., Boyd, S.: CVXPY: a python-embedded modeling language for convex optimization. J. Mach. Learn. Res. 17(1), 2909–2913 (2016)

    MathSciNet  MATH  Google Scholar 

  31. Virtanen, P., et al.: SciPy 10: fundamental algorithms for scientific computing in python. Nat. Methods 17(3), 261–272 (2020)

    Article  Google Scholar 

  32. Altman, N.S.: An introduction to kernel and nearest-neighbor nonparametric regression. Am. Stat. 46(3), 175–185 (1992)

    MathSciNet  Google Scholar 

  33. Boria, N., Bougleux, S., Gaüzère, B., Brun, L.: Generalized median graph via iterative alternate minimizations. In: Conte, D., Ramel, J.-Y., Foggia, P. (eds.) GbRPR 2019. LNCS, vol. 11510, pp. 99–109. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20081-7_10

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Computer Science, University of Bern, Bern, 3012, Switzerland

    Linlin Jia & Kaspar Riesen

  2. State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, 2 Sipailou, Nanjing, 210096, People’s Republic of China

    Xiao Ning

  3. The LITIS Lab, INSA Rouen Normandie, Rouen, France

    Benoit Gaüzère

  4. The LITIS Lab, Université de Rouen Normandie, Rouen, France

    Paul Honeine

Authors
  1. Linlin Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiao Ning
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Benoit Gaüzère
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Paul Honeine
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kaspar Riesen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Linlin Jia .

Editor information

Editors and Affiliations

  1. Kyushu Institute of Technology, Kitakyushu, Fukuoka, Japan

    Huimin Lu

  2. The University of Sydney, Sydney, NSW, Australia

    Michael Blumenstein

  3. Yonsei University, Seoul, Korea (Republic of)

    Sung-Bae Cho

  4. Chinese Academy of Sciences, Bejing, China

    Cheng-Lin Liu

  5. Osaka University, Osaka, Ibaraki, Japan

    Yasushi Yagi

  6. Kyushu Institute of Technology, Kitakyushu, Japan

    Tohru Kamiya

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Jia, L., Ning, X., Gaüzère, B., Honeine, P., Riesen, K. (2023). Bridging Distinct Spaces in Graph-Based Machine Learning. In: Lu, H., Blumenstein, M., Cho, SB., Liu, CL., Yagi, Y., Kamiya, T. (eds) Pattern Recognition. ACPR 2023. Lecture Notes in Computer Science, vol 14407. Springer, Cham. https://doi.org/10.1007/978-3-031-47637-2_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-47637-2_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-47636-5

  • Online ISBN: 978-3-031-47637-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics