Skip to main content
SpringerLink
Log in

Subgraph Mining for Graph Neural Networks

  • Conference paper
  • First Online:
Advances in Intelligent Data Analysis XXII (IDA 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14641))

Included in the following conference series:

  • 157 Accesses

Abstract

While Graph Neural Networks (GNNs) are state-of-the-art models for graph learning, they are only as expressive as the first-order Weisfeiler-Leman graph isomorphism test algorithm. To enhance their expressiveness one can incorporate complex structural information as attributes of the nodes in input graphs. However, this typically demands significant human effort and specialised domain knowledge. We demonstrate the feasibility of automatically extracting such information through subgraph mining and feature selection. Our experimental evaluation, conducted across graph classification tasks, reveals that GNNs extended with automatically selected features obtained using subgraph mining can achieve comparable or even superior performance to GNNs relying on manually crafted features.

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 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 64.99
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://github.com/ademkikaj/AutoGSN.

References

  1. Alsentzer, E., Finlayson, S., Li, M., Zitnik, M.: Subgraph neural networks. In: NeurIPS, vol. 33, pp. 8017–8029 (2020)

    Google Scholar 

  2. Bodnar, C., et al.: Weisfeiler and lehman go topological: message passing simplicial networks. In: ICML, pp. 1026–1037. PMLR (2021)

    Google Scholar 

  3. Bouritsas, G., Frasca, F., Zafeiriou, S., Bronstein, M.M.: Improving graph neural network expressivity via subgraph isomorphism counting. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 657–668 (2022)

    Article  Google Scholar 

  4. Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)

    Article  Google Scholar 

  5. Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016)

    Google Scholar 

  6. Cheng, H., Yan, X., Han, J.: Mining graph patterns. In: Frequent Pattern Mining, pp. 307–338 (2014)

    Google Scholar 

  7. Cordella, L.P., Foggia, P., Sansone, C., Vento, M.: A (sub) graph isomorphism algorithm for matching large graphs. IEEE Trans. Pattern Anal. Mach. Intell. 26(10), 1367–1372 (2004)

    Article  Google Scholar 

  8. Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: ICML, pp. 1263–1272. PMLR (2017)

    Google Scholar 

  9. Huang, N.T., Villar, S.: A short tutorial on the Weisfeiler-Lehman test and its variants. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8533–8537. IEEE (2021)

    Google Scholar 

  10. Jegelka, S.: Theory of graph neural networks: representation and learning. arXiv preprint arXiv:2204.07697 (2022)

  11. Jin, N., Young, C., Wang, W.: GAIA: graph classification using evolutionary computation. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data, pp. 879–890 (2010)

    Google Scholar 

  12. Ketkar, N.S., Holder, L.B., Cook, D.J.: Subdue: compression-based frequent pattern discovery in graph data. In: Proceedings of the 1st International Workshop on Open Source Data Mining: Frequent Pattern Mining Implementations, pp. 71–76 (2005)

    Google Scholar 

  13. Kraskov, A., Stögbauer, H., Grassberger, P.: Estimating mutual information. Phys. Rev. E 69(6), 066138 (2004)

    Article  MathSciNet  Google Scholar 

  14. Leman, A., Weisfeiler, B.: A reduction of a graph to a canonical form and an algebra arising during this reduction. Nauchno-Technicheskaya Informatsiya 2(9), 12–16 (1968)

    Google Scholar 

  15. Liu, H., Setiono, R.: Chi2: feature selection and discretization of numeric attributes. In: Proceedings of 7th IEEE ICTAI, pp. 388–391. IEEE (1995)

    Google Scholar 

  16. Maron, H., Ben-Hamu, H., Serviansky, H., Lipman, Y.: Provably powerful graph networks. In: NeurIPS, vol. 32 (2019)

    Google Scholar 

  17. McKay, B.: http://users.cecs.anu.edu.au/~bdm/data/graphs.html

  18. Meilicke, C., Chekol, M.W., Ruffinelli, D., Stuckenschmidt, H.: Anytime bottom-up rule learning for knowledge graph completion. In: IJCAI, pp. 3137–3143 (2019)

    Google Scholar 

  19. Morris, C., Kriege, N.M., Bause, F., Kersting, K., Mutzel, P., Neumann, M.: TUDataset: a collection of benchmark datasets for learning with graphs. arXiv preprint arXiv:2007.08663 (2020)

  20. 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 

  21. NetworkX. https://networkx.org/documentation/stable/reference/algorithms/isomorphism.vf2.html#subgraph-isomorphism

  22. Nijssen, S., Kok, J.N.: The Gaston tool for frequent subgraph mining. Electron. Notes Theor. Comput. Sci. 127(1), 77–87 (2005)

    Article  Google Scholar 

  23. Ribeiro, P., Paredes, P., Silva, M.E., Aparicio, D., Silva, F.: A survey on subgraph counting: concepts, algorithms, and applications to network motifs and graphlets. ACM Comput. Surv. (CSUR) 54(2), 1–36 (2021)

    Article  Google Scholar 

  24. Saigo, H., Nowozin, S., Kadowaki, T., Kudo, T., Tsuda, K.: gBoost: a mathematical programming approach to graph classification and regression. Mach. Learn. 75, 69–89 (2009)

    Article  Google Scholar 

  25. Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Networks 20(1), 61–80 (2008)

    Article  Google Scholar 

  26. Sun, Q., et al.: SUGAR: subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism. In: Proceedings of the Web Conference 2021, pp. 2081–2091 (2021)

    Google Scholar 

  27. Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018)

  28. Yan, X., Han, J.: gSpan: graph-based substructure pattern mining. In: 2002 IEEE International Conference on Data Mining, Proceedings, pp. 721–724. IEEE (2002)

    Google Scholar 

  29. Zeman, V., Kliegr, T., Svátek, V.: RDFRules: making RDF rule mining easier and even more efficient. Semant. Web 12(4), 569–602 (2021)

    Article  Google Scholar 

  30. Zhang, M., Li, P.: Nested graph neural networks. In: NeurIPS, vol. 34, pp. 15734–15747 (2021)

    Google Scholar 

  31. Zhao, L., Jin, W., Akoglu, L., Shah, N.: From stars to subgraphs: uplifting any GNN with local structure awareness. arXiv preprint arXiv:2110.03753 (2021)

Download references

Acknowledgments

This research received funding from the Flemish Government (AI Research Program) and the KU Leuven Research Fund (iBOF/21/075). GM has also received funding from KU Leuven Research Fund (STG/22/021).

Author information

Authors and Affiliations

  1. Department of Computer Science, KU Leuven, Leuven, Belgium

    Adem Kikaj, Giuseppe Marra & Luc De Raedt

  2. Leuven.AI - KU Leuven Institute for AI, Leuven, Belgium

    Adem Kikaj, Giuseppe Marra & Luc De Raedt

Authors
  1. Adem Kikaj
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Giuseppe Marra
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Luc De Raedt
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Adem Kikaj .

Editor information

Editors and Affiliations

  1. Stockholm University, Kista, Sweden

    Ioanna Miliou

  2. Fraunhofer IAIS, Sankt Augustin, Germany

    Nico Piatkowski

  3. Stockholm University, Kista, Sweden

    Panagiotis Papapetrou

Rights and permissions

Reprints and permissions

Copyright information

© 2024 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

Kikaj, A., Marra, G., De Raedt, L. (2024). Subgraph Mining for Graph Neural Networks. In: Miliou, I., Piatkowski, N., Papapetrou, P. (eds) Advances in Intelligent Data Analysis XXII. IDA 2024. Lecture Notes in Computer Science, vol 14641. Springer, Cham. https://doi.org/10.1007/978-3-031-58547-0_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-58547-0_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-58546-3

  • Online ISBN: 978-3-031-58547-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation