Advertisement

Mining Tree Patterns with Partially Injective Homomorphisms

  • Till Hendrik SchulzEmail author
  • Tamás Horváth
  • Pascal Welke
  • Stefan Wrobel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11052)

Abstract

One of the main differences between inductive logic programming (ILP) and graph mining lies in the pattern matching operator applied: While it is mainly defined by relational homomorphism (i.e., subsumption) in ILP, subgraph isomorphism is the most common pattern matching operator in graph mining. Using the fact that subgraph isomorphisms are injective homomorphisms, we bridge the gap between ILP and graph mining by considering a natural transition from homomorphisms to subgraph isomorphisms that is defined by partially injective homomorphisms, i.e., which require injectivity only for subsets of the vertex pairs in the pattern. Utilizing positive complexity results on deciding homomorphisms from bounded tree-width graphs, we present an algorithm mining frequent trees from arbitrary graphs w.r.t. partially injective homomorphisms. Our experimental results show that the predictive performance of the patterns obtained is comparable to that of ordinary frequent subgraphs. Thus, by preserving much from the advantageous properties of homomorphisms and subgraph isomorphisms, our approach provides a trade-off between efficiency and predictive power.

References

  1. 1.
    Chandra, A.K., Merlin, P.M.: Optimal implementation of conjunctive queries in relational data bases. In: Proceedings of the 9th Annual ACM Symposium on Theory of Computing, (STOC), pp. 77–90. ACM Press (1977)Google Scholar
  2. 2.
    Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27 (2011)CrossRefGoogle Scholar
  3. 3.
    Dalmau, V., Kolaitis, P.G., Vardi, M.Y.: Constraint satisfaction, bounded treewidth, and finite-variable logics. In: Van Hentenryck, P. (ed.) CP 2002. LNCS, vol. 2470, pp. 310–326. Springer, Heidelberg (2002).  https://doi.org/10.1007/3-540-46135-3_21CrossRefGoogle Scholar
  4. 4.
    Deshpande, M., Kuramochi, M., Wale, N., Karypis, G.: Frequent substructure-based approaches for classifying chemical compounds. Trans. Knowl. Data Eng. 17(8), 1036–1050 (2005)CrossRefGoogle Scholar
  5. 5.
    Diestel, R.: Graph Theory. Springer, Berlin (2000)zbMATHGoogle Scholar
  6. 6.
    Gottlob, G., Leone, N., Scarcello, F.: Hypertree decompositions and tractable queries. J. Comput. Syst. Sci. 64(3), 579–627 (2002)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Horváth, T., Turán, G.: Learning logic programs with structured background knowledge. Artif. Intell. 128(1–2), 31–97 (2001)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Horváth, T., Ramon, J.: Efficient frequent connected subgraph mining in graphs of bounded tree-width. Theor. Comput. Sci. 411(31), 2784–2797 (2010)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Nienhuys-Cheng, S.-H., de Wolf, R.: Foundations of Inductive Logic Programming. LNCS, vol. 1228. Springer, Heidelberg (1997).  https://doi.org/10.1007/3-540-62927-0CrossRefzbMATHGoogle Scholar
  10. 10.
    Nijssen, S., Kok, J.N.: The Gaston tool for frequent subgraph mining. Electron. Notes Theor. Comput. Sci. 127(1), 77–87 (2005)CrossRefGoogle Scholar
  11. 11.
    Robertson, N., Seymour, P.D.: Graph minors. II. Algorithmic aspects of tree-width. J. Algorithms 7(3), 309–322 (1986)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Rose, D.J.: On simple characterizations of k-trees. Discret. Math. 7(3–4), 317–322 (1974)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Welke, P., Horváth, T., Wrobel, S.: Probabilistic frequent subtrees for efficient graph classification and retrieval. Mach. Learn. 107(11), 1847–1873 (2018)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Till Hendrik Schulz
    • 1
    Email author
  • Tamás Horváth
    • 1
    • 2
    • 3
  • Pascal Welke
    • 1
  • Stefan Wrobel
    • 1
    • 2
    • 3
  1. 1.Department of Computer ScienceUniversity of BonnBonnGermany
  2. 2.Fraunhofer IAIS, Schloss BirlinghovenSankt AugustinGermany
  3. 3.Fraunhofer Center for Machine LearningSankt AugustinGermany

Personalised recommendations