Propositionalisation and Aggregates

  • Arno J. Knobbe
  • Marc de Haas
  • Arno Siebes
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2168)


The fact that data is scattered over many tables causes many problems in the practice of data mining. To deal with this problem, one either constructs a single table by hand, or one uses a Multi-Relational Data Mining algorithm. In this paper, we propose a different approach in which the single table is constructed automatically using aggregate functions, which repeatedly summarise information from different tables over associations in the datamodel. Following the construction of the single table, we apply traditional data mining algorithms. Next to an in-depth discussion of our approach, the paper presents results of experiments on three well-known data sets.


Inductive Logic Programming Single Table Target Table Selection Graph Traditional Data Mining 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Alphonse, É., Rouveirol, C. Selective Propositionalization for Relational Learning, In Proceedings of PKDD’ 99, 1999Google Scholar
  2. 2.
    Dehaspe, L., Toivonen, H., Discovery of frequent Datalog patterns, Data Mining and Knowledge Discovery 3(1), 1999Google Scholar
  3. 3.
    Dietterich, T.G., Lathrop, R.H., Lozano-Pérez, T., Solving the multiple-instance problem with axis-parallel rectangles, Artificial Intelligence, 89(1–2):31–71, 1997zbMATHCrossRefGoogle Scholar
  4. 4.
    Džeroski, S., Blockeel, H., Kompare, B., Kramer, S., Pfahringer, B., Van Laer, W., Experiments in Predicting Biodegradability, In Proceedings of ILP’ 99, 1999Google Scholar
  5. 5.
    Friedman, N., Getoor, L., Koller, D., Pfeffer, A., Learning Probabilistic Relational Models, In Proceedings of IJCAI’ 99, 1999Google Scholar
  6. 6.
    Kramer, S., Relational Learning vs. Propositionalization, Ph.D thesis, 1999Google Scholar
  7. 7.
    Kramer, S., Pfahringer, B., Helma, C., Stochastic Propositionalization of non-determinate background knowledge, In Proceedings of ILP’ 98, 1998Google Scholar
  8. 8.
    Knobbe, A.J., Blockeel, H., Siebes, A., Van der Wallen, D.M.G. Multi-Relational Data Mining, In Proceedings of Benelearn’ 99, 1999Google Scholar
  9. 9.
    Knobbe, A.J., Siebes, A., Blockeel, H., Van der Wallen, D.M.G., Multi-Relational Data Mining, using UML for ILP, In Proceedings of PKDD 2000, 2000Google Scholar
  10. 10.
    Lavrač, N., Džeroski, S., Grobelnik, M., Learning nonrecursive definitions of relations with LINUS, In Proceedings of EWSL’91, 1991Google Scholar
  11. 11.
    Srinivasan, A., King, R.D., Feature construction with ILP: a study of quantitative predictions of biological activity by structural attributes, In Proceedings of ILP’ 96, 1996Google Scholar
  12. 12.
    Srinivasan, A., King, R.D., Bristol, D.W., An Assessment of ILP-Assisted Models for Toxicology and the PTE-3 Experiment, In Proceedings of ILP’ 99, 1999Google Scholar
  13. 13.
    Todorovski, L., Džeroski, S., Experiments in Meta-level Learning with ILP, In Proceedings of PKDD’ 99, 1999Google Scholar
  14. 14.
    Workshop notes on Discovery Challenge PKDD’ 99, 1999Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Arno J. Knobbe
    • 1
    • 2
  • Marc de Haas
    • 3
  • Arno Siebes
    • 2
  1. 1.KiminkiiDD HoutenThe Netherlands
  2. 2.Utrecht UniversityTB UtrechtThe Netherlands
  3. 3.Perot Systems Nederland B.V.GG AmersfoortThe Netherlands

Personalised recommendations