Predicate Invention and the Revision of First-Order Concept Lattices

  • Michael Bain
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2961)

Abstract

In previous work it was shown that Formal Concept Analysis (FCA) can provide a useful framework for adjustment of representational bias for classifier learning and the construction of taxonomical hierarchies. This used techniques of predicate invention from Inductive Logic Programming (ILP) to introduce new attributes and re-formulate object descriptions. Such re-formulation of the descriptions of objects forces revision of the concept lattice. Hence a definition of revision operators based on ILP operators was introduced and shown to generate correct updates. However, in knowledge representation it is often the case that first-order or relational concepts are useful. Although there are previously published approaches to using first-order representations in FCA, in this paper we present an approach to constructing formal concepts using first-order logic intended to allow the application of methods developed in ILP. A lattice revision operator for relational concepts is then defined based on an ILP method for predicate invention.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bain, M.: Structured Features from Concept Lattices for Unsupervised Learning and Classification. In: McKay, B., Slaney, J.K. (eds.) Canadian AI 2002. LNCS (LNAI), vol. 2557, pp. 557–568. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  2. 2.
    Bain, M.: Learning Ontologies from Concept Lattices. In: Ganter, B., de Moor, A. (eds.) Using Conceptual Structures: Contributions to ICCS 2003, Aachen, Germany, pp. 199–212. Shaker Verlag, Aachen (2003)Google Scholar
  3. 3.
    Chaudron, L., Maille, N.: 1st Order Logic Formal Concept Analysis: from logic programming to theory. Linkoping Electronic Articles in Computer and Information Science 3(13) (1998)Google Scholar
  4. 4.
    Davey, B.A., Priestley, H.A.: An Introduction to Lattices and Order, 2nd edn. Cambridge University Press, Cambridge (2002)Google Scholar
  5. 5.
    Ferré, S., Ridoux, O.: A Logical Generalization of Formal Concept Analysis. In: Mineau, G., Ganter, B. (eds.) Proc. Eighth Intl. Conf. on Conceptual Structures, Springer, Berlin (2000)Google Scholar
  6. 6.
    Ganter, B., Kuznetsov, S.: Pattern Structures and their Projections. In: Delugach, H., Stumme, G. (eds.) ICCS 2001. LNCS (LNAI), vol. 2120, pp. 129–142. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  7. 7.
    Ganter, B., Wille, R.: Formal Concept Analysis: Mathematical Foundations. Springer, Berlin (1999)MATHGoogle Scholar
  8. 8.
    Kietz, J.-U., Lübbe, M.: n Efficient Subsumption Algorithm for Inductive Logic Programming. In: Wrobel, S. (ed.) Proc. Fourth Intl. Workshop on Inductive Logic Programming, pp. 97–106. Gesellschaft für Mathematik und Datenverarbeitung MBH (1994)Google Scholar
  9. 9.
    Lloyd, J.W.: Logic Programming, 2nd edn. Springer, Berlin (1987)MATHGoogle Scholar
  10. 10.
    Michie, D.: King and Rook Against King: Historical Background and a Problem on the Infinite Board. In: Clarke, M.R.B. (ed.) Advances in Computer Chess, vol. 1, pp. 30–59. Edinburgh University Press, Edinburgh (1977)Google Scholar
  11. 11.
    Muggleton, S.: Inverse Entailment and Progol. New Generation Computing 13, 245–286 (1995)CrossRefGoogle Scholar
  12. 12.
    Muggleton, S., Feng, C.: Efficient induction of logic programs. In: Muggleton, S. (ed.) Inductive Logic Programming, pp. 281–298. Academic Press, London (1992)Google Scholar
  13. 13.
    Plotkin, G.D.: Automatic Methods of Inductive Inference. PhD thesis, Edinburgh University (August 1971)Google Scholar
  14. 14.
    Sammut, C.: Prolog, Refinements and RLGG. In: Page, D. (ed.) ILP 1998. LNCS, vol. 1446, pp. 225–234. Springer, Heidelberg (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Michael Bain
    • 1
  1. 1.School of Computer Science and EngineeringUniversity of New South WalesSydneyAustralia

Personalised recommendations