Learning relations: Basing top-down methods on inverse resolution

  • F. Bergadano
  • D. Gunetti
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 728)


Top-down algorithms for relational learning specialize general rules until they are consistent, and are guided by heuristics of different kinds. In general, a correct solution is not guaranteed. By contrast, bottom-up methods are well formalized, usually within the framework of inverse resolution. Inverse resolution has also been used as an efficient tool for deductive reasoning, and here we prove that input refutations can be translated into inverse unit refutations. This result allows us to show that top-down learning methods can be also described by means of inverse resolution, yielding a unified theory of relational learning.


Machine learning Automated reasoning Relational Learning 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    F. Bergadano. Inductive Database Relations. IEEE Trans. on Data and Knowledge Engineering, 5(4), 1993.Google Scholar
  2. [2]
    F. Bergadano and D. Gunetti. An interactive system to learn functional logic programs. In Proc. 13th Int. Joint. Conf. on Artificial Intelligence, Chambery, France, 1993. Morgan Kaufmann.Google Scholar
  3. [3]
    F. Bergadano and D. Gunetti. Unifying Top-Down and Inverse Resolution Approaches to Inductive Logic Programming. Tech. Rep. 93.3.28, CS Dept., Univ. of Torino, 1993.Google Scholar
  4. [4]
    D. Gunetti. Efficient proofs in propositional calculus with inverse resolution. In P. Dewilde and J. Vanderwalle, editors, Proc. of the CompEuro, 1992, The Hague, Netherlands, 1992. IEEE Comp. Soc. Press.Google Scholar
  5. [5]
    D. W. Loveland. Automated Theorem Proving: a Logical Basis. North Holland, 1978.Google Scholar
  6. [6]
    S. Muggleton. Machine Invention of First Order Predicates by Inverting Resolution. In Proc. of the Fifth Int. Conf on Machine Learning, pages 339–352, Ann Arbor, MI, 1988.Google Scholar
  7. [7]
    S. Muggleton. Inductive Logic Programming. New Generation Computing, 8(4):295–318, 1991.Google Scholar
  8. [8]
    G. Plotkin. A note on Inductive Generalization. In B. Meltzer and D. Michie, editors, Machine Intelligence 5, pages 153–163, 1970.Google Scholar
  9. [9]
    R. Quinlan. Learning Logical Definitions from Relations. Machine Learning, 5:239–266, 1990.Google Scholar
  10. [10]
    E. Y. Shapiro. Algorithmic Program Debugging. MIT Press, 1983.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • F. Bergadano
    • 1
  • D. Gunetti
    • 2
  1. 1.University of CataniaCataniaItaly
  2. 2.University of TorinoTorinoItaly

Personalised recommendations