Learning relations without closing the world

  • Edgar Sommer
Extended Abstracts
Part of the Lecture Notes in Computer Science book series (LNCS, volume 784)


This paper describes Link, a heuristically guided learner that combines aspects of three major approaches to ILP — LGG, search heuristic and (declarative) structural bias. In the manner of LGG algorithms, Link generates sets of candidate premise literals by collecting facts about the terms that appear in goal examples. It uses a linked-enough heuristic to select amongst these candidates to form hypothesis clauses (conjunctions of literals), and uses structural criteria to select among possible hypotheses in the manner of declarative bias-based systems. This combination — together with a parametrized hypothesis evaluation function — allows Link to learn in realistic situations where many FOL learners have problems because they are forced to make assumptions about the data: when there are no negative examples, when information is sparse, and when the closed-world assumption cannot or should not be made on examples and/or background.


  1. [deRaedt/Bruynooghe 93]
    Luc deRaedt and Maurice Bruynooghe. A Theory of Clausal Discovery. In S. Muggleton (ed.), Proc. 3rd Intl. Workshop on Inductive Logic Programming (ILP'93), pp. 25–40, 1993.Google Scholar
  2. [Kietz/Wrobel 92]
    Jörg-Uwe Kietz and Stefan Wrobel. Controlling the Complexity of Learning in Logic through Syntactic and Task-Oriented Models. In Stephen Muggleton (ed.), Inductive Logic Programming, chapter 16. Academic Press, London, New York, 1992.Google Scholar
  3. [Semeraro et al. 93]
    G. Semeraro, C. Brunk, and M. Pazzani. Traps and Pitfalls when Learning Logical Theories: A Case Study with FOIL and FOCL. Technical Report 93–33, University of California at Irvine, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Edgar Sommer
    • 1
  1. 1.GMD German National Research Center for Computer ScienceSchloss BirlinghovenSt. AugustinGermany

Personalised recommendations