Abstract
Many top-down Inductive Logic Programming systems use a greedy, covering approach to construct hypotheses. This paper presents an alternative, cautious approach, known as cautious induction. We conjecture that cautious induction can allow better hypotheses to be found, with respect to some hypothesis quality criteria. This conjecture is supported by the presentation of an algorithm called OILS, and with a complexity analysis and empirical comparison of OILS with the Progol system. The results are encouraging and demonstrate the applicability of cautious induction to problems with noisy datasets, and to problems which require large, complex hypotheses to be learnt.
Preview
Unable to display preview. Download preview PDF.
References
S. Muggleton. Progol 4.1 distribution, release notes and example sets.
S. Muggleton. Inductive logic programming. New Generation Computing, 8:295–318,1991.
S. Muggleton. Inverse entailment and Progol. New Generation Computing, 13:245–286, 1995.
S. Muggleton and L. De Raedt. Inductive logic programming — theory and methods. Journal of Logic Programming, 19–20:629–679, 1994.
J. R. Quinlan. Learning logical definitions from relations. Machine Learning, 5:239–266, 1990.
A. Srinivasan. P-Progol 2.1 distribution, release notes and example sets.
A. Srinivasan, S. Muggleton, M. J. E. Sternberg, and R. D. King. Theories for mutagenicity: A study in first-order and feature-based induction. Technical Report PRG-TR-8-95, Oxford University Computing Laboratory, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Anthony, S., Frisch, A.M. (1997). Cautious induction in inductive logic programming. In: Lavrač, N., Džeroski, S. (eds) Inductive Logic Programming. ILP 1997. Lecture Notes in Computer Science, vol 1297. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3540635149_34
Download citation
DOI: https://doi.org/10.1007/3540635149_34
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63514-7
Online ISBN: 978-3-540-69587-5
eBook Packages: Springer Book Archive