Abstract
We present in this paper the original notion of natural relation, a quasi order that extends the idea of generality order: it allows the sound and dynamic pruning of hypotheses that do not satisfy a property, be it completeness or correctness with respect to the training examples, or hypothesis language restriction.
Natural relations for conjunctions of such properties are characterized. Learning operators that satisfy these complex natural relations allow pruning with respect to this set of properties to take place before inappropriate hypotheses are generated.
Once the natural relation is defined that optimally prunes the search space with respect to a set of properties, we discuss the existence of ideal operators for the search space ordered by this natural relation. We have adapted the results from [vdLNC94a] on the non-existence of ideal operators to those complex natural relations. We prove those nonexistence conditions do not apply to some of those natural relations, thus overcoming the previous negative results about ideal operators for space ordered by θ-subsumption only.
Chapter PDF
References
W. Buntine. Generalized subsumption and its application to induction and redundancy. Artificial Intelligence, 36:375–399, 1988.
M. Champesme, P. Brézellec, and H. Soldano. Empirically conservative search space reductions. In L. De Raedt, editor, Proceedings of the 5th International Workshop on Inductive Logic Programming, pages 387–402. Department of Computer Science, Katholieke Universiteit Leuven, 1995.
S. Džeroski, S. Muggleton, and S. Russel. PAC-Learnability of Determinate Logic Programs. In Proceedings of 5th ACM Workshop on Computational Learning Theory, pages 128–135. ACM Press, 1992.
F. Esposito, A. Laterza, D. Malerba, and G. Semeraro. Refinement of datalog programs. In Proceedings of the MLnet Familiarization Workshop on Data Mining with Inductive Logic Programming (ILP for KDD), pages 73–94, July 1996.
Georg Gottlob. Subsumption and implication. Information Processing Letters, 24(2):109–111, January 1987.
P. Idestam-Almquist. Generalization of clauses under implication. Journal of Artificial Intelligence Research, 3:467–489, 1995.
J. W. Lloyd. Foundations of Logic Programming. Springer, Berlin, 2 edition, 1987.
S. Muggleton and C. Feng. Efficient induction of logic programs. In Proceedings of the 1st Conference on Algorithmic Learning Theory, pages 368–381. Ohmsma, Tokyo, Japan, 1990.
T. M. Mitchell. Generalization as search. Artificial Intelligence, 18:203–226, 1982.
S. Muggleton and L. De Raedt. Inductive logic programming: Theory and methods. Journal of Logic Programming, 19:629–679, 1994.
S.H. Nienhuys-Cheng and R. de Wolf. Least generalizations and greatest specializations of sets of clauses. Journal of Artificial Intelligence Research, 4:341–363, 1996.
T. Niblett. A note on refinement operators. In P. B. Brazdil, editor, Proceedings of the 6th European Conference on Machine Learning, volume 667 of Lecture Notes in Artificial Intelligence, pages 329–335. Springer-Verlag, April 1993.
NRA+96. C. Nédellec, C. Rouveirol, H. Adé, F. Bergadano, and B. Tausend. Declarative bias in ILP. In L. De Raedt, editor, Advances in Inductive Logic Programming, pages 82–103. IOS Press, 1996.
G. Plotkin. A note on inductive generalization. In Machine Intelligence, volume 5. Edinburgh University Press, 1970.
J. R. Quinlan. Learning logical definitions from relations. Machine Learning, 5(3):239–266, 1990.
E. Y. Shapiro. Inductive inference of theories from facts. Technical Report 192, Yale University Department of Computer Science, February 1981.
F. Torre and C. Rouveirol. Natural ideal operators in inductive logic programming. Technical report, Laboratoire de Recherche en Informatique, Université Paris Sud, 1997. To appear.
P.R.J. van der Laag. An Analysis of Refinement Operators in Inductive Logic Programming. PhD thesis, Erasmus Universiteit, Rotterdam, the Netherlands, 1995.
P.R.J van der Laag and S.H. Nienhuys-Cheng. Existence and nonexistence of complete refinement operators. In F. Bergadano and L. de Raedt, editors, Proceedings of the 7th European Conference on Machine Learning, volume 784 of Lecture Notes in Artificial Intelligence, pages 307–322. Springer-Verlag, April 1994.
P.R.J. van der Laag and S.H. Nienhuys-Cheng. A note on ideal refinement operators in ILP. In S. Wrobel, editor, Proceedings of the 4th International Workshop on Inductive Logic Programming, volume 237 of GMD-Studien, pages 247–262. Gesellschaft für Mathematik und Datenverarbeitung MBH, September 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Torre, F., Rouveirol, C. (1997). Natural ideal operators in Inductive Logic Programming. In: van Someren, M., Widmer, G. (eds) Machine Learning: ECML-97. ECML 1997. Lecture Notes in Computer Science, vol 1224. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62858-4_92
Download citation
DOI: https://doi.org/10.1007/3-540-62858-4_92
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62858-3
Online ISBN: 978-3-540-68708-5
eBook Packages: Springer Book Archive