Abstract
Modern explanatory inductive logic programming methods like Progol, Residue procedure, CF-induction, HAIL and Imparo use the principle of inverse entailment (IE). Those IE-based methods commonly compute a hypothesis in two steps: by first constructing an intermediate theory and next by generalizing its negation into the hypothesis with the inverse of the entailment relation. Inverse entailment ensures the completeness of generalization. On the other hand, it imposes many non-deterministic generalization operators that cause the search space to be very large. For this reason, most of those methods use the inverse relation of subsumption, instead of entailment. However, it is not clear how this logical reduction affects the completeness of generalization. In this paper, we investigate whether or not inverse subsumption can be embedded in a complete induction procedure; and if it can, how it is to be realized. Our main result is a new form of inverse subsumption that ensures the completeness of generalization. Consequently, inverse entailment can be reduced to inverse subsumption without losing the completeness for finding hypotheses in explanatory induction.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Badea, L., & Stanciu, M. (1999). Refinement operators can be (weakly) perfect. In LNAI: Vol. 1634. Proceedings of the 9th international workshop on inductive logic programming (pp. 21–32). Berlin: Springer.
Bratko, I. (1999). Refining complete hypotheses in ILP. In LNAI: Vol. 1634. Proceedings of the 9th international workshop on inductive logic programming (pp. 44–55). Berlin: Springer.
Chang, C. L., & Lee, R. C. T. (1973). Symbolic logic and mechanical theorem proving. New York: Academic Press.
De Raedt, L. (1997). Logical setting for concept-learning. Artificial Intelligence, 95, 187–201.
Fredman, M., & Khanchiyan, L. (1996). On the complexity of dualization of monotone disjunctive normal forms. Journal of Algorithms, 28, 618–628.
Flach, P. A. (1996). Rationality postulates for induction. In Proceedings of the 6th international conference on theoretical aspects of rationality and knowledge (pp. 267–281).
Inoue, K. (2004). Induction as consequence finding. Machine Learning, 55(2), 109–135.
Kimber, T., Broda, K., & Russo, A. (2009). Induction on failure: learning connected Horn theories. In LNCS: Vol. 5753. Proceedings of the 10th international conference on logic programming and nonmonotonic reasoning (pp. 169–181). Berlin: Springer.
Lee, C. T. (1967). A completeness theorem and computer program for finding theorems. Ph.D. thesis, Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA.
Muggleton, S. H. (1995). Inverse entailment and Progol. New Generation Computing, 13, 245–286.
Muggleton, S. H., & Buntine, W. L. (1988). Machine invention of first-order predicates by inverting resolution. In Proceedings of the 5th international conference on machine learning (pp. 339–352).
Muggleton, S. H., & De Raedt, L. (1994). Inductive logic programming: theory and methods. The Journal of Logic Programming, 19/20, 629–679.
Nienhuys-Cheng, S., & De Wolf, R. (1997). LNCS: Vol. 1228. Foundations of inductive logic programming. Berlin: Springer.
Ray, O. (2009). Nonmonotonic abductive inductive learning. Journal of Applied Logic, 7(3), 329–340.
Ray, O., & Inoue, K. (2008). Mode directed inverse entailment for full clausal theories. In LNCS: Vol. 4894. Proceedings of the 17th international conference on inductive logic programming (pp. 225–238). Berlin: Springer.
Ray, O., Broda, K., & Russo, A. M. (2003). Hybrid abductive inductive learning. In LNCS: Vol. 2835. Proceedings of the 13th international conference on inductive logic programming (pp. 311–328). Berlin: Springer.
Riguzzi, F. (2005). Two results regarding refinement operators. In Late-breaking paper proceedings of the 15th international conference on inductive logic programming (pp. 53–58).
Satoh, K., & Uno, T. (2002). Enumerating maximal frequent sets using irredundant dualization. In LNCS: Vol. 2843. Proceedings of the 6th international conference on discovery science (pp. 256–268). Berlin: Springer.
Tamaddoni-Nezhad, A., & Muggleton, S. H. (2009). The lattice structure and refinement operators for the hypothesis space bounded by a bottom clause. Machine Learning, 76, 37–72.
Uno, T. (2002). A practical fast algorithm for enumerating minimal set coverings. IPSJ SIG Notes, 2002(29), 9–16.
Westergaard, S. L., Oliveira, A. P., Bro, C., Olsson, L., & Nielsen, J. (2006). A systems biology approach to study glucose repression in the yeast Saccharomyces cerevisiae. Biotechnology and Bioengineering, 96, 134–145.
Yamamoto, A. (2003). Hypothesis finding based on upward refinement of residue hypotheses. Theoretical Computer Science, 298, 5–19.
Yamamoto, Y., Ray, O., & Inoue, K. (2008). Towards a logical reconstruction of CF-induction. In LNCS: Vol. 4914. New frontiers in artificial intelligence (pp. 330–343). Berlin: Springer.
Yamamoto, Y., Inoue, K., & Iwanuma, K. (2009a). Hypothesis enumeration by CF-induction. In Proceedings of the 6th workshop on learning with logics and logics for learning (pp. 80–87).
Yamamoto, Y., Inoue, K., & Doncescu, A. (2009b). Integrating abduction and induction in biological inference using CF-induction. In H. Lodhi & S. Muggleton (Eds.), Elements of computational systems biology (pp. 213–234). Chap. 9.
Author information
Authors and Affiliations
Corresponding author
Additional information
Editors: Paolo Frasconi and Francesca Lisi.
Rights and permissions
About this article
Cite this article
Yamamoto, Y., Inoue, K. & Iwanuma, K. Inverse subsumption for complete explanatory induction. Mach Learn 86, 115–139 (2012). https://doi.org/10.1007/s10994-011-5250-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10994-011-5250-y