A framework for learning constraints: Preliminary report
Constraints represent a powerful way of specifying knowledge in any problem solving domain. Typically the appropriate constraints for a given problem need to be fully specified. In general it is difficult to describe the appropriate constraints in every problem setting. Hence automatic constraint acquisition is an important problem.
In this paper we develop a model for automatic constraint acquisition. We show that a universal scheme for generalizing constraints specified on variables across any domain, whether continuous or discrete, is not feasible. Here we provide a generalization model for constraints specified in the form of relations with explicit enumeration of allowed tuples. We provide a scheme to generalize the constraints expressed in this form in our model. We discuss the properties of the generalized constraint obtained from input constraints.
We also show that this scheme provides a uniform method of generalization for any type of constraint on variables with finite and discrete domain. In the end we elaborate upon the different applications of our scheme. We show how learning in our scheme can help improve the search efficiency in a CSP,
KeywordsConstraint Programming Learning
Unable to display preview. Download preview PDF.
- [Ellman, 1993]Ellman T., Abstraction via approximate symmetry. In Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, Chamberry, France, August 1993.Google Scholar
- [Freuder and Wallace 95]Freuder E.C. and Wallace R.J., “Generalizing inconsistency learning for constraint satisfaction”, Proceedings of IJCAI-95 the Fourteenth International Joint Conference on Artificial Intelligence, C. Mellish, ed., Morgan Kaufmann.Google Scholar
- [Han 95]Han J., “Mining Knowledge at Multiple Concept Levels”, Proc. 4th Int'l Conf. on Information and Knowledge Management (CIKM'95), Baltimore, Maryland, Nov. 1995, pp. 19–24.Google Scholar
- [Kawamura and Furukawa 93]Kawamura T. and Furukawa K., “Towards Inductive Generalization in Constraint Logic Programs”, Proceedings of the IJCAI-93 Workshop on Inductive Logic Programming, Chambery France(August 93), pp. 93–104.Google Scholar
- [Mackworth 92]Mackworth A., Constraint Satisfaction, in S.C.Shapiro,ed.,The Encyclopedia of AI,pp 285–293,Wiley, New York,1992.Google Scholar
- [Mizoguchi and Ohwada 92]Mizoguchi F. and Ohwada H., “Constraint-directed generalization for learning spatial relations”, Proceedings of the International Workshop on Inductive Logic Programming, ICOT TM-1182, Tokyo 1992.Google Scholar
- [Muggleton 92]Muggleton S., Inductive Logic Programming. Academic Press, 1992.Google Scholar
- [Page and Frisch 91]Page C.D., and Frisch A.M., “Generalizing atoms in constraint logic”, Proceedings of the Second International Conference on Knowledge Representation and Reasoning, pp 429–440, 1991.Google Scholar
- [Scheix et al 93]Scheix T. et al., “Nogood recording for static and dynamic CSP's”, Proc. of International Conference on Tools for AI, 1993.Google Scholar
- [Shavlik and Dietterich 90]Shavlik J.W., and Dietterich T.G. (eds.), Readings in machine learning. Morgan Kaufmann Publishers, 1990.Google Scholar
- [Wu 95]Wu Xindong, Knowledge Acquisition from Databases. Ablex Publishing Corporation, 1995.Google Scholar
- [Zweben et al. 1992]