Finding tree patterns consistent with positive and negative examples using queries
This paper is concerned with the problem of finding a hypothesis in TP2 consistent with given positive and negative examples. The hypothesis class TP2 consists of all the sets of at most two tree patterns and represents the class of unions of at most two tree pattern languages. Especially, we consider the problem from the point of view of the consistency problem for TP2. The consistency problem is a problem to decide whether there exists a consistent hypothesis with given positive and negative data within some fixed hypothesis space. Efficient solvability of that problem is closely related to the possibility of efficient machine learning or machine discovery. Unfortunately, however, the consistency problem is known to be NP-complete for many hypothesis spaces, including the class TP2. In order to overcome this computational hardness, in this paper, we try to use additional information obtained by making queries. First, we give an algorithm that, using restricted subset queries, solves the consistency problem for TP2 in time polynomial in the total size of given positive and negative examples. Next, we show that each subset query made by the algorithm can be replaced by several membership queries under some condition on a set of function symbols. As a result, we have that the consistency problem for TP2 is solved in polynomial time using membership queries.
Unable to display preview. Download preview PDF.
- 1.D. Angluin. Queries and concept learning. Machine Learning, 2(4):319–342, 1988.Google Scholar
- 2.H. Arimura, T. Shinohara, and S. Otsuki. A polynomial time algorithm for finding finite unions of tree pattern languages. In Proc. of the 2nd International Workshop on Nonmonotonic and Inductive Logics, 1991. LNAI 659.Google Scholar
- 3.H. Arimura, T. Shinohara, and S. Otsuki. Finding minimal generalizations for unions of pattern languages and its application to inductive inference from positive data. In P. Enjalbert, E. Mayr, and K. W. Wagner, editors, Proceedings of the 11th Annual Symposium on Theoretical Aspects of Computer Science, pp. 649–660. Springer-Verlag, 1994. LNCS 775.Google Scholar
- 4.J-L. Lassez, M. J. Maher, and K. Marriott. Unification revisited. In J. Minker, editor, Foundations of Deductive Databases and Logic Programming, pp. 587–625. Morgan Kaufmann, 1988.Google Scholar
- 5.S. Miyano, A. Shinohara, and T. Shinohara. Which classes of elementary formal systems are polynomial-time learnable? In S. Arikawa, A. Maruoka, and T. Sato, editors, Proc. ALT '91, pp. 139–150. JSAI, 1991.Google Scholar
- 6.Y. Mukouchi and S. Arikawa. Inductive inference machines that can refute hypothesis spaces. In K. P. Jantke, S. Kobayashi, E. Tomita, and T. Yokomori, editors, Proc. ALT '93, pp. 123–136. Springer-Verlag, 1993. LNAI 744.Google Scholar
- 7.B. K. Natarajan. Machine Learning, A Theoretical Approach. Morgan Kaufmann, 1991.Google Scholar
- 8.L. Pitt and L. G. Valiant. Computational limitations on learning from examples. JACM, 35(4):965–984, 1988.Google Scholar
- 9.G. D. Plotkin. A note on inductive generalization. In B. Meltzer and D. Michie, editors, Machine Intelligence 5, pp. 153–163. Edinburgh University Press, 1970.Google Scholar
- 10.J. C. Reynolds. Transformational systems and the algebraic structure of atomic formulas. In B. Meltzer and D. Michie, editors, Machine Intelligence 5, pp. 135–152. Edinburgh University Press, 1970.Google Scholar
- 11.L. G. Valiant. A theory of the learnable. Comm. ACM, 27:1134–1142, 1984.Google Scholar