Abstract
As a form of knowledge acquisition from data, we consider the problem of computing “monotone” extensions of a pair of data sets (T, F), where T (resp., F) ⊑ {0, 1}n is a set of positive (resp., negative) examples, and an extension is a Boolean function that is consistent with (T, F). A motivation of this study comes from an observation that real world data are often monotone (or at least approximately monotone), and in such cases it is natural to build monotone extensions. We define five types of monotone extensions called error-free, best-fit, consistent, robust and most-robust extensions to deal with various cases, in which (T, F) may contain errors and/or incomplete data. We provide polynomial time algorithms for constructing error-free, best-fit, consistent and robust extensions. For most-robust extensions, we show that the problem is solvable in polynomial time if AS(a) ≤ 1 holds for all a ∈ T∪F, where AS(a) denotes the set of missing bits in a vector a, but is NP-hard even if AS(a) < 2 holds for all a ∈ T∪F. We also give an approximability result for computing a most-robust extension.
Preview
Unable to display preview. Download preview PDF.
References
M. Anthony and N. Biggs, Computational Learning Theory, Cambridge University Press, 1992.
A. Ben-David, Monotonicity maintenance in information-theoretic machine learning algorithms, Machine Learning 19 (1995) 29–43.
A. Ben-David, L. Sterling and Y. H. Pao, Learning and classification of monotonic ordinal concepts, Computational Intelligence 5 (1989) 45–49.
E. Boros, V. Gurvich, P. L. Hammer, T. Ibaraki and A. Kogan, Decomposability of partially defined Boolean functions, Discrete Applied Mathematics, 62 (1995) 51–75.
E. Boros, P. L. Hammer, T. Ibaraki, A. Kogan, E. Mayoraz and I. Muchnik, An implementation of logical analysis of data, RUTCOR Research Report RRR 22-96, Rutgers University, 1996.
E. Boros, T. Ibaraki and K. Makino, Error-free and best-fit extensions of a partially defined Boolean function, RUTCOR Research Report RRR 14-95, Rutgers University, 1995.
E. Boros, T. Ibaraki and K. Makino, Extensions of partially defined Boolean functions with missing data, RUTCOR Research Report RRR 06-96, Rutgers University (1996).
E. Boros, T. Ibaraki and K. Makino, Boolean analysis of incomplete examples, SWAT '96 Algorithm Theory, edited by R. Karlsson and A. Lingas, Springer Lecture Notes in Computer Science 1097 (1996) 440–451.
Y. Crama, P. L. Hammer and T. Ibaraki, Cause-effect relationships and partially defined boolean functions, Annals of Operations Research, 16 (1988) 299–326.
U. M. Fayyad, G. Piatetsky-Shapiro, P. Smyth and R. Uthurusamy, Advances in Knowledge Discovery and Data Mining, AAAI Press, 1996.
D. Kavvadias, C. H. Papadimitriou and M. Sideri, On Horn envelopes and hypergraph transversals, ISAAC'93 Algorithms and Computation, edited by K. W. Ng et al., Springer Lecture Notes in Computer Science 762 (1993) 399–405.
M. Kearns, M. Li and L. Valiant, Learning Boolean formulas, Journal of ACM, 41 (1994) 1298–1328.
H. W. Kuhn, The Hungarian method for solving the assignment problem, Naval Res. Logist. Quart., 2 (1955) 83–97.
H. W. Kuhn, Variants of the Hungarian method for solving the assignment problem, Naval Res. Logist. Quart., 3 (1956) 253–258.
K. Makino, K. Hatanaka and T. Ibaraki, Horn extensions of a partially defined Boolean function, RUTCOR Research Report RRR 27-95, Rutgers University, 1995.
K. Makino, K. Yano and T. Ibaraki, Positive and Horn decomposability of partially defined Boolean functions, Discrete Applied Mathematics, 74 (1997) 251–274.
J. R. Quinlan, Induction of decision trees, Machine Learning 1 (1986) 81–106.
L. G. Valiant, A theory of the learnable, Communications of the ACM 27 (1984) 1134–1142. *** DIRECT SUPPORT *** A0008157 00004
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Borosl, E., Ibaraki, T., Makino, K. (1997). Monotone extensions of boolean data sets. In: Li, M., Maruoka, A. (eds) Algorithmic Learning Theory. ALT 1997. Lecture Notes in Computer Science, vol 1316. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63577-7_42
Download citation
DOI: https://doi.org/10.1007/3-540-63577-7_42
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63577-2
Online ISBN: 978-3-540-69602-5
eBook Packages: Springer Book Archive