Abstract

. We investigate the use of oblivious, read-once decision graphs as structures for representing concepts over discrete domains, and present a bottom-up, hill-climbing algorithm for inferring these structures from labelled instances. The algorithm is robust with respect to irrelevant attributes, and experimental results show that it performs well on problems considered difficult for symbolic induction methods, such as the Monk's problems and parity. 1 Introduction Top down induction of decision trees [25, 24, 20] has been one of the principal induction methods for symbolic, supervised learning. The tree structure, which is used for representing the hypothesized target concept, suffers from some wellknown problems, most notably the replication problem and the fragmentation problem [23]. The replication problem forces duplication of subtrees in disjunctive concepts, such as (A B) (C D); the fragmentation problem causes partitioning of the data into fragments, when a high-arity attrib...

Citations

4071	C4.5: Programs for machine learning - Quinlan - 1993
2888	Induction of Decision Trees - Quinlan - 1986
2605	Graph-based algorithms for Boolean function manipulation - Bryant - 1986
792	Symbolic boolean manipulation with ordered binary decision diagrams - Bryant - 1992
515	K: Irrelevant features and the subset selection problem - GH, Kohavi, et al.
421	Efficient implementation of a BDD package - Brace, Rudell, et al. - 1990
335	On the Hardness of Approximating Minimization Problems - Lund, Yannakakis - 1994
319	Symbolic model checking: 10 states and beyond - Burch, Clarke, et al. - 1990
315	The Complexity of Boolean Functions - Wegener - 1987
312	Binary decision diagrams - Akers - 1978
190	Boolean feature discovery in empirical learning - Pagallo, Haussler - 1990
184	Bounded-width polynomial-size branching programs recognize exactly those languages in NC 1 - Barrington - 1989
164	The MONK's problem: A performance comparison of different learning algorithms - Thrun - 1991
115	The synthesis of two terminal switching circuits - Shannon - 1949
106	On variable ordering of binary decision diagrams for the application of multi-level logic synthesis - Fujita, Matsunaga, et al. - 1991
90	Supowit : Finding an optimal variable ordering for binary decision diagrams - Friedman, J - 1990
78	Representation of switching circuits by binary-decision programs - Lee - 1959
62	Representing circuits more efficiently in symbolic model checking, in “28th ACM/IEEE Design Automation Conference - BURCH, CLARKE, et al.
58	Decision Trees and Diagrams - Moret - 1982
31	Decision graphs - an extension of decision trees - Oliver - 1993
26	Variable Ordering Algorithms for Ordered Binary Decision Diagrams and Their Evaluation - Fujita, Fujisawa, et al. - 1993
26	An empirical comparison of genetic and decisiontree classifiers - Quinlan - 1988
16	A fast algorithm for the string editing problem and decision graph complexity - MASEK - 1976
16	Minimum-Width Method of Variable Ordering for Binary Decision Diagrams - Minato - 1992
16	Inferring decision graphs using the Minimum Message Length principle - Oliver, Dowe, et al. - 1992
7	Branching Programs - An Efficient Data Structure for ComputerAided Circuit Design - Meinel - 1991
7	Nagisa Ishiura, and Shuzo Yajima. Shared Binary Decision Diagrams with Attributed Edges for Efficient Boolean Function Manipulation - Minato - 1990
4	Yajima: Minimization of Binary Decision Diagrams Based on Exchanges of Variables - Ishiura, Sawada, et al. - 1991
3	An optimization technique for ordered (binary) decision diagrams - Dvorak - 1992
3	NP-completeness of minimum binary decision diagram identification - Takenaga, Yajima - 1993
2	An investigation of the laws of thought, on which are founded the theories of logic and probabilities - Boole - 1954
2	Boppana and Michael Sipser. The complexity of finite functions - Ravi - 1990