The appropriateness of predicate invention as bias shift operation in ILP

The task of predicate invention in Inductive Logic Programming is to extend the hypothesis language with new predicates if the vocabulary given initially is insufficient for the learning task. However, whether predicate invention really helps to make learning succeed in the extended language depends on the language bias currently employed.In this paper, we investigate for which commonly employed language biases predicate invention is an appropriate shift operation. We prove that for some restricted languages predicate invention does not help when the learning task fails and we characterize the languages for which predicate invention is useful. We investigate the decidability of the bias shift problem for these languages and discuss the capabilities of predicate invention as a bias shift operation.

[1]  Rüdiger Wirth,et al.  Two Methods for Improving Inductive Logic Programming Systems , 1993, ECML.

[2]  Jack Mostow,et al.  Learning Logical Definitions from Relations , 1990 .

[3]  Stan Matwin,et al.  Constructive Inductive Logic Programming , 1993, IJCAI.

[4]  Stephen Muggleton,et al.  Efficient Induction of Logic Programs , 1990, ALT.

[5]  Stephen Muggleton.  Inductive Logic Programming: Derivations, Successes and Shortcomings , 1993, ECML.

[6]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

[7]  Peter A. Flach.  Predicate Invention in Inductive Data Engineering , 1993, ECML.

[8]  Maurice Bruynooghe,et al.  Interactive Concept-Learning and Constructive Induction by Analogy , 1992, Machine Learning.

[9]  Saso Dzeroski,et al.  PAC-learnability of determinate logic programs , 1992, COLT '92.

[10]  Luc De Raedt,et al.  Acquiring Object-Knowledge for Learning Systems , 1991, EWSL.

[11]  Stefan Wrobel,et al.  Concept Formation During Interactive Theory Revision , 1994, Machine Learning.

[12]  Katharina Morik,et al.  A Polynomial Approach to the Constructive Induction of Structural Knowledge , 2004, Machine Learning.

[13]  Stephen Muggleton,et al.  A Strategy for Constructing New Predicates in First-Order Logic , 1988, EWSL.

[14]  Ehud Shapiro,et al.  A Type System for Logic Programs , 1988, J. Log. Program..

[15]  Ashwin Srinivasan,et al.  Distinguishing Exceptions From Noise in Non-Monotonic Learning , 1992 .

[16]  S. C. Kleene,et al.  Finite Axiomatizability of Theories in the Predicate Calculus Using Additional Predicate Symbols , 1952 .

[17]  William W. Cohen.  Pac-Learning a Restricted Class of Recursive Logic Programs , 1993, AAAI.

[18]  Stephen Muggleton,et al.  Machine Invention of First Order Predicates by Inverting Resolution , 1988, ML.

[19]  Luc De Raedt,et al.  Inductive Logic Programming: Theory and Methods , 1994, J. Log. Program..

[20]  J. R. Quinlan.  Learning Logical Definitions from Relations , 1990 .

[21]  L. D. Raedt.  Interactive theory revision: an inductive logic programming approach , 1992 .

[22]  Jorg-uwe Kietz,et al.  Controlling the Complexity of Learning in Logic through Syntactic and Task-Oriented Models , 1992 .

[23]  Luc De Raedt,et al.  Towards Friendly Concept-Learners , 1989, IJCAI.

[24]  Rüdiger Wirth,et al.  Constraints on Predicate Invention , 1991, ML.