Abstract

We consider the problem of finding statistically unusual subgroups in a multi-relation database, and extend previous work on singlerelation subgroup discovery. We give a precise definition of the multirelation subgroup discovery task, propose a specific form of declarative bias based on foreign links as a means of specifying the hypothesis space, and show how propositional evaluation functions can be adapted to the multi-relation setting. We then describe an algorithm for this problem setting that uses optimistic estimate and minimal support pruning, an optimal refinement operator and sampling to ensure efficiency and can easily be parallelized.

Citations

1478	The probabilistic method - Spencer - 1992
784	Learning logical definitions from relations - Quinlan - 1989
560	Inverse entailment and progol - Muggleton - 1995
409	Fast discovery of association rules - Agrawal, Mannila, et al. - 1996
95	Controlling the complexity of learning in logic through syntactic and task-oriented models - Kietz, Wrobel - 1992
95	Random sampling from databases - Olken - 1993
85	Explora: A Multipattern and Multistrategy Discovery Assistant - Klösgen - 1996
63	First order jk-clausal theories are PAClearnable - Raedt, Dˇzeroski - 1994
51	The power of sampling in knowledge discovery - Kivinen, Mannila - 1994
31	An algorithm for finding all interesting sentences - Mannila, Toivonen - 1996
16	The ILP description learning problem: Towards a general model-level definition of data mining - Wrobel, Dˇzeroski - 1995
12	Parallel and Distributed Search for Structure in Multivariate Time Series - Oates, Schmill, et al.
1	This article was processed using the L a T E X macro package with LLNCS style - Dortmund