ILP-based concept discovery in multi-relational data mining Export

@article{citeulike:5493154, abstract = {Multi-relational data mining has become popular due to the limitations of propositional problem definition in structured domains and the tendency of storing data in relational databases. Several relational knowledge discovery systems have been developed employing various search strategies, heuristics, language pattern limitations and hypothesis evaluation criteria, in order to cope with intractably large search space and to be able to generate high-quality patterns. In this work, an ILP-based concept discovery method, namely Confidence-based Concept Discovery (C 2 D), is described in which strong declarative biases and user-defined specifications are relaxed. Moreover, this new method directly works on relational databases. In addition to this, a new confidence-based pruning is used in this technique. We also describe how to define and use aggregate predicates as background knowledge in the proposed method. In order to use aggregate predicates, we show how to handle numerical attributes by using comparison operators on them. Finally, we analyze the effect of incorporating unrelated facts for generating transitive rules on the proposed method. A set of experiments are conducted on real-world problems to test the performance of the proposed method.}, author = {Kavurucu, Y. and Senkul, P. and Toroslu, I. H.}, citeulike-article-id = {5493154}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.eswa.2009.02.100}, citeulike-linkout-1 = {http://linkinghub.elsevier.com/retrieve/pii/S0957417409002000}, doi = {10.1016/j.eswa.2009.02.100}, issn = {09574174}, journal = {Expert Systems with Applications}, month = {November}, number = {9}, pages = {11418--11428}, posted-at = {2009-11-03 16:17:58}, priority = {2}, title = {ILP-based concept discovery in multi-relational data mining}, url = {http://dx.doi.org/10.1016/j.eswa.2009.02.100}, volume = {36}, year = {2009} }

TY - JOUR ID - citeulike:5493154 L3 - citeulike-article-id:5493154 N2 - Multi-relational data mining has become popular due to the limitations of propositional problem definition in structured domains and the tendency of storing data in relational databases. Several relational knowledge discovery systems have been developed employing various search strategies, heuristics, language pattern limitations and hypothesis evaluation criteria, in order to cope with intractably large search space and to be able to generate high-quality patterns. In this work, an ILP-based concept discovery method, namely Confidence-based Concept Discovery (C 2 D), is described in which strong declarative biases and user-defined specifications are relaxed. Moreover, this new method directly works on relational databases. In addition to this, a new confidence-based pruning is used in this technique. We also describe how to define and use aggregate predicates as background knowledge in the proposed method. In order to use aggregate predicates, we show how to handle numerical attributes by using comparison operators on them. Finally, we analyze the effect of incorporating unrelated facts for generating transitive rules on the proposed method. A set of experiments are conducted on real-world problems to test the performance of the proposed method. IS - 9 JF - Expert Systems with Applications SN - 09574174 EP - 11428 TI - ILP-based concept discovery in multi-relational data mining VL - 36 SP - 11418 AU - Kavurucu, Y AU - Senkul, P AU - Toroslu, IH PY - 2009/11// UR - http://dx.doi.org/10.1016/j.eswa.2009.02.100 ER -