PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Closed sets for labeled data
Gemma C. Garriga, Petra Kralj and Nada Lavrac
In: 10th European Conference on Principles and Practice of Knowledge Discovery in Databases, 18 - 22 Sep 2006, Berlin, Germany.


Closed sets are being successfully applied in the context of compacted data representation for association rule learning. However, their use is mainly descriptive. In this paper we will show that, when considering labeled data, closed sets can be adapted for predictive purposes by conveniently contrasting covering properties on positive and negative examples. We formally justify that these sets characterize the space of relevant combinations of features for discriminating the target class. In practice, identifying relevant/irrelevant combinations of features through closed sets is useful in many applications. Here we apply it to emerging patterns, subgroup discovery, and fast learning of relevant rules on datasets characterized by highly unbalanced distribution.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:2346
Deposited By:Petra Kralj
Deposited On:22 November 2006