Using Highly Expressive Contrast Patterns for Classification - Is It Worthwhile?

Authors:
Elsa Loekito;James Bailey
Affiliations:
NICTA Victoria Laboratory Department of Computer Science and Software Engineering, University of Melbourne, Australia;NICTA Victoria Laboratory Department of Computer Science and Software Engineering, University of Melbourne, Australia
Venue:
PAKDD '09 Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Year:
2009

Citing 9
Cited 2

Mining quantitative association rules in large relational tables

SIGMOD '96 Proceedings of the 1996 ACM SIGMOD international conference on Management of data
Efficient mining of emerging patterns: discovering trends and differences

KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
Mining generalised disjunctive association rules

Proceedings of the tenth international conference on Information and knowledge management
Making use of the most expressive jumping emerging patterns for classification

Knowledge and Information Systems
CAEP: Classification by Aggregating Emerging Patterns

DS '99 Proceedings of the Second International Conference on Discovery Science
Fast mining of high dimensional expressive contrast patterns using zero-suppressed binary decision diagrams

Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
Discovering significant rules

Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
Using Significant, Positively Associated and Relatively Class Correlated Rules for Associative Classification of Imbalanced Datasets

ICDM '07 Proceedings of the 2007 Seventh IEEE International Conference on Data Mining
Mining a complete set of both positive and negative association rules from large databases

PAKDD'08 Proceedings of the 12th Pacific-Asia conference on Advances in knowledge discovery and data mining

On the stimulation of patterns: definitions, calculation method and first usages

ICCS'10 Proceedings of the 18th international conference on Conceptual structures: from information to intelligence
A new method for mining disjunctive emerging patterns in high-dimensional datasets using hypergraphs

Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Classification is an important task in data mining. Contrast patterns, such as emerging patterns, have been shown to be powerful for building classifiers, but they rarely exist in sparse data. Recently proposed disjunctive emerging patterns are highly expressive, and can potentially overcome this limitation. Simple contrast patterns only allow simple conjunctions, whereas disjunctive patterns additionally allow expressions of disjunctions. This paper investigates whether expressive contrasts are beneficial for classification. We adopt a statistical methodology for eliminating noisy patterns. Our experiments identify circumstances where expressive patterns can improve over previous contrast pattern based classifiers. We also present some guidelines for i) using expressive patterns based on the nature of the given data, ii) how to choose between the different types of contrast patterns for building a classifier.