Mining association rules between sets of items in large databases
SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data
Efficient mining of association rules using closed itemset lattices
Information Systems
A condensed representation to find frequent patterns
PODS '01 Proceedings of the twentieth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Concise Representation of Frequent Patterns Based on Disjunction-Free Generators
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Concise Representation of Frequent Patterns Based on Generalized Disjunction-Free Generators
PAKDD '02 Proceedings of the 6th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Dataless Transitions Between Concise Representations of Frequent Patterns
Journal of Intelligent Information Systems
Data Mining and Knowledge Discovery
Essential patterns: a perfect cover of frequent patterns
DaWaK'05 Proceedings of the 7th international conference on Data Warehousing and Knowledge Discovery
DS'10 Proceedings of the 13th international conference on Discovery science
Key roles of closed sets and minimal generators in concise representations of frequent patterns
Intelligent Data Analysis
| Hi-index | 0.00 |
The discovery of frequent patterns is one of the most important issues in the data mining area. A major difficulty concerning frequent patterns is huge amount of discovered patterns. The problem can be solved or at least significantly alleviated by applying concise representations of frequent patterns. A number of most concise representations use generalized disjunctive rules for reasoning about patterns. Recently, the representation based on essential patterns has been introduced, but was not confronted with the representations using generalized disjunctive rules. In this paper, we 1) prove that essential patterns with at least two elements can be defined equivalently in terms of generalized disjunctive rules of a particular subtype and that singleton patterns are essential if their supports do not equal 0, 2) identify the relationship between compressed disjunction-free patterns and essential ones, 3) propose new lossless representation E-CDFR of frequent patterns that is primarily based on compressed disjunction-free patterns and uses generalized disjunctive rules to reason about other patterns, 4) prove that the new representation is never less concise than the representation based on essential patterns.