Frequent Itemset Border Approximation by Dualization

Abstract : The approach FIBAD is introduced with the purpose of computing approximate borders of frequent itemsets by leveraging dualization and computation of approximate minimal transversals of hypergraphs. The distinctiveness of the FIBAD's theoretical foundations s the approximate dualization where a new function ~f is defined to compute the approximate negative border. From a methodological point of view, the function ~f is implemented by the method AMTHR that consists of a reduction of the hypergraph and a computation of its minimal transversals. For evaluation purposes, we study the sensibility of FIBAD to AMTHR by replacing this latter by two other algorithms that compute approximate minimal transversals. We also compare our approximate dualization-based method with an existing approach that computes directly, without dualization, the approximate borders. The experimental results show that our method outperforms the other methods as it produces borders that have the highest quality.
Document type :
Journal articles
Complete list of metadatas

Cited literature [41 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01465110
Contributor : Nicolas Durand <>
Submitted on : Wednesday, December 12, 2018 - 2:22:15 PM
Last modification on : Friday, July 26, 2019 - 1:32:08 PM
Long-term archiving on : Wednesday, March 13, 2019 - 2:50:10 PM

File

durand_tldks2016.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01465110, version 1

Collections

Citation

Nicolas Durand, Mohamed Quafafou. Frequent Itemset Border Approximation by Dualization. Transactions on Large-Scale Data- and Knowledge-Centered Systems, Springer Berlin / Heidelberg, 2016, 26, pp.32-60. ⟨hal-01465110⟩

Share

Metrics

Record views

237

Files downloads

82