@InProceedings{Supelec628,
author = {Frederic Pennerath},
title = {{Fast Extraction of Locally Optimal Patterns based on Consistent Pattern Function Variations}},
year = {2010},
booktitle = {{Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2010}},
publisher = {Springer},
volume = {6323},
pages = {34-49},
month = {September},
editor = {José L. Balcazar and Francesco Bonchi and Aristides Gionis and Michèle Sebag},
series = {Lecture Notes in Computer Science},
address = {Barcelona (Spain)},
url = {http://dx.doi.org/10.1007/978-3-642-15939-8_3},
isbn = {978-3-642-15938-1},
doi = {10.1007/978-3-642-15939-8_3},
abstract = {This article introduces the problem of searching locally optimal
patterns within a set of patterns constrained by some
anti-monotonic predicate: given any pattern scoring function, a
locally optimal pattern has a maximal (or minimal) score locally
among neighboring patterns. Some instances of this problem have
produced patterns of interest in the framework of knowledge
discovery since locally optimal patterns extracted from datasets
are very few, informative and non-redundant compared to other
pattern families derived from frequent patterns. This article
then introduces the concept of
variation consistency to characterize pattern functions and uses
this notion to propose GALLOP, an algorithm that outperforms
existing algorithms to extract locally optimal itemsets. Finally
it shows how GALLOP can generically be applied to two classes of
scoring functions useful in binary classification or clustering
pattern mining problems.}
}