@InProceedings{Supelec537,
author = {Frederic Pennerath and Amedeo Napoli},
title = {The Model of Most Informative Patterns and its Application to Knowledge Extraction from Graph Databases},
year = {2009},
booktitle = {Machine Learning and Knowledge Discovery in Databases, European Conference (ECML PKDD 2009), Proceedings, Part II},
publisher = {Springer},
volume = {5782},
pages = {205-220},
month = {September},
editor = {Wray L. Buntine and Marko Grobelnik and Dunja Mladenic and John Shawe-Taylor},
series = {Lecture Notes in Computer Science},
address = {Bled (Slovenia)},
url = {http://dx.doi.org/10.1007/978-3-642-04174-7_14},
isbn = {978-3-642-04173-0},
doi = {10.1007/978-3-642-04174-7_14},
abstract = {This article introduces the class of Most Informative Patterns (MIPs) for characterizing a given dataset. MIPs form a reduced subset of non redundant closed patterns that are extracted from data thanks to a scoring function depending on domain knowledge. Accordingly, MIPs are designed for providing experts good insights on the content of datasets during data analysis. The article presents the model of MIPs and their formal properties wrt other kinds of patterns. Then, two algorithms for extracting MIPs are detailed: the first directly searches for MIPs in a dataset while the second screens MIPs from frequent patterns. The efficiencies of both algorithms are compared when applied to reference datasets. Finally the application of MIPs to labelled graphs, here molecular graphs, is discussed.}
}