@inproceedings{ebbf8984846c4e3a9bfc06a0164b2164,
title = "Efficient pattern mining of uncertain data with sampling",
abstract = "Mining frequent itemsets from transactional datasets is a well known problem with good algorithmic solutions. In the case of uncertain data, however, several new techniques have been proposed. Unfortunately, these proposals often suffer when a lot of items occur with many different probabilities. Here we propose an approach based on sampling by instantiating {"}possible worlds{"} of the uncertain data, on which we subsequently run optimized frequent itemset mining algorithms. As such we gain efficiency at a surprisingly low loss in accuracy. These is confirmed by a statistical and an empirical evaluation on real and synthetic data.",
author = "T. Calders and C. Garboni and B. Goethals",
year = "2010",
doi = "10.1007/978-3-642-13657-3\_51",
language = "English",
isbn = "978-3-642-13656-6",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "480--487",
editor = "M.J. Zaki and J.X. Yu and B. Ravindran and V. Pudi",
booktitle = "Advances in Knowledge Discovery and Data Mining (14th Pacific-Asia Conference, PAKDD 2010, Hyderabad, India, June 21-24, 2010. Proceedings, Part I)",
address = "Germany",
}