Reducing Examples in Relational Learning with Bounded-Treewidth Hypotheses

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00196268" target="_blank" >RIV/68407700:21230/13:00196268 - isvavai.cz</a>
Result on the web
<a href="http://www.di.uniba.it/~ceci/micFiles/papers/NFMCP.pdf" target="_blank" >http://www.di.uniba.it/~ceci/micFiles/papers/NFMCP.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-642-37382-4_2" target="_blank" >10.1007/978-3-642-37382-4_2</a>

Result language
angličtina
Original language name
Reducing Examples in Relational Learning with Bounded-Treewidth Hypotheses
Original language description
We study reducibility of learning examples in the learning from entailment setting. We start with an existing reduction method and improve it for the case when learned hypotheses are restricted to have bounded treewidth. We show that in such cases thereis a polynomial-time reduction algorithm which reduces the learning examples at least as much as the existing exponential-time algorithm despite the fact that the examples which are reduced can have arbitrarily high treewidth.
Czech name
—
Czech description
—

Project
<a href="/en/project/GAP103%2F11%2F2170" target="_blank" >GAP103/11/2170: Transferring ILP techniques to statistical relational learning</a><br>
Continuities
S - Specificky vyzkum na vysokych skolach

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the Workshop on New Frontiers In Mining Complex Patterns
ISBN
978-3-642-37381-7
ISSN
0302-9743
e-ISSN
—
Number of pages
16
Pages from-to
17-32
Publisher name
ICAR - National Research Council
Place of publication
Naples
Event location
Bristol
Event date
Sep 24, 2012
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)