RRepresenting uncertainty in Description Logics has recently received an increasing attention because of its potential to model real world domains. EDGE, for “Em over bDds for description loGics para mEter learning”, is an algorithm for learning the parameters of probabilistic ontologies from data. However, the computational cost of this algorithm is significant since it may take hours to complete an execution. In this paper we present EDGEMR, a distributed version of EDGE that exploits the MapReduce strategy by means of the Message Passing Interface. Experiments on various domains show that EDGEMR significantly reduces EDGE running time.

Distributed Parameter Learning for Probabilistic Ontologies

ZESE, Riccardo;BELLODI, Elena;RIGUZZI, Fabrizio
;
LAMMA, Evelina
2016

Abstract

RRepresenting uncertainty in Description Logics has recently received an increasing attention because of its potential to model real world domains. EDGE, for “Em over bDds for description loGics para mEter learning”, is an algorithm for learning the parameters of probabilistic ontologies from data. However, the computational cost of this algorithm is significant since it may take hours to complete an execution. In this paper we present EDGEMR, a distributed version of EDGE that exploits the MapReduce strategy by means of the Message Passing Interface. Experiments on various domains show that EDGEMR significantly reduces EDGE running time.
2016
978-3-319-40565-0
Probabilistic Description Logics, Parameter Learning, MapReduce, Message Passing Interface
File in questo prodotto:
File Dimensione Formato  
edgempi_reviewed.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Post-print
Licenza: PUBBLICO - Pubblico con Copyright
Dimensione 436.92 kB
Formato Adobe PDF
436.92 kB Adobe PDF Visualizza/Apri
full text.pdf

solo gestori archivio

Descrizione: articolo
Tipologia: Full text (versione editoriale)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 453.58 kB
Formato Adobe PDF
453.58 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in SFERA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11392/2350944
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 0
social impact