Heuristic Method for Discriminative Structure Learning of Markov Logic Networks

Abstract : In this paper, we present a heuristic-based algorithm to learn discriminative MLN structures automatically, directly from a training dataset. The algorithm heuristically transforms the relational dataset into boolean tables from which it builds candidate clauses for learning the final MLN. Comparisons to the state-of-the-art structure learning algorithms for MLNs in the three real-world domains show that the proposed algorithm outperforms them in terms of the conditional log likelihood (CLL), and the area under the precision-recall curve (AUC).
Document type :
Conference papers
Sorin Draghici and Taghi M. Khoshgoftaar and Vasile Palade and Witold Pedrycz and M. Arif Wani and Xingquan Zhu. ICMLA 2010, Dec 2010, Washington DC, United States. IEEE Computer Society, pp. 163-168, 2010
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00553007
Contributor : Christel Vrain <>
Submitted on : Thursday, January 6, 2011 - 12:34:14 PM
Last modification on : Thursday, January 17, 2019 - 3:06:04 PM

Identifiers

  • HAL Id : hal-00553007, version 1

Collections

Citation

Quang-Thang Dinh, Matthieu Exbrayat, Christel Vrain. Heuristic Method for Discriminative Structure Learning of Markov Logic Networks. Sorin Draghici and Taghi M. Khoshgoftaar and Vasile Palade and Witold Pedrycz and M. Arif Wani and Xingquan Zhu. ICMLA 2010, Dec 2010, Washington DC, United States. IEEE Computer Society, pp. 163-168, 2010. 〈hal-00553007〉

Share

Metrics

Record views

36