A Comparison between Two Statistical Relational Models - Archive ouverte HAL Access content directly
Conference Papers Year : 2008

A Comparison between Two Statistical Relational Models

Lorenza Saitta
  • Function : Author

Abstract

Statistical Relational Learning has received much attention this last decade. In the ILP community, several models have emerged for modelling and learning uncertain knowledge, expressed in subset of first order logics. Nevertheless, no deep comparisons have been made among them and, given an application, determining which model must be chosen is difficult. In this paper, we compare two of them, namely Markov Logic Networks and Bayesian Programs, especially with respect to their representation ability and inference methods. The comparison shows that the two models are substantially different, from the point of view of the user, so that choosing one really means choosing a different philosophy to look at the problem. In order to make the comparison more concrete, we have used a running example, which shows most of the interesting points of the approaches, yet remaining exactly tractable.
No file

Dates and versions

hal-00460933 , version 1 (02-03-2010)

Identifiers

  • HAL Id : hal-00460933 , version 1

Cite

Lorenza Saitta, Christel Vrain. A Comparison between Two Statistical Relational Models. ILP 08 - Inductive Logic Programming Conference, 2008, Prague, Czech Republic. pp.244-260. ⟨hal-00460933⟩
125 View
0 Download

Share

Gmail Mastodon Facebook X LinkedIn More