Basic Principles of Learning Bayesian Logic ProgramsKristian Kersting; Luc De Raedt
In: Luc De Raedt; Paolo Frasconi; Kristian Kersting; Stephen H. Muggleton (Hrsg.). Probabilistic Inductive Logic Programming - Theory and Applications. Pages 189-221, Lecture Notes in Computer Science, Vol. 4911, Springer, 2008.
Bayesian logic programs tightly integrate definite logic programs with Bayesian networks in order to incorporate the notions of objects and relations into Bayesian networks. They establish a one-to-one mapping between ground atoms and random variables, and between the immediate consequence operator and the directly influenced by relation. In doing so, they nicely separate the qualitative (i.e. logical) component from the quantitative (i.e. the probabilistic) one providing a natural framework to describe general, probabilistic dependencies among sets of random variables. In this chapter, we present results on combining Inductive Logic Programming with Bayesian networks to learn both the qualitative and the quantitative components of Bayesian logic programs from data. More precisely, we show how the qualitative components can be learned by combining the inductive logic programming setting learning from interpretations with score-based techniques for learning Bayesian networks. The estimation of the quantitative components is reduced to the corresponding problem of (dynamic) Bayesian networks.