First-Order Bayes-Ball for CP-Logic
Nima Taghipour, Wannes Meert, Jan Struyf, Hendrik Blockeel · Lirias · 2009
Efficient probabilistic inference is key to the success of statistical relational learning. One issue that affects inference cost is the pres-ence of irrelevant random variables. The Bayes-ball algorithm can identify such irrel-evant variables in a propositional Bayesian network. This paper presents a lifted ver-sion of Bayes-ball, which works directly on the first-order level, and shows how this al-gorithm applies to CP-logic inference. 1.