Hybrid possibilistic networks

Possibilistic networks are important tools for dealing with uncertain pieces of information. For multiply-connected networks, it is well known that the inference process is a hard problem. This paper studies a new rep-resentation of possibilistic networks, called hybrid pos-sibilistic networks. The uncertainty is no longer repre-sented by local conditional possibility distributions, but by their compact representations which are possibilis-tic knowledge bases. We show that the inference algo-rithm in hybrid networks is strictly more efficient than the ones of standard propagation algorithm