'Say EM' for Selecting Probabilistic Models for Logical Sequences
This addresses model selection for logical hidden Markov models in domains like protein secondary structures or shell logs, representing an incremental improvement over existing methods.
The paper tackles the problem of selecting probabilistic models for logical sequences, which have rich internal structures, by proposing SAGEM, a method that combines generalized expectation maximization with structure search using inductive logic programming refinement operators, and experimental results demonstrate its effectiveness.
Many real world sequences such as protein secondary structures or shell logs exhibit a rich internal structures. Traditional probabilistic models of sequences, however, consider sequences of flat symbols only. Logical hidden Markov models have been proposed as one solution. They deal with logical sequences, i.e., sequences over an alphabet of logical atoms. This comes at the expense of a more complex model selection problem. Indeed, different abstraction levels have to be explored. In this paper, we propose a novel method for selecting logical hidden Markov models from data called SAGEM. SAGEM combines generalized expectation maximization, which optimizes parameters, with structure search for model selection using inductive logic programming refinement operators. We provide convergence and experimental results that show SAGEM's effectiveness.