Two novel Ant Colony Optimization approaches for Bayesian network structure learning

Learning Bayesian networks from data is an NP-hard problem with important practical applications. Several researchers have designed algorithms to overcome the computational complexity of this task. Difficult challenges remain however in reducing computation time for structure learning in networks of medium to large size and in understanding problem-dependent aspects of performance. In this paper, we present two novel algorithms (ChainACO and K2ACO) that use Ant Colony Optimization (ACO). Both algorithms search through the space of orderings of data variables. The ChainACO approach uses chain structures to reduce computational complexity of evaluation but at the expense of ignoring the richer structure that is explored in the K2ACO approach. The novel algorithms presented here are ACO versions of previously published GA approaches. We are therefore able to compare ACO vs GA algorithms and Chain vs K2 evaluations. We present a series of experiments on three well-known benchmark problems. Our results show problem-specific trade-offs between solution quality and computational effort. However it seems that the ACO-based approaches might be favored for larger problems, achieving better fitnesses and success rate than their GA counterparts on the largest network studied in our experiments.