Likelihood-Based Robust Classification with Bayesian Networks
Authors: Alessandro Antonucci, Marco Cattaneo and Giorgio Corani
Abstract: Bayesian networks are commonly used for classification: a structural learning algorithm determines the network graph, while standard approaches estimate the model parameters from data. Yet, with few data the corresponding assessments can be unreliable. To gain robustness in this phase, we consider a likelihood-based learning approach, which takes all the model quantifications whose likelihood exceeds a given threshold. A new classification algorithm based on this approach is presented. Notably, this is a credal classifier, i.e., more than a single class can be returned in output. This is the case when the Bayesian networks consistent with the threshold constraint assign different class labels to a test instance. This is the first classifier of this kind for general topologies. Experiments show how this approach provide the desired robustness.
Details: In Greco, S. and Bouchon-Meunier, B. and Coletti, G. and Fedrizzi, M. and Matarazzo, B. and Yager, R.R. (Eds.), Advances in Computational Intelligence. Springer, pp. 491-500.
A version similar to the published paper can be downloaded.