Compression-based AODE classifiers
Authors: Giorgio Corani, Alessandro Antonucci and Rosa, R.
Abstract: We propose the COMP-AODE classifier, which adopts the compression-based approach to average the posterior probabilities computed by different non-naive classifier (SPODEs). COMP-AODE improves classification performance over the well-known AODE model. COMP-AODE assumes a uniform prior over the SPODEs; we then develop the credal classifier COMP-AODE*, substituting the uniform prior by a set of priors. COMP-AODE* returns more classes when the classification is prior-dependent, namely if the most probable class varies with the prior adopted over the SPODEs. COMP-AODE* achieves higher classification utility than both COMP-AODE and AODE.
Details: In De Raedt, L. and Bessiere, C. and Dubois, D. and Doherty, P. and Frasconi, P. and Heintz, F. and Lucas, P.J.F. (Eds.), Proceedings 20th European Conference on Artificial Intelligence (ECAI 2012). IOS Press, pp. 264-269.
A version similar to the published paper can be downloaded.