Learning the structure of continuous-time Bayesian networks directly from data has traditionally been performed using score-based structure learning algorithms. Only recently has a constraint-based method been proposed, proving to be more suitable under specific settings, as in modelling systems with variables having more than two states. As a result, studying diverse structure learning algorithms is essential to learn the most appropriate models according to data characteristics and task-related priorities, such as learning speed or accuracy. This article proposes several alternatives of such algorithms for learning multidimensional continuous-time Bayesian network classifiers, introducing for the first time constraint-based and hybrid algorithms for these models. Nevertheless, these contributions also apply to the simpler one-dimensional classification problem for which only score-based solutions exist in the literature. More specifically, the aforementioned constraint-based structure learning algorithm is first adapted to the supervised classification setting. Then, a novel algorithm of this kind, specifically tailored for the multidimensional classification problem, is presented to improve the learning times for the induction of multidimensional classifiers. Finally, a hybrid algorithm is introduced, attempting to combine the strengths of the score- and constraint-based approaches. Experiments with synthetic data are performed not only to validate the capabilities of the proposed algorithms but also to conduct a comparative study of the available structure learning algorithms.

Villa-Blanco, C., Bregoli, A., Bielza, C., Larranaga, P., Stella, F. (2022). Structure learning algorithms for multidimensional continuous-time Bayesian network classifiers. In 11th International Conference on Probabilistic Graphical Models, PGM 2022 (pp.313-324). ML Research Press.

Structure learning algorithms for multidimensional continuous-time Bayesian network classifiers

Bregoli Alessandro
Secondo
;
Stella Fabio
Ultimo
2022

Abstract

Learning the structure of continuous-time Bayesian networks directly from data has traditionally been performed using score-based structure learning algorithms. Only recently has a constraint-based method been proposed, proving to be more suitable under specific settings, as in modelling systems with variables having more than two states. As a result, studying diverse structure learning algorithms is essential to learn the most appropriate models according to data characteristics and task-related priorities, such as learning speed or accuracy. This article proposes several alternatives of such algorithms for learning multidimensional continuous-time Bayesian network classifiers, introducing for the first time constraint-based and hybrid algorithms for these models. Nevertheless, these contributions also apply to the simpler one-dimensional classification problem for which only score-based solutions exist in the literature. More specifically, the aforementioned constraint-based structure learning algorithm is first adapted to the supervised classification setting. Then, a novel algorithm of this kind, specifically tailored for the multidimensional classification problem, is presented to improve the learning times for the induction of multidimensional classifiers. Finally, a hybrid algorithm is introduced, attempting to combine the strengths of the score- and constraint-based approaches. Experiments with synthetic data are performed not only to validate the capabilities of the proposed algorithms but also to conduct a comparative study of the available structure learning algorithms.
paper
Bayesian network classifiers; Continuous-time Bayesian networks; learning from data; multidimensional classification; structure learning algorithms;
English
11th International Conference on Probabilistic Graphical Models, PGM 2022 - 5 October 2022 through 7 October 2022
2022
Salmeron, A; Rumi, R
11th International Conference on Probabilistic Graphical Models, PGM 2022
2022
186
313
324
none
Villa-Blanco, C., Bregoli, A., Bielza, C., Larranaga, P., Stella, F. (2022). Structure learning algorithms for multidimensional continuous-time Bayesian network classifiers. In 11th International Conference on Probabilistic Graphical Models, PGM 2022 (pp.313-324). ML Research Press.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/446221
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
Social impact