Hierarchical Dependency Constrained Averaged One-Dependence Estimators Classifiers for Hierarchical Feature Spaces

Cen Wan, Alex Freitas
Proceedings of the 10th International Conference on Probabilistic Graphical Models, PMLR 138:557-568, 2020.

Abstract

The Averaged One-Dependence Estimators classifier is a type of probabilistic graphical model that constructs an ensemble of one-dependency networks, using each feature in turn as a parent node for all other features, in order to estimate the distribution of the data. In this work, we propose two new types of Hierarchical dependency constrained Averaged One-Dependence Estimators (Hie-AODE) algorithms, which consider the pre-defined parent-child relationship between features during the construction of individual one-dependence estimators, when coping with hierarchically structured features. Experiments with 28 real-world bioinformatics datasets showed that the proposed Hie-AODE methods obtained better predictive performance than the conventional AODE classifier, and enhanced the robustness against imbalanced class distributions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v138-wan20a, title = {Hierarchical Dependency Constrained Averaged One-Dependence Estimators Classifiers for Hierarchical Feature Spaces}, author = {Wan, Cen and Freitas, Alex}, booktitle = {Proceedings of the 10th International Conference on Probabilistic Graphical Models}, pages = {557--568}, year = {2020}, editor = {Jaeger, Manfred and Nielsen, Thomas Dyhre}, volume = {138}, series = {Proceedings of Machine Learning Research}, month = {23--25 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v138/wan20a/wan20a.pdf}, url = {https://proceedings.mlr.press/v138/wan20a.html}, abstract = {The Averaged One-Dependence Estimators classifier is a type of probabilistic graphical model that constructs an ensemble of one-dependency networks, using each feature in turn as a parent node for all other features, in order to estimate the distribution of the data. In this work, we propose two new types of Hierarchical dependency constrained Averaged One-Dependence Estimators (Hie-AODE) algorithms, which consider the pre-defined parent-child relationship between features during the construction of individual one-dependence estimators, when coping with hierarchically structured features. Experiments with 28 real-world bioinformatics datasets showed that the proposed Hie-AODE methods obtained better predictive performance than the conventional AODE classifier, and enhanced the robustness against imbalanced class distributions.} }
Endnote
%0 Conference Paper %T Hierarchical Dependency Constrained Averaged One-Dependence Estimators Classifiers for Hierarchical Feature Spaces %A Cen Wan %A Alex Freitas %B Proceedings of the 10th International Conference on Probabilistic Graphical Models %C Proceedings of Machine Learning Research %D 2020 %E Manfred Jaeger %E Thomas Dyhre Nielsen %F pmlr-v138-wan20a %I PMLR %P 557--568 %U https://proceedings.mlr.press/v138/wan20a.html %V 138 %X The Averaged One-Dependence Estimators classifier is a type of probabilistic graphical model that constructs an ensemble of one-dependency networks, using each feature in turn as a parent node for all other features, in order to estimate the distribution of the data. In this work, we propose two new types of Hierarchical dependency constrained Averaged One-Dependence Estimators (Hie-AODE) algorithms, which consider the pre-defined parent-child relationship between features during the construction of individual one-dependence estimators, when coping with hierarchically structured features. Experiments with 28 real-world bioinformatics datasets showed that the proposed Hie-AODE methods obtained better predictive performance than the conventional AODE classifier, and enhanced the robustness against imbalanced class distributions.
APA
Wan, C. & Freitas, A.. (2020). Hierarchical Dependency Constrained Averaged One-Dependence Estimators Classifiers for Hierarchical Feature Spaces. Proceedings of the 10th International Conference on Probabilistic Graphical Models, in Proceedings of Machine Learning Research 138:557-568 Available from https://proceedings.mlr.press/v138/wan20a.html.

Related Material