Extended Tree Augmented Naive Classifier

Cassio P. de Campos, Marco Cuccu, Giorgio Corani, Marco Zaffalon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)


This work proposes an extended version of the well-known tree-augmented naive Bayes (TAN) classifier where the structure learning step is performed without requiring features to be connected to the class. Based on a modification of Edmonds’ algorithm, our structure learning procedure explores a superset of the structures that are considered by TAN, yet achieves global optimality of the learning score function in a very efficient way (quadratic in the number of features, the same complexity as learning TANs). A range of experiments show that we obtain models with better accuracy than TAN and comparable to the accuracy of the state-of-the-art classifier averaged one-dependence estimator.
Original languageEnglish
Title of host publicationProbabilistic Graphical Models: 7th European Workshop, PGM 2014, Utrecht, The Netherlands, September 17-19, 2014. Proceedings
EditorsLinda C. van der Gaag, Ad J. Feelders
Number of pages14
VolumeLNAI 8754
ISBN (Electronic)9783319114330
ISBN (Print)9783319114323
Publication statusPublished - 2015
Event7th European Workshop, PGM 2014 - Utrecht, Netherlands
Duration: 17 Sep 201419 Sep 2014

Publication series

NameLecture Notes in Artificial Intelligence
VolumeLNAI 8794


Conference7th European Workshop, PGM 2014

Bibliographical note

(selected for special issue, blind peer reviewed by >3 reviewers)


Dive into the research topics of 'Extended Tree Augmented Naive Classifier'. Together they form a unique fingerprint.

Cite this