An efficient algorithm for finding optimal gain-ratio multiple-split tests on hierarchical attributes in decision tree learning

Authors:
Hussein Almuallim;Yasuhiro Akiba;Shigeo Kaneda
Affiliations:
Information and Computer Science Department, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia;NTT Communication Science Labs, Yokosuka-shi, Kanagawa, Japan;NTT Communication Science Labs, Yokosuka-shi, Kanagawa, Japan
Venue:
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Year:
1996

Citing 8
Cited 4

Quantifying inductive bias: AI learning algorithms and Valiant's learning framework

Artificial Intelligence
Boolean Feature Discovery in Empirical Learning

Machine Learning
The Use of Background Knowledge in Decision Tree Induction

Machine Learning
On the Handling of Continuous-Valued Attributes in Decision Tree Generation

Machine Learning
C4.5: programs for machine learning

C4.5: programs for machine learning
Trading Accuracy for Simplicity in Decision Trees

Machine Learning
Branching on attribute values in decision tree generation

AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
Induction of Decision Trees

Machine Learning

Building Hierarchical Classifiers Using Class Proximity

VLDB '99 Proceedings of the 25th International Conference on Very Large Data Bases
Hierarchical Classification of Documents with Error Control

PAKDD '01 Proceedings of the 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining
Learning accurate and concise naïve Bayes classifiers from attribute value taxonomies and data

Knowledge and Information Systems
Hierarchical classification of HTML documents with WebClassII

ECIR'03 Proceedings of the 25th European conference on IR research

Quantified Score

Hi-index	0.00

Visualization

Abstract

Given a set of training examples S and a tree-structured attribute x, the goal in this work is to find a multiple-split test defined on x that maximizes Quinlan's gain-ratio measure. The number of possible such multiple-split tests grows exponentially in the size of the hierarchy associated with the attribute. It is, therefore, impractical to enumerate and evaluate all these tests in order to choose the best one. We introduce an efficient algorithm for solving this problem that guarantees maximizing the gain-ratio over all possible tests. For a training set of m examples and an attribute hierarchy of height d, our algorithm runs in time proportional to dm, which makes it efficient enough for practical use.