Learning Bayesian networks with local structure
Learning in graphical models
Molecular feature mining in HIV data
Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining
An Assessment of ILP-Assisted Models for Toxicology and the PTE-3 Experiment
ILP '99 Proceedings of the 9th International Workshop on Inductive Logic Programming
Tree Induction for Probability-Based Ranking
Machine Learning
Learning relational probability trees
Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Top-down induction of first-order logical decision trees
Artificial Intelligence
Generalized Ordering-Search for Learning Directed Probabilistic Logical Models
Inductive Logic Programming
Learning directed probabilistic logical models from relational data
AI Communications
Using Decision Trees as the Answer Networks in Temporal Difference-Networks
Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
Online learning and exploiting relational models in reinforcement learning
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
| Hi-index | 0.01 |
Probability trees (or Probability Estimation Trees, PET's) are decision trees with probability distributions in the leaves. Several alternative approaches for learning probability trees have been proposed but no thorough comparison of these approaches exists. In this paper we experimentally compare the main approaches using the relational decision tree learner Tilde (both on non-relational and on relational datasets). Next to the main existing approaches, we also consider a novel variant of an existing approach based on the Bayesian Information Criterion (BIC). Our main conclusion is that overall trees built using the C4.5-approach or the C4.4-approach (C4.5 without post-pruning) have the best predictive performance. If the number of classes is low, however, BIC performs equally well. An additional advantage of BIC is that its trees are considerably smaller than trees for the C4.5- or C4.4-approach.