Enumerating Equivalence Classes of Bayesian Networks Using EC Graphs
Abstract
We consider the problem of learning Bayesian network structures from complete data. In particular, we consider the enumeration of their k-best equivalence classes. We propose a new search space for A* search, called the EC graph, that facilitates the enumeration of equivalence classes, by representing the space of completed, partially directed acyclic graphs. We also propose a canonization of this search space, called the EC tree, which further improves the efficiency of enumeration. Empirically, our approach is orders of magnitude more efficient than the state-of-the-art at enumerating equivalence classes.
Cite
Text
Chen et al. "Enumerating Equivalence Classes of Bayesian Networks Using EC Graphs." International Conference on Artificial Intelligence and Statistics, 2016.Markdown
[Chen et al. "Enumerating Equivalence Classes of Bayesian Networks Using EC Graphs." International Conference on Artificial Intelligence and Statistics, 2016.](https://mlanthology.org/aistats/2016/chen2016aistats-enumerating/)BibTeX
@inproceedings{chen2016aistats-enumerating,
title = {{Enumerating Equivalence Classes of Bayesian Networks Using EC Graphs}},
author = {Chen, Eunice Yuh-Jie and Choi, Arthur and Darwiche, Adnan},
booktitle = {International Conference on Artificial Intelligence and Statistics},
year = {2016},
pages = {591-599},
url = {https://mlanthology.org/aistats/2016/chen2016aistats-enumerating/}
}