### Abstract

We present two algorithms for learning the structure of a Markov network from discrete data: GSMN and GSIMN. Both algorithms use statistical conditional independence tests on data to infer the structure by successively constraining the set of structures consistent with the results of these tests. GSMN is a natural adaptation of the Grow-Shrink algorithm of Margaritis and Thrun for learning the structure of Bayesian networks. GSIMN extends GSMN by additionally exploiting Pearl's well-known properties of conditional independence relations to infer novel independencies from known independencies, thus avoiding the need to perform these tests. Experiments on artificial and real data sets show GSIMN can yield savings of up to 70% with respect to GSMN, while generating a Markov network with comparable or in several cases considerably improved quality. In addition to GSMN, we also compare GSIMN to a forward-chaining implementation, called GSIMN-FCH, that produces all possible conditional independence results by repeatedly applying Pearl's theorems on the known conditional independence tests. The results of this comparison show that GSIMN is nearly optimal in terms of the number of tests it can infer, under a fixed ordering of the tests performed.

Original language | English (US) |
---|---|

Title of host publication | Proceedings of the Sixth SIAM International Conference on Data Mining |

Pages | 141-152 |

Number of pages | 12 |

State | Published - Jul 3 2006 |

Event | Sixth SIAM International Conference on Data Mining - Bethesda, MD, United States Duration: Apr 20 2006 → Apr 22 2006 |

### Publication series

Name | Proceedings of the Sixth SIAM International Conference on Data Mining |
---|---|

Volume | 2006 |

### Other

Other | Sixth SIAM International Conference on Data Mining |
---|---|

Country | United States |

City | Bethesda, MD |

Period | 4/20/06 → 4/22/06 |

### All Science Journal Classification (ASJC) codes

- Engineering(all)

## Fingerprint Dive into the research topics of 'Efficient Markov network structure discovery using independence tests'. Together they form a unique fingerprint.

## Cite this

*Proceedings of the Sixth SIAM International Conference on Data Mining*(pp. 141-152). (Proceedings of the Sixth SIAM International Conference on Data Mining; Vol. 2006).