“School of Biological Sciences”
Back to Papers HomeBack to Papers of School of Biological Sciences
| Paper IPM / Biological Sciences / 14427 |
|
||||||
| Abstract: | |||||||
|
One of the most effective structure-learning methods in Bayesian network is K2 algorithm. Because the performance of the K2 algorithm
depends on node ordering, more effective node ordering inference methods are needed. In this paper, we introduce a novel node ordering method
based on the L1-regularized Markov Blanket and Modified Likelihood Reduction Factor (LRF). For this purpose, based on the fact that the parent
and child variables are identified by estimated Markov Blanket (MB), we first estimate the MB of a variable by using the L1-regularized Markov
Blanket. We then determine the candidate parents of a variable by evaluating the conditional frequency associations using a modification LRF.
In other words, we introduce a novel scoring which infers the better parent variable through the estimated MB. Then the candidate parents are
used as input for the K2 algorithm. Experimental results for most of the datasets indicate that our proposed method significantly outperforms
previous method.
Download TeX format |
|||||||
| back to top | |||||||
