• 1
  • 2
  • 5
  • 6
  • 3
  • 4
IPM
30
YEARS OLD

“School of Biological Sciences”

Back to Papers Home
Back to Papers of School of Biological Sciences

Paper   IPM / Biological Sciences / 15257
School of Biological Sciences
  Title:   Some Node Ordering Methods for the K2 Algorithm
  Author(s): 
1.  Rosa Aghdam
2.  Vahid Rezaei Tabar
3.  Hamid Pezeshk
  Status:   Published
  Journal: Computational Intelligence
  Vol.:  DOI: 10.1111/coin.12182
  Year:  2018
  Pages:   1-17
  Supported by:  IPM
  Abstract:
Inferring Bayesian network structure from data is a challenging issue and many researchers have been working on this problem. The K2 is a well-known order dependent algorithm to learn Bayesian network. The result of the algorithm is not robust since it achieves different network structure if node orderings are permuted. Consequently, choosing suitable sequential node ordering for the input of the K2 algorithm is a challenging task. In this work, some deterministic methods for selecting suitable sequential node ordering are introduced. The effectiveness of these methods bench marked through the Asia, Alarm, Car and Insurance networks. The results indicate that the methods based on the concept of mutual information and entropy are suitable for finding a sequential node ordering and considerably improves the precision of network inference. The source code and selected data sets are available on http://profiles.bs.ipm.ir/softwares/ordering/.
Key words: Inferring Bayesian network structure, the K2 Algorithm, order dependent algorithm, mutual information, entropy.

Download TeX format
back to top
Clients Logo
Clients Logo
Clients Logo
Clients Logo
Clients Logo
Clients Logo
Clients Logo
Clients Logo
scroll left or right