When and where to transfer for Bayesian network parameter learning

作者：

Highlights：

• Proposed a Bayesian network parameter transfer learning (BNPTL) algorithm.

• This algorithm can deal with both discrete and continuous cases.

• This algorithm can diagnose both network and sub-graph relatedness across BNs.

• Improved parameter learning performance of BNs in medical decision applications.

摘要

•Proposed a Bayesian network parameter transfer learning (BNPTL) algorithm.•This algorithm can deal with both discrete and continuous cases.•This algorithm can diagnose both network and sub-graph relatedness across BNs.•Improved parameter learning performance of BNs in medical decision applications.

论文关键词：Bayesian networks parameter learning,Transfer learning,Bayesian model comparison,Bayesian model averaging

论文评审过程：Received 14 August 2015, Revised 15 January 2016, Accepted 8 February 2016, Available online 18 February 2016, Version of Record 5 March 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.02.011