Learning parameters of Bayesian networks from incomplete data via importance sampling

被引：19
|
作者：
Riggelsen, C [1 ]
机构：
[1] Univ Utrecht, Dept Informat & Comp Sci, NL-3508 TB Utrecht, Netherlands
来源：
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING | 2006年 / 42卷 / 1-2期
关键词：
Bayesian networks; parameter learning; incomplete data; MCMC; Bayesian statistics;
D O I：
10.1016/j.ijar.2005.10.005
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We present an algorithm for learning parameters of Bayesian networks from incomplete data. By using importance sampling we are able to assign a score to imputation proposals depending on the quality of such a proposal in combination with the observed data. This in effect makes it possible to approximate the posterior parameter distribution given incomplete data by using a mixture distribution with a tractable number of components. The technique allows for different imputation methods, in particular we propose an imputation method that combines Gibbs sampling and a data augmentation derivative. We evaluate our algorithm, and we compare the results to those obtained with WinBUGS and the EM algorithm. (C) 2005 Elsevier Inc. All rights reserved.
引用
收藏
页码：69 / 83
页数：15
相关论文
共 50 条
  • [1] Parameter learning from incomplete data for Bayesian networks
    Cowell, RG
    ARTIFICIAL INTELLIGENCE AND STATISTICS 99, PROCEEDINGS, 1999, : 193 - 196
  • [2] UNCERTAIN BAYESIAN NETWORKS: LEARNING FROM INCOMPLETE DATA
    Hougen, Conrad D.
    Kaplan, Lance M.
    Cerutti, Federico
    Hero, Alfred O.
    2021 IEEE 31ST INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2021,
  • [3] Learning from incomplete data in Bayesian networks with qualitative influences
    Masegosa, Andres R.
    Feelders, Ad J.
    van der Gaag, Linda C.
    INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2016, 69 : 18 - 34
  • [4] Being Bayesian about learning Gaussian Bayesian networks from incomplete data
    Grzegorczyk M.
    International Journal of Approximate Reasoning, 2023, 160
  • [5] An experimental comparison of methods for handling incomplete data in learning parameters of Bayesian networks
    Onisko, A
    Druzdzel, MJ
    Wasyluk, H
    INTELLIGENT INFORMATION SYSTEMS 2002, PROCEEDINGS, 2002, 17 : 351 - 360
  • [6] Learning Bayesian Networks with Incomplete Data by Augmentation
    Adel, Tameem
    de Campos, Cassio P.
    THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 1684 - 1690
  • [7] Learning the Parameters of Bayesian Networks from Uncertain Data
    Wasserkrug, Segev
    Marinescu, Radu
    Zeltyn, Sergey
    Shindin, Evgeny
    Feldman, Yishai A.
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 12190 - 12197
  • [8] Learning causal Bayesian networks from incomplete observational data and interventions
    Borchani, Hanen
    Chaouachi, Maher
    Ben Amor, Nahla
    SYMBOLIC AND QUANTITATIVE APPROACHES TO REASONING WITH UNCERTAINTY, PROCEEDINGS, 2007, 4724 : 17 - +
  • [9] A new method of learning Bayesian networks structures from incomplete data
    Li, XL
    He, XD
    Yuan, SM
    ARTIFICIAL NEURAL NETWORKS: FORMAL MODELS AND THEIR APPLICATIONS - ICANN 2005, PT 2, PROCEEDINGS, 2005, 3697 : 261 - 266
  • [10] Learning Bayesian networks from incomplete data using evolutionary algorithms
    Myers, JW
    Laskey, RB
    DeJong, KA
    GECCO-99: PROCEEDINGS OF THE GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 1999, : 458 - 465
12345