Learning Bayesian Network Model Structure from Data
By Dimitris Margaritis. 2003
362 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/bc9205c2f3c46a7a05ddf7ce00d27a5474430fcc
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Yang Liu
- Kyunghyun Cho
- Zhe Gan
- Mohit Bansal
- Percy Liang
- Ruslan Salakhutdinov
- Charu C. Aggarwal
Citations in the corpus
- Learning Deep Generative Models of Graphs (2018, background): “Distributions on graphs can also provide priors for Bayesian structure learning of graphical models (Margaritis, 2003).”
- A survey of Bayesian Network structure learning (2021, background): “Although detailed performance results are not given, the authors suggested that cases where Sepsets do include non-parents are relatively rare, and so performance may in practice be relatively close to PC.”
- Plausible Deniability for Privacy-Preserving Data Synthesis (2017, background): “There are multiple approaches to this problem in the literature [35].”
- Interventional Fairness: Causal Database Repair for Algorithmic Fairness (2019, methodology): “For all datasets, the chosen training variables included the Markov boundary of the outcome variables, which were learned from data using the Grow-Shrink algorithm [32] and permutation [44].”
- Driver Behavior Analysis for Safe Driving: A Survey (2015, methodology): “In this section, we first categorize human fatigue expressions based on A Dynamic Bayesian Network for Fatigue Modeling [18].”
- Learning Bayesian Networks with the bnlearn R Package (2009, methodology): “…implements the following constraint-based learning algorithms (the respective function names are reported in parenthesis): • Grow-Shrink ( gs ): based on the Grow-Shrink Markov Blanket , the simplest Markov blanket detection algorithm (Margaritis 2003) used in a structure learning algorithm.”
- PrivBayes: private data release via bayesian networks (2014, background): “, hill-climbing, genetic algorithms, and simulated annealing) are often employed in practice [28].”