Active Structure Learning of Bayesian Networks in an Observational Setting

Noa Ben-David, Sivan Sabato

Research output: Contribution to journalArticlepeer-review


We study active structure learning of Bayesian networks in an observational setting, in which there are external limitations on the number of variable values that can be observed from the same sample. Random samples are drawn from the joint distribution of the network variables, and the algorithm iteratively selects which variables to observe in the next sample. We propose a new active learning algorithm for this setting, that finds with a high probability a structure with a score that is -close to the optimal score. We show that for a class of distributions that we term stable, a sample complexity reduction of up to a factor of Ω(e d3) can be obtained, where d is the number of network variables. We further show that in the worst case, the sample complexity of the active algorithm is guaranteed to be almost the same as that of a naive baseline algorithm. To supplement the theoretical results, we report experiments that compare the performance of the new active algorithm to the naive baseline and demonstrate the sample complexity improvements. Code for the algorithm and for the experiments is provided at

Original languageEnglish
Article number188
Pages (from-to)1-38
JournalJournal of Machine Learning Research
StatePublished - 1 Jun 2022


  • Active learning
  • Bayesian networks
  • combinatorial optimization
  • graphical models
  • sample complexity

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence


Dive into the research topics of 'Active Structure Learning of Bayesian Networks in an Observational Setting'. Together they form a unique fingerprint.

Cite this