# Learning Bayesian Networks with Local Structure

arXiv: https://arxiv.org/abs/1302.3577 · HTML: https://mlsanity.com/paper/1302.3577/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2013.

## Built on by (most cited first, 9 of 9)

- [Staged trees and asymmetry-labeled DAGs](https://mlsanity.com/paper/2108.01994/) (2021)
- [Structural Learning of Simple Staged Trees](https://mlsanity.com/paper/2203.04390/) (2022)
- [Highly Efficient Structural Learning of Sparse Staged Trees](https://mlsanity.com/paper/2206.06970/) (2022)
- [Structure Learning of Contextual Markov Networks using Marginal Pseudo-likelihood](https://mlsanity.com/paper/2103.15540/) (2021)
- [Scalable Bayesian Network Structure Learning with Splines](https://mlsanity.com/paper/2110.14626/) (2021)
- [Learning and interpreting asymmetry-labeled DAGs: a case study on COVID-19 fear](https://mlsanity.com/paper/2301.00629/) (2023)
- [Causal KL: Evaluating Causal Discovery](https://mlsanity.com/paper/2111.06029/) (2021)
- [Efficiently Disentangle Causal Representations](https://mlsanity.com/paper/2201.01942/) (2022)
- [Causal Modeling of Adverse Pregnancy Outcomes via Adaptive LLM Proposals](https://mlsanity.com/paper/2608.21079/) (2026)

## Abstract (arXiv)

In this paper we examine a novel addition to the known methods for learning Bayesian networks from data that improves the quality of the learned networks. Our approach explicitly represents and learns the local structure in the conditional probability tables (CPTs), that quantify these networks. This increases the space of possible models, enabling the representation of CPTs with a variable number of parameters that depends on the learned local structures. The resulting learning procedure is capable of inducing models that better emulate the real complexity of the interactions present in the data. We describe the theoretical foundations and practical aspects of learning local structures, as well as an empirical evaluation of the proposed method. This evaluation indicates that learning curves characterizing the procedure that exploits the local structure converge faster than these of the standard procedure. Our results also show that networks learned with local structure tend to be more complex (in terms of arcs), yet require less parameters.