Learning Bayesian Network Parameters with Prior Knowledge about Context-Specific Qualitative Influences

TL;DR

This paper introduces a method for learning Bayesian network parameters that incorporates prior knowledge of influence signs, including context-specific signs, using order constraints and isotonic regression to improve estimates especially with limited data.

Contribution

It extends Bayesian network parameter learning by integrating context-specific qualitative influence signs and applying order-constrained estimation techniques.

Findings

Improved fit of the true distribution with prior sign knowledge

Estimates are consistent with specified influence signs

Enhanced model acceptance by domain experts

Abstract

We present a method for learning the parameters of a Bayesian network with prior knowledge about the signs of influences between variables. Our method accommodates not just the standard signs, but provides for context-specific signs as well. We show how the various signs translate into order constraints on the network parameters and how isotonic regression can be used to compute order-constrained estimates from the available data. Our experimental results show that taking prior knowledge about the signs of influences into account leads to an improved fit of the true distribution, especially when only a small sample of data is available. Moreover, the computed estimates are guaranteed to be consistent with the specified signs, thereby resulting in a network that is more likely to be accepted by experts in its domain of application.