Exploiting monotonicity via logistic regression in Bayesian network learning

An important challenge in machine learning is to find ways of learning quickly from very small amounts of training data. The only way to learn from small data samples is to constrain the learning process by exploiting background knowledge. In this report, we present a theoretical analysis on the use of constrained logistic regression for estimating conditional probability distribution in Bayesian Networks (BN) by using background knowledge in the form of qualitative monotonicity statements. Such background knowledge is treated as a set of constraints on the parameters of a logistic function during training. Our goal of finding the appropriate BN model is two-fold: (a) we want to exploit any monotonic relationship between random variables that may generally exist as domain knowledge and (b) we want to be able to address the problem of estimating the conditional distribution of a random variable with a large number of parents. We discuss variants of the logistic regression model and present an analysis on the corresponding constraints required to implement monotonicity. More importantly, we outline the problem in some of these variants in terms of the number of parameters and constraints which, in some cases, can grow exponentially with the number of parent variables. To address this problem, we present two variants of the constrained logistic regression model, M2b CLR and M3 CLR, in which the number of constraints required to implement monotonicity does not grow exponentially with the number of parents hence providing a practicable method for estimating conditional probabilities with very sparse data.