Unsupervised Learning of Noisy-Or Bayesian Networks

By Yoni Halpern, David A. Sontag. 2013

36 citations recorded by the source corpus.

This paper considers the problem of learning the parameters in Bayesian networks of discrete variables with known structure and hidden variables. Previous approaches in these settings typically use expectation maximization; when the network has high treewidth, the required expectations might be approximated using Monte Carlo or variational methods. We show how to avoid inference altogether during learning by giving a polynomial-time algorithm based on the method-of-moments, building upon recent work on learning discrete-valued mixture models. In particular, we show how to learn the parameters for a family of bipartite noisy-or Bayesian networks. In our experimental results, we demonstrate an application of our algorithm to learning QMR-DT, a large Bayesian network used for medical diagnosis. We show that it is possible to fully learn the parameters of QMR-DT even when only the findings are observed in the training data (ground truth diseases unknown).

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Improving the accuracy of medical diagnosis with causal machine learning (2020, background): “In addition, they support ef ﬁ cient inference 67 and learning 68,69 , and allow for large BNs to be described by a number of parameters that grows linearly with the size of the network 68,70 .”
Tensor Factorization via Matrix Factorization (2015, unknown): “knowledge bases [2], topic modeling [3], community detection [4], learning graphical models [5, 6].”
Discovering Hidden Variables in Noisy-Or Networks using Quartet Tests (2013, methodology): “Furthermore, using a technique introduced by Halpern & Sontag (2013), we show how to subtract already learned latent variables to create new singly-coupled quartets, substantially expanding the class of structures that we can learn.”
Unsupervised Risk Estimation with only Structural Assumptions (2016, background): “As an example, these conditions hold for many groups of diseases/symptoms in the QMR knowledge base (Halpern & Sontag, 2013); more generally, the 3-view assumption is the workhorse of the method of moments for estimating latent-variable models (e.g., Anandkumar et al., 2013).”
Evaluate the Malignancy of Pulmonary Nodules Using the 3-D Deep Leaky Noisy-OR Network (2017, methodology): “Halpern and Sontag [33] proposed an unsupervised learning method based on the noisy-OR model and validated it on the quick medical reference model.”