Unsupervised Learning of Noisy-Or Bayesian Networks

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).

[1]  H. E. Pople,et al.  Internist-I, an Experimental Computer-Based Diagnostic Consultant for General Internal Medicine , 1982 .

[2]  Anima Anandkumar,et al.  A Method of Moments for Mixture Models and Hidden Markov Models , 2012, COLT.

[3]  Michael I. Jordan,et al.  Approximate Inference A lgorithms for Two-Layer Bayesian Networks , 1999, NIPS.

[4]  D. Heckerman,et al.  ,81. Introduction , 2022 .

[5]  Anima Anandkumar,et al.  A Spectral Algorithm for Latent Dirichlet Allocation , 2012, Algorithmica.

[6]  Sham M. Kakade,et al.  Identifiability and Unmixing of Latent Parse Trees , 2012, NIPS.

[7]  Adel Javanmard,et al.  Learning Linear Bayesian Networks with Latent Variables , 2012, ICML.

[8]  David Heckerman,et al.  A Tractable Inference Algorithm for Diagnosing Multiple Diseases , 2013, UAI.

[9]  Yishay Mansour,et al.  Exact Inference of Hidden Structure from Sample Data in noisy-OR Networks , 1998, UAI.

[10]  J. Myers,et al.  The INTERNIST-1/QUICK MEDICAL REFERENCE project--status report. , 1986, The Western journal of medicine.

[11]  Milos Hauskrecht,et al.  Noisy-OR Component Analysis and its Application to Link Analysis , 2006, J. Mach. Learn. Res..

[12]  J. Berge,et al.  Kruskal's polynomial for 2×2×2 arrays and a generalization to 2×n×n arrays , 1991 .

[13]  Michael I. Jordan,et al.  Variational Probabilistic Inference and the QMR-DT Network , 2011, J. Artif. Intell. Res..

[14]  C. Matias,et al.  Identifiability of parameters in latent structure models with many observed variables , 2008, 0809.5032.

[15]  Quaid Morris,et al.  Anonymised QMR KB to aQMR-DT , 2007 .

[16]  Joseph T. Chang,et al.  Full reconstruction of Markov models on evolutionary trees: identifiability and consistency. , 1996, Mathematical biosciences.