Mining massive hierarchical data using a scalable probabilistic graphical model

Probabilistic Graphical Models (PGM) are very useful in the fields of machine learning and data mining. The crucial limitation of those models, however, is their scalability. The Bayesian Network, which is one of the most common PGMs used in machine learning and data mining, demonstrates this limitation when the training data consists of random variables, in which each of them has a large set of possible values. In the big data era, one could expect new extensions to the existing PGMs to handle the massive amount of data produced these days by computers, sensors and other electronic devices. With hierarchical data - data that is arranged in a treelike structure with several levels - one may see hundreds of thousands or millions of values distributed over even just a small number of levels. When modeling this kind of hierarchical data across large data sets, unrestricted Bayesian Networks may become infeasible for representing the probability distributions. In this paper, we introduce an extension to Bayesian Networks that can handle massive sets of hierarchical data in a reasonable amount of time and space. The proposed model achieves high precision and high recall when used as a multi-label classifier for the annotation of mass spectrometry data. On another data set of 1.5 billion search logs provided by CareerBuilder.com, the model was able to predict latent semantic relationships among search keywords with high accuracy.