← Back to papers
2007 NIPS NeurIPS 2007

Infinite State Bayes-Nets for Structured Domains

Abstract

A general modeling framework is proposed that unifies nonparametric-Bayesian models, topic-models and Bayesian networks. This class of infinite state Bayes nets (ISBN) can be viewed as directed networks of ‘hierarchical Dirichlet processes’ (HDPs) where the domain of the variables can be structured (e.g. words in documents or features in images). We show that collapsed Gibbs sampling can be done efficiently in these models by leveraging the structure of the Bayes net and using the forward-filtering-backward-sampling algorithm for junction trees. Existing models, such as nested-DP, Pachinko allocation, mixed membership sto- chastic block models as well as a number of new models are described as ISBNs. Two experiments have been performed to illustrate these ideas.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Machine Learning
🧭 Keyword Pioneer — bayesian networks
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics
📈 Trend Setter — Topic Modeling
🐣 Hot Topic Early Bird — bayesian network

Authors

Max Welling , Ian Porteous , Evgeniy Bart

Topics

Artificial Intelligence > Bayesian & Probabilistic > Bayesian Learning Artificial Intelligence > Bayesian & Probabilistic > Probabilistic Modeling Machine Learning > Core Methods > Clustering Machine Learning > Bayesian & Probabilistic > Bayesian Learning Machine Learning > Bayesian & Probabilistic > Probabilistic Modeling Machine Learning > Bayesian & Probabilistic > Bayesian Inference Machine Learning > Core Methods > Topic Modeling Machine Learning > Bayesian & Probabilistic > Bayesian Networks Machine Learning > Bayesian & Probabilistic > Nonparametric Bayesian

Keywords

nonparametric bayesian hierarchical dirichlet processes gibbs sampling hierarchical dirichlet process collapsed gibbs sampling bayesian network graphical model probabilistic graphical model topic model
Download PDF

Related papers

Exponential Family Predictive Representations of State 2007
Privacy-Preserving Belief Propagation and Sampling 2007
Efficient Principled Learning of Thin Junction Trees 2007
How SVMs can estimate quantiles and the median 2007
Rapid Inference on a Novel AND/OR graph for Object Detection, Segmentation and Parsing 2007