General Purpose MRF Learning with Neural Network Potentials

General Purpose MRF Learning with Neural Network Potentials

Hao Xiong, Nicholas Ruozzi

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Main track. Pages 2769-2776. https://doi.org/10.24963/ijcai.2020/384

Maximum likelihood learning is a well-studied approach for fitting discrete Markov random fields (MRFs) to data. However, general purpose maximum likelihood estimation for fitting MRFs with continuous variables have only been studied in much more limited settings. In this work, we propose a generic MLE estimation procedure for MRFs whose potential functions are modeled by neural networks. To make learning effective in practice, we show how to leverage a highly parallelizable variational inference method that can easily fit into popular machining learning frameworks like TensorFlow. We demonstrate experimentally that our approach is capable of effectively modeling the data distributions of a variety of real data sets and that it can compete effectively with other common methods on multilabel classification and generative modeling tasks.
Keywords:
Machine Learning: Learning Graphical Models
Uncertainty in AI: Approximate Probabilistic Inference
Uncertainty in AI: Graphical Models