Region-based Energy Neural Network for Approximate Inference
This addresses the problem of efficient and accurate inference in general Markov random fields for researchers and practitioners in machine learning, offering a novel approach that avoids iterative message-passing and sampling, though it builds incrementally on existing region-based free energy concepts.
The paper tackles approximate inference in Markov random fields by proposing a region-based energy neural network (RENN) that directly minimizes region-based free energy, resulting in faster performance and outperforming methods like mean field, loopy belief propagation, and state-of-the-art neural models in experiments on marginal distribution estimation, partition function estimation, and MRF learning.
Region-based free energy was originally proposed for generalized belief propagation (GBP) to improve loopy belief propagation (loopy BP). In this paper, we propose a neural network based energy model for inference in general Markov random fields (MRFs), which directly minimizes the region-based free energy defined on region graphs. We term our model Region-based Energy Neural Network (RENN). Unlike message-passing algorithms, RENN avoids iterative message propagation and is faster. Also different from recent deep neural network based models, inference by RENN does not require sampling, and RENN works on general MRFs. RENN can also be employed for MRF learning. Our experiments on marginal distribution estimation, partition function estimation, and learning of MRFs show that RENN outperforms the mean field method, loopy BP, GBP, and the state-of-the-art neural network based model.