Learning Neural Random Fields with Inclusive Auxiliary Generators

By Yunfu Song, Zhijian Ou. 2018

31 citations recorded by the source corpus.

Neural random fields (NRFs), which are defined by using neural networks to implement potential functions in undirected models (sometimes known as energy-based models), provide an interesting family of model spaces for machine learning, besides various directed models such as generative adversarial networks (GANs). In this paper we propose a new approach, the inclusive-NRF approach, to learning NRFs for continuous data (e.g. images), by developing inclusive-divergence minimized auxiliary generators and stochastic gradient sampling. As demonstrations of how the new approach can be flexibly and effectively used, specific inclusive-NRF models are developed and thoroughly evaluated for a number of tasks - unsupervised/supervised image generation, semi-supervised classification and anomaly detection. The proposed models consistently achieve strong experimental results in all these tasks compared to state-of-the-art methods. Remarkably, in addition to superior sample generation, one fundamental additional benefit of our inclusive-NRF approach is that, unlike GANs, it directly provides (unnormalized) density estimate for sample evaluation. With these contributions and results, this paper significantly advances the learning and applications of undirected models to a new level, both theoretically and empirically, which have never been obtained before.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Generative Models

In Probabilistic & Bayesian Methods

Citations in the corpus

Improved Contrastive Divergence Training of Energy Based Models (2020, background): “…issue, a separate line of work utilizes an auxiliary network to amortize the negative portions of the sampling procedure (Kim & Bengio, 2016; Kumar et al., 2019; Han et al., 2019; Xie et al., 2018a; Song & Ou, 2018; Dai et al., 2019; Che et al., 2020; Grathwohl et al., 2020a; Arbel et al., 2020).”
Compositional Visual Generation with Energy Based Models (2020, methodology): “A number of methods have been used for inference and sampling in EBMs, from Gibbs Sampling [12], Langevin Dynamics [31, 3], Path Integral methods [2] and learned samplers [13, 26].”
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling (2020, background): “…structure prediction (Ingraham et al., 2019; Du et al., 2020), and provided beneﬁt to fundamental problems in machine learning such as adversarial robustness, calibration, out-of-distribution detection (Grathwohl et al., 2019; Du & Mor-datch, 2019), and semi-supervised learning (Song & Ou, 2018).”