Bayesian Semisupervised Learning with Deep Generative Models

06/29/2017
by   Jonathan Gordon, et al.
0

Neural network based generative models with discriminative components are a powerful approach for semi-supervised learning. However, these techniques a) cannot account for model uncertainty in the estimation of the model's discriminative component and b) lack flexibility to capture complex stochastic patterns in the label generation process. To avoid these problems, we first propose to use a discriminative component with stochastic inputs for increased noise flexibility. We show how an efficient Gibbs sampling procedure can marginalize the stochastic inputs when inferring missing labels in this model. Following this, we extend the discriminative component to be fully Bayesian and produce estimates of uncertainty in its parameter values. This opens the door for semi-supervised Bayesian active learning.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

11/22/2016

Max-Margin Deep Generative Models for (Semi-)Supervised Learning

Deep generative models (DGMs) are effective on learning multilayered rep...
08/21/2016

Inverting Variational Autoencoders for Improved Generative Accuracy

Recent advances in semi-supervised learning with deep generative models ...
01/26/2021

Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification

Semi-supervised learning through deep generative models and multi-lingua...
02/03/2019

Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning

Predicting bioactivity and physical properties of small molecules is a c...
01/07/2022

On robust risk-based active-learning algorithms for enhanced decision support

Classification models are a fundamental component of physical-asset mana...
06/12/2017

SEVEN: Deep Semi-supervised Verification Networks

Verification determines whether two samples belong to the same class or ...
09/03/2015

Semi-described and semi-supervised learning with Gaussian processes

Propagating input uncertainty through non-linear Gaussian process (GP) m...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.