Regularizing Generative Models Using Knowledge of Feature Dependence

02/06/2019
by   Naoya Takeishi, et al.
0

Generative modeling is a fundamental problem in machine learning with many potential applications. Efficient learning of generative models requires available prior knowledge to be exploited as much as possible. In this paper, we propose a method to exploit prior knowledge of relative dependence between features for learning generative models. Such knowledge is available, for example, when side-information on features is present. We incorporate the prior knowledge by forcing marginals of the learned generative model to follow a prescribed relative feature dependence. To this end, we formulate a regularization term using a kernel-based dependence criterion. The proposed method can be incorporated straightforwardly into many optimization-based learning schemes of generative models, including variational autoencoders and generative adversarial networks. We show the effectiveness of the proposed method in experiments with multiple types of datasets and models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/21/2023

Matching-based Data Valuation for Generative Model

Data valuation is critical in machine learning, as it helps enhance mode...
research
11/16/2018

Generative Model for Material Experiments Based on Prior Knowledge and Attention Mechanism

Material irradiation experiment is dangerous and complex, thus it requir...
research
06/19/2019

Generative Restricted Kernel Machines

We propose a novel method for estimating generative models based on the ...
research
02/27/2021

Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilation

Using generative models from the machine learning literature to create a...
research
05/13/2020

Generative Models for Generic Light Field Reconstruction

Recently deep generative models have achieved impressive progress in mod...
research
09/08/2021

Self-explaining variational posterior distributions for Gaussian Process models

Bayesian methods have become a popular way to incorporate prior knowledg...
research
09/29/2019

Natural representation of composite data with replicated autoencoders

Generative processes in biology and other fields often produce data that...

Please sign up or login with your details

Forgot password? Click here to reset