Semi-Supervised Learning with Variational Bayesian Inference and Maximum Uncertainty Regularization

12/03/2020
by   Kien Do, et al.
0

We propose two generic methods for improving semi-supervised learning (SSL). The first integrates weight perturbation (WP) into existing "consistency regularization" (CR) based methods. We implement WP by leveraging variational Bayesian inference (VBI). The second method proposes a novel consistency loss called "maximum uncertainty regularization" (MUR). While most consistency losses act on perturbations in the vicinity of each data point, MUR actively searches for "virtual" points situated beyond this region that cause the most uncertain class predictions. This allows MUR to impose smoothness on a wider area in the input-output manifold. Our experiments show clear improvements in classification errors of various CR based methods when they are combined with VBI or MUR or both.

READ FULL TEXT

page 7

page 14

page 15

page 16

research
08/18/2018

Tangent-Normal Adversarial Regularization for Semi-supervised Learning

The ever-increasing size of modern datasets combined with the difficulty...
research
11/13/2019

Adversarial Transformations for Semi-Supervised Learning

We propose a Regularization framework based on Adversarial Transformatio...
research
06/14/2018

Improving Consistency-Based Semi-Supervised Learning with Weight Averaging

Recent advances in deep unsupervised learning have renewed interest in s...
research
02/28/2021

A Survey on Deep Semi-supervised Learning

Deep semi-supervised learning is a fast-growing field with a range of pr...
research
11/23/2020

AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence

Semi-supervised learning (SSL) is a key approach toward more data-effici...
research
11/11/2022

Semi-supervised Variational Autoencoder for Regression: Application on Soft Sensors

We present the development of a semi-supervised regression method using ...
research
12/10/2021

Revisiting Consistency Regularization for Semi-Supervised Learning

Consistency regularization is one of the most widely-used techniques for...

Please sign up or login with your details

Forgot password? Click here to reset