A Heuristic for Unsupervised Model Selection for Variational Disentangled Representation Learning

05/29/2019
by   Sunny Duan, et al.
0

Disentangled representations have recently been shown to improve data efficiency, generalisation, robustness and interpretability in simple supervised and reinforcement learning tasks. To extend such results to more complex domains, it is important to address a major shortcoming of the current state of the art unsupervised disentangling approaches -- high convergence variance, whereby different disentanglement quality may be achieved by the same model depending on its initial state. The existing model selection methods require access to the ground truth attribute labels, which are not available for most datasets. Hence, the benefits of disentangled representations have not yet been fully explored in practical applications. This paper addresses this problem by introducing a simple yet robust and reliable method for unsupervised disentangled model selection. We show that our approach performs comparably to the existing supervised alternatives across 5400 models from six state of the art unsupervised disentangled representation learning model classes.

READ FULL TEXT

page 1

page 8

page 17

page 20

page 21

page 25

page 26

research
05/03/2019

Disentangling Factors of Variation Using Few Labels

Learning disentangled representations is considered a cornerstone proble...
research
12/14/2020

Odd-One-Out Representation Learning

The effective application of representation learning to real-world probl...
research
05/20/2020

Reducing Overlearning through Disentangled Representations by Suppressing Unknown Tasks

Existing deep learning approaches for learning visual features tend to o...
research
04/07/2021

Where and What? Examining Interpretable Disentangled Representations

Capturing interpretable variations has long been one of the goals in dis...
research
09/21/2020

Improving Robustness and Generality of NLP Models Using Disentangled Representations

Supervised neural networks, which first map an input x to a single repre...
research
07/21/2020

Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

We construct an unsupervised learning model that achieves nonlinear dise...
research
01/21/2021

Blocked and Hierarchical Disentangled Representation From Information Theory Perspective

We propose a novel and theoretical model, blocked and hierarchical varia...

Please sign up or login with your details

Forgot password? Click here to reset