DeepAI
Log In Sign Up

Unsupervised Disentangled Representation Learning with Analogical Relations

04/25/2018
by   Zejian Li, et al.
0

Learning the disentangled representation of interpretable generative factors of data is one of the foundations to allow artificial intelligence to think like people. In this paper, we propose the analogical training strategy for the unsupervised disentangled representation learning in generative models. The analogy is one of the typical cognitive processes, and our proposed strategy is based on the observation that sample pairs in which one is different from the other in one specific generative factor show the same analogical relation. Thus, the generator is trained to generate sample pairs from which a designed classifier can identify the underlying analogical relation. In addition, we propose a disentanglement metric called the subspace score, which is inspired by subspace learning methods and does not require supervised information. Experiments show that our proposed training strategy allows the generative models to find the disentangled factors, and that our methods can give competitive performances as compared with the state-of-the-art methods.

READ FULL TEXT

page 2

page 5

page 6

01/13/2020

High-Fidelity Synthesis with Disentangled Representation

Learning disentangled representation of data without supervision is an i...
02/22/2019

FAVAE: Sequence Disentanglement using Information Bottleneck Principle

We propose the factorized action variational autoencoder (FAVAE), a stat...
08/26/2020

Orientation-Disentangled Unsupervised Representation Learning for Computational Pathology

Unsupervised learning enables modeling complex images without the need f...
08/08/2022

Interpretable Disentangled Parametrization of Measured BRDF with β-VAE

Finding a low dimensional parametric representation of measured BRDF rem...
10/04/2022

Evaluating Disentanglement in Generative Models Without Knowledge of Latent Factors

Probabilistic generative models provide a flexible and systematic framew...
02/02/2021

Evaluating the Interpretability of Generative Models by Interactive Reconstruction

For machine learning models to be most useful in numerous sociotechnical...
03/02/2021

Learning disentangled representations via product manifold projection

We propose a novel approach to disentangle the generative factors of var...

Code Repositories