Robust Ordinal VAE: Employing Noisy Pairwise Comparisons for Disentanglement

Recent work by Locatello et al. (2018) has shown that an inductive bias is required to disentangle factors of interest in Variational Autoencoder (VAE). Motivated by a real-world problem, we propose a setting where such bias is introduced by providing pairwise ordinal comparisons between instances,...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Chen, Junxiang, Kayhan Batmanghelich
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 14.10.2019
Subjects
Bias
Illnesses
Random variables
Robustness
Trustworthiness
Online AccessGet full text

Cover

More Information
Summary:Recent work by Locatello et al. (2018) has shown that an inductive bias is required to disentangle factors of interest in Variational Autoencoder (VAE). Motivated by a real-world problem, we propose a setting where such bias is introduced by providing pairwise ordinal comparisons between instances, based on the desired factor to be disentangled. For example, a doctor compares pairs of patients based on the level of severity of their illnesses, and the desired factor is a quantitive level of the disease severity. In a real-world application, the pairwise comparisons are usually noisy. Our method, Robust Ordinal VAE (ROVAE), incorporates the noisy pairwise ordinal comparisons in the disentanglement task. We introduce non-negative random variables in ROVAE, such that it can automatically determine whether each pairwise ordinal comparison is trustworthy and ignore the noisy comparisons. Experimental results demonstrate that ROVAE outperforms existing methods and is more robust to noisy pairwise comparisons in both benchmark datasets and a real-world application.
ISSN:2331-8422