Disentangled VAE Representations for Multi-Aspect and Missing Data

06/24/2018
by   Samuel K. Ainsworth, et al.
0

Many problems in machine learning and related application areas are fundamentally variants of conditional modeling and sampling across multi-aspect data, either multi-view, multi-modal, or simply multi-group. For example, sampling from the distribution of English sentences conditioned on a given French sentence or sampling audio waveforms conditioned on a given piece of text. Central to many of these problems is the issue of missing data: we can observe many English, French, or German sentences individually but only occasionally do we have data for a sentence pair. Motivated by these applications and inspired by recent progress in variational autoencoders for grouped data, we develop factVAE, a deep generative model capable of handling multi-aspect data, robust to missing observations, and with a prior that encourages disentanglement between the groups and the latent dimensions. The effectiveness of factVAE is demonstrated on a variety of rich real-world datasets, including motion capture poses and pictures of faces captured from varying poses and perspectives.

READ FULL TEXT

page 6

page 8

research
06/23/2020

Learning Disentangled Representations of Video with Missing Data

Missing data poses significant challenges while learning representations...
research
01/16/2022

Reconstruction of Incomplete Wildfire Data using Deep Generative Models

We present our submission to the Extreme Value Analysis 2021 Data Challe...
research
06/09/2020

VAEs in the Presence of Missing Data

Real world datasets often contain entries with missing elements e.g. in ...
research
08/17/2023

Conditional Sampling of Variational Autoencoders via Iterated Approximate Ancestral Sampling

Conditional sampling of variational autoencoders (VAEs) is needed in var...
research
09/25/2019

Multi-modal segmentation with missing MR sequences using pre-trained fusion networks

Missing data is a common problem in machine learning and in retrospectiv...
research
08/09/2023

AspectMMKG: A Multi-modal Knowledge Graph with Aspect-aware Entities

Multi-modal knowledge graphs (MMKGs) combine different modal data (e.g.,...
research
01/04/2023

Text sampling strategies for predicting missing bibliographic links

The paper proposes various strategies for sampling text data when perfor...

Please sign up or login with your details

Forgot password? Click here to reset