Multimodal Variational Autoencoders for Semi-Supervised Learning: In Defense of Product-of-Experts

by   Svetlana Kutuzova, et al.

Multimodal generative models should be able to learn a meaningful latent representation that enables a coherent joint generation of all modalities (e.g., images and text). Many applications also require the ability to accurately sample modalities conditioned on observations of a subset of the modalities. Often not all modalities may be observed for all training data points, so semi-supervised learning should be possible. In this study, we evaluate a family of product-of-experts (PoE) based variational autoencoders that have these desired properties. We include a novel PoE based architecture and training procedure. An empirical evaluation shows that the PoE based models can outperform an additive mixture-of-experts (MoE) approach. Our experiments support the intuition that PoE models are more suited for a conjunctive combination of modalities while MoEs are more suited for a disjunctive fusion.


page 5

page 9

page 14

page 15


Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models

Learning generative models that span multiple data modalities, such as v...

Multimodal Generative Models for Scalable Weakly-Supervised Learning

Multiple modalities often co-occur when describing natural phenomena. Le...

Mixture-of-experts VAEs can disregard variation in surjective multimodal data

Machine learning systems are often deployed in domains that entail data ...

An empirical study of domain-agnostic semi-supervised learning via energy-based models: joint-training and pre-training

A class of recent semi-supervised learning (SSL) methods heavily rely on...

Variational Autoencoders for Generative Modelling of Water Cherenkov Detectors

Matter-antimatter asymmetry is one of the major unsolved problems in phy...

Benchmarking Multimodal Variational Autoencoders: GeBiD Dataset and Toolkit

Multimodal Variational Autoencoders (VAEs) have been a subject of intens...

Learning Multimodal VAEs through Mutual Supervision

Multimodal VAEs seek to model the joint distribution over heterogeneous ...