The Conceptual VAE

TL;DR

The paper introduces the Conceptual VAE, a model that learns interpretable, factored conceptual representations from images and labels, closely integrating language and concepts within a variational autoencoder framework.

Contribution

It presents a novel VAE-based model that incorporates language, learns interpretable concepts, and relates to conceptual spaces theory, improving on prior models like Beta-VAE.

Findings

Successfully learned interpretable concepts from images and labels

Can be used as a concept classifier with fewer labels

Theoretically connected to Gardenfors' conceptual spaces

Abstract

In this report we present a new model of concepts, based on the framework of variational autoencoders, which is designed to have attractive properties such as factored conceptual domains, and at the same time be learnable from data. The model is inspired by, and closely related to, the Beta-VAE model of concepts, but is designed to be more closely connected with language, so that the names of concepts form part of the graphical model. We provide evidence that our model -- which we call the Conceptual VAE -- is able to learn interpretable conceptual representations from simple images of coloured shapes together with the corresponding concept labels. We also show how the model can be used as a concept classifier, and how it can be adapted to learn from fewer labels per instance. Finally, we formally relate our model to Gardenfors' theory of conceptual spaces, showing how the Gaussians we use to represent concepts can be formalised in terms of "fuzzy concepts" in such a space.