Are disentangled representations helpful for abstract visual reasoning?

Sjoerd van Steenkiste, Francesco Locatello, Jürgen Schmidhuber, Olivier Bachem

Research output: Chapter in Book/Report/Conference proceedingConference contribution

91 Scopus citations

Abstract

A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is useful in learning to solve many real-world down-stream tasks, there is little empirical evidence that supports this claim. In this paper, we conduct a large-scale study that investigates whether disentangled representations are more suitable for abstract reasoning tasks. Using two new tasks similar to Raven's Progressive Matrices, we evaluate the usefulness of the representations learned by 360 state-of-the-art unsupervised disentanglement models. Based on these representations, we train 3600 abstract reasoning models and observe that disentangled representations do in fact lead to better down-stream performance. In particular, they enable quicker learning using fewer samples.
Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint

Dive into the research topics of 'Are disentangled representations helpful for abstract visual reasoning?'. Together they form a unique fingerprint.

Cite this