Linear Disentangled Representations and Unsupervised Action Estimation
This work addresses the challenge of learning disentangled representations without labeled data, which is incremental but improves upon prior supervised approaches in representation learning.
The paper demonstrates that standard VAE models lack linear disentangled representations, requiring loss landscape modifications to induce them, and proposes an unsupervised method to learn these representations from action sequences without labels, successfully learning 4 independent symmetries from pixels.
Disentangled representation learning has seen a surge in interest over recent times, generally focusing on new models which optimise one of many disparate disentanglement metrics. Symmetry Based Disentangled Representation learning introduced a robust mathematical framework that defined precisely what is meant by a "linear disentangled representation". This framework determined that such representations would depend on a particular decomposition of the symmetry group acting on the data, showing that actions would manifest through irreducible group representations acting on independent representational subspaces. Caselles-Dupre et al [2019] subsequently proposed the first model to induce and demonstrate a linear disentangled representation in a VAE model. In this work we empirically show that linear disentangled representations are not generally present in standard VAE models and that they instead require altering the loss landscape to induce them. We proceed to show that such representations are a desirable property with regard to classical disentanglement metrics. Finally we propose a method to induce irreducible representations which forgoes the need for labelled action sequences, as was required by prior work. We explore a number of properties of this method, including the ability to learn from action sequences without knowledge of intermediate states and robustness under visual noise. We also demonstrate that it can successfully learn 4 independent symmetries directly from pixels.