Quantifying and Learning Linear Symmetry-Based Disentanglement

Abstract

The definition of Linear Symmetry-Based Disentanglement (LSBD) formalizes the notion of linearly disentangled representations, but there is currently no metric to quantify LSBD. Such a metric is crucial to evaluate LSBD methods and to compare to previous understandings of disentanglement. We propose ${\mathcal{D}}_{\mathrm{LSBD}}$, a mathematically sound metric to quantify LSBD, and provide a practical implementation for $\mathrm{SO}(2)$ groups. Furthermore, from this metric we derive LSBD-VAE, a semi-supervised method to learn LSBD representations. We demonstrate the utility of our metric by showing that (1) common VAE-based disentanglement methods don't learn LSBD representations, (2) LSBD-VAE as well as other recent methods can learn LSBD representations, needing only limited supervision on transformations, and (3) various desirable properties expressed by existing disentanglement metrics are also achieved by LSBD representations.

The Thirty-ninth International Conference on Machine Learning (ICML 2022)

References in corpus (8)

• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• Disentangling by Factorising
• Towards a Definition of Disentangled Representations
• Understanding disentangling in $\beta$-VAE
• Learning Deep Disentangled Embeddings with the F-Statistic Loss
• 3D ShapeNets: A Deep Representation for Volumetric Shapes
• Diffusion Variational Autoencoders
• Learning Group Structure and Disentangled Representations of Dynamical Environments