Skip to yearly menu bar Skip to main content


Poster

Isometric Quotient Variational Auto-Encoders for Structure-Preserving Representation Learning

In Huh · changwook jeong · Jae Myung Choe · YOUNGGU KIM · Daesin Kim

Great Hall & Hall B1+B2 (level 1) #542

Abstract: We study structure-preserving low-dimensional representation of a data manifold embedded in a high-dimensional observation space based on variational auto-encoders (VAEs). We approach this by decomposing the data manifold M as M=M/G×G, where G and M/G are a group of symmetry transformations and a quotient space of M up to G, respectively. From this perspective, we define the structure-preserving representation of such a manifold as a latent space Z which is isometrically isomorphic (i.e., distance-preserving) to the quotient space M/G rather M (i.e., symmetry-preserving). To this end, we propose a novel auto-encoding framework, named isometric quotient VAEs (IQVAEs), that can extract the quotient space from observations and learn the Riemannian isometry of the extracted quotient in an unsupervised manner. Empirical proof-of-concept experiments reveal that the proposed method can find a meaningful representation of the learned data and outperform other competitors for downstream tasks.

Chat is not available.