Unsupervised Disentanglement with Tensor Product Representations on the TorusDownload PDF

29 Sept 2021, 00:31 (edited 14 Mar 2022)ICLR 2022 PosterReaders: Everyone
  • Keywords: Variational Auto-Encoder, Disentanglement Learning
  • Abstract: The current methods for learning representations with auto-encoders almost exclusively employ vectors as the latent representations. In this work, we propose to employ a tensor product structure for this purpose. This way, the obtained representations are naturally disentangled. In contrast to the conventional variations methods, which are targeted toward normally distributed features, the latent space in our representation is distributed uniformly over a set of unit circles. We argue that the torus structure of the latent space captures the generative factors effectively. We employ recent tools for measuring unsupervised disentanglement, and in an extensive set of experiments demonstrate the advantage of our method in terms of disentanglement, completeness, and informativeness. The code for our proposed method is available at https://github.com/rotmanmi/Unsupervised-Disentanglement-Torus.
  • One-sentence Summary: Decomposition of a latent space on a torus leads to a disentangled representation
  • Supplementary Material: zip
26 Replies