Recursive Disentanglement NetworkDownload PDF

29 Sept 2021, 00:32 (edited 16 Mar 2022)ICLR 2022 PosterReaders: Everyone
  • Keywords: disentanglement, representation learning, compositional
  • Abstract: Disentangled feature representation is essential for data-efficient learning. The feature space of deep models is inherently compositional. Existing $\beta$-VAE-based methods, which only apply disentanglement regularization to the resulting embedding space of deep models, cannot effectively regularize such compositional feature space, resulting in unsatisfactory disentangled results. In this paper, we formulate the compositional disentanglement learning problem from an information-theoretic perspective and propose a recursive disentanglement network (RecurD) that propagates regulatory inductive bias recursively across the compositional feature space during disentangled representation learning. Experimental studies demonstrate that RecurD outperforms $\beta$-VAE and several of its state-of-the-art variants on disentangled representation learning and enables more data-efficient downstream machine learning tasks.
  • One-sentence Summary: This paper has described a solution to the compositional disentangled representation learning problem.
28 Replies