Recent advances in autoencoder-based representation learning


Michael Tschannen, Olivier Bachem, and Mario Lucic


Third workshop on Bayesian Deep Learning (NeurIPS 2018), 2018.

[BibTeX, LaTeX, and HTML Reference]


Learning useful representations with little or no supervision is a key challenge in artificial intelligence. We provide an in-depth review of recent advances in representation learning with a focus on autoencoder-based models. To organize these results we make use of meta-priors believed useful for downstream tasks, such as disentanglement and hierarchical organization of features. In particular, we un- cover three main mechanisms to enforce such properties, namely (i) regularizing the (approximate or aggregate) posterior distribution, (ii) factorizing the encoding and decoding distribution, or (iii) introducing a structured prior distribution. While there are some promising results, implicit or explicit supervision remains a key enabler and all current methods use strong inductive biases and modeling assumptions. Finally, we provide an analysis of autoencoder-based representation learning through the lens of rate-distortion theory and identify a clear tradeoff between the amount of prior knowledge available about the downstream tasks, and how useful the representation is for this task.


autoencoder, variational autoencoder, representation learning, disentanglement, rate-distortion tradeoff, unsupervised

Download this document:


Copyright Notice: © 2018 M. Tschannen, O. Bachem, and M. Lucic.

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.