Learning Disentangled Representations with Wasserstein Auto-Encoders

Paul K. Rubenstein, Bernhard Schoelkopf, Ilya Tolstikhin

Abstract: We apply Wasserstein auto-encoders (WAEs) to the problem of disentangled representation learning. We highlight the potential of WAEs with promising results on a benchmark disentanglement task.

Keywords: wasserstein auto-encoders, WAE, disentanglement

TL;DR: We apply Wasserstein Auto-encoders to the problem of disentangled representation learning