Learning disentangled representations with the Wasserstein Autoencoder

Benoit Gaujac, Ilya Feige, David Barber

Keywords: generative modeling, disentangle learning, wasserstein autoencoder

Abstract: Disentangled representation learning has undoubtedly benefited from objective function surgery. However, a delicate balancing act of tuning is still required in order to trade off reconstruction fidelity versus disentanglement. Building on previous successes of penalizing the total correlation in the latent variables, we propose TCWAE (Total Correlation Wasserstein Autoencoder). Working in the WAE paradigm naturally enables the separation of the total-correlation term, thus providing disentanglement control over the learned representation, while offering more flexibility in the choice of reconstruction cost. We propose two variants using different KL estimators and perform extensive quantitative comparisons on data sets with known generative factors, showing competitive results relative to state-of-the-art techniques. We further study the trade off between disentanglement and reconstruction on more-difficult data sets with unknown generative factors, where we expect improved reconstructions due to the flexibility of the WAE paradigm.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: Improving the reconstruction-disentanglement trade off with the Wasserstein Autoencoder.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2010.03459/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=E1can8OJl