Disentangling by Factorising

Hyunjik Kim, Andriy Mnih
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:2649-2658, 2018.

Abstract

We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon beta-VAE by providing a better trade-off between disentanglement and reconstruction quality and being more robust to the number of training iterations. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

Cite this Paper

BibTeX
@InProceedings{pmlr-v80-kim18b, title = {Disentangling by Factorising}, author = {Kim, Hyunjik and Mnih, Andriy}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {2649--2658}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/kim18b/kim18b.pdf}, url = {https://proceedings.mlr.press/v80/kim18b.html}, abstract = {We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon beta-VAE by providing a better trade-off between disentanglement and reconstruction quality and being more robust to the number of training iterations. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.} }
Endnote
%0 Conference Paper %T Disentangling by Factorising %A Hyunjik Kim %A Andriy Mnih %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-kim18b %I PMLR %P 2649--2658 %U https://proceedings.mlr.press/v80/kim18b.html %V 80 %X We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon beta-VAE by providing a better trade-off between disentanglement and reconstruction quality and being more robust to the number of training iterations. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.
APA
Kim, H. & Mnih, A.. (2018). Disentangling by Factorising. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:2649-2658 Available from https://proceedings.mlr.press/v80/kim18b.html.

Related Material