Disentangling factors of variation using few labels

Locatello F, Tschannen M, Bauer S, Rätsch G, Schölkopf B, Bachem O. 2019. Disentangling factors of variation using few labels. 8th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.

Download (ext.)
Conference Paper | Published | English

Scopus indexed
Author
Locatello, FrancescoISTA ; Tschannen, Michael; Bauer, Stefan; Rätsch, Gunnar; Schölkopf, Bernhard; Bachem, Olivier
Department
Abstract
Learning disentangled representations is considered a cornerstone problem in representation learning. Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to consistently learn disentangled representations. However, in many practical settings, one might have access to a limited amount of supervision, for example through manual labeling of (some) factors of variation in a few training examples. In this paper, we investigate the impact of such supervision on state-of-the-art disentanglement methods and perform a large scale study, training over 52000 models under well-defined and reproducible experimental conditions. We observe that a small number of labeled examples (0.01--0.5\% of the data set), with potentially imprecise and incomplete labels, is sufficient to perform model selection on state-of-the-art unsupervised models. Further, we investigate the benefit of incorporating supervision into the training process. Overall, we empirically validate that with little and imprecise supervision it is possible to reliably learn disentangled representations.
Publishing Year
Date Published
2019-12-20
Proceedings Title
8th International Conference on Learning Representations
Conference
ICLR: International Conference on Learning Representations
Conference Location
Virtual
Conference Date
2020-04-26 – 2020-05-01
IST-REx-ID

Cite this

Locatello F, Tschannen M, Bauer S, Rätsch G, Schölkopf B, Bachem O. Disentangling factors of variation using few labels. In: 8th International Conference on Learning Representations. ; 2019.
Locatello, F., Tschannen, M., Bauer, S., Rätsch, G., Schölkopf, B., & Bachem, O. (2019). Disentangling factors of variation using few labels. In 8th International Conference on Learning Representations. Virtual.
Locatello, Francesco, Michael Tschannen, Stefan Bauer, Gunnar Rätsch, Bernhard Schölkopf, and Olivier Bachem. “Disentangling Factors of Variation Using Few Labels.” In 8th International Conference on Learning Representations, 2019.
F. Locatello, M. Tschannen, S. Bauer, G. Rätsch, B. Schölkopf, and O. Bachem, “Disentangling factors of variation using few labels,” in 8th International Conference on Learning Representations, Virtual, 2019.
Locatello F, Tschannen M, Bauer S, Rätsch G, Schölkopf B, Bachem O. 2019. Disentangling factors of variation using few labels. 8th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.
Locatello, Francesco, et al. “Disentangling Factors of Variation Using Few Labels.” 8th International Conference on Learning Representations, 2019.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data ISTA Research Explorer

Sources

arXiv 1905.01258

Search this title in

Google Scholar