Weakly Supervised Disentanglement with Guarantees

10/22/2019
by   Rui Shu, et al.
12

Learning disentangled representations that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning. Recently, concerns about the viability of learning disentangled representations in a purely unsupervised manner has spurred a shift toward the incorporation of weak supervision. However, there is currently no formalism that identifies when and how weak supervision will guarantee disentanglement. To address this issue, we provide a theoretical framework to assist in analyzing the disentanglement guarantees (or lack thereof) conferred by weak supervision when coupled with learning algorithms based on distribution matching. We empirically verify the guarantees and limitations of several weak supervision methods (restricted labeling, match-pairing, and rank-pairing), demonstrating the predictive power and usefulness of our theoretical framework.

READ FULL TEXT

page 8

page 14

page 16

page 23

page 24

page 25

page 26

page 27

research
09/15/2020

Constrained Labeling for Weakly Supervised Learning

Curation of large fully supervised datasets has become one of the major ...
research
09/12/2022

Modular Representations for Weak Disentanglement

The recently introduced weakly disentangled representations proposed to ...
research
06/03/2019

Weakly Supervised Disentanglement by Pairwise Similarities

Recently, researches related to unsupervised disentanglement learning wi...
research
04/18/2023

Generalized Weak Supervision for Neural Information Retrieval

Neural ranking models (NRMs) have demonstrated effective performance in ...
research
02/07/2020

Weakly-Supervised Disentanglement Without Compromises

Intelligent agents should be able to learn useful representations by obs...
research
11/11/2020

Quantifying and Learning Disentangled Representations with Limited Supervision

Learning low-dimensional representations that disentangle the underlying...
research
02/28/2023

Representation Disentaglement via Regularization by Identification

This work focuses on the problem of learning disentangled representation...

Please sign up or login with your details

Forgot password? Click here to reset