Weakly Supervised Disentanglement with Guarantees
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.
Code (1)
Tasks
DisentanglementSimilar Papers 제목 키워드 기반
Weakly Supervised Disentanglement by Pairwise Similarities
Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of in…
DisentanglementSW-VAE: Weakly Supervised Learn Disentangled Representation Via Latent Factor Swapping
Representation disentanglement is an important goal of representation learning that benefits various downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been …
DisentanglementRepresentation LearningSCADI: Self-supervised Causal Disentanglement in Latent Variable Models
Causal disentanglement has great potential for capturing complex situations. However, there is a lack of practical and efficient approaches. It is already known that most unsupervised disentangling methods are unable to …
DisentanglementPseudo LabelDisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing
Face parsing aims to segment facial images into key components such as eyes, lips, and eyebrows. While existing methods rely on dense pixel-level annotations, such annotations are expensive and labor-intensive to obtain.…
Semantic SegmentationFace ParsingOdd-One-Out Representation Learning
The effective application of representation learning to real-world problems requires both techniques for learning useful representations, and also robust ways to evaluate properties of representations. Recent work in dis…
DisentanglementMetric LearningModel SelectionOdd One Out+2