DEFT: distilling entangled factors by preventing information diffusion

DOI10.1007/S10994-022-06134-7MaRDI QIDQ2163258zbMATH OpenOpenAlexFDO

Authors Jiantao, Lin Wang, Bo Yang, Fanqi Li, Chunxiuzi Liu, Jin Zhou

Publication date 10 August 2022

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2102.03986

zbMATH Keywords

disentanglementinformation bottleneckinformation diffusionrepresentation learningVAE

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• A sober look at the unsupervised learning of disentangled representations and their evaluation
• Disentangled Representation Learning and Generation With Manifold Optimization
• Emergence of invariance and disentanglement in deep representations
• The deterministic information bottleneck
• Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints

Cites work

• Independent component analysis, a new concept?
• Information Theoretical Analysis of Multivariate Correlation
• Semi-supervised learning in causal and anticausal settings

Cited in

(1)

• A sober look at the unsupervised learning of disentangled representations and their evaluation

Describes a project that uses

Uses Software

• InfoGAN
• DARLA
• dSprites
• GitHub

This page was built for publication: DEFT: distilling entangled factors by preventing information diffusion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2163258)