AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Disentangling Learning Representations with Density Estimation

Eric Yeats, Frank Y Liu, Hai Li

ICLR 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Tractable probabilistic models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add positive disentanglement regularization (λ > 0) (ablation)GCAE · dSpritesMIG: ~0.03 -> ~0.35Improved
Add positive disentanglement regularization (λ > 0) (ablation)GCAE · dSpritesFactorScore: ~0.47 -> ~0.6Improved
Add positive disentanglement regularization (λ > 0) (ablation)GCAE · dSpritesDCI Disentanglement: ~0.03 -> ~0.45Improved
Add positive disentanglement regularization (λ > 0) (ablation)GCAE · dSpritesSAP: ~0.08 -> ~0.37Improved
Use σ={0.2, 0.3} rather than σ=0.1 (ablation)GCAE · dSpritesdisentanglement scoresImproved
Use σ={0.2, 0.3} rather than σ=0.1 (ablation)GCAE · Beamsynthesisdisentanglement scoresImproved
Increase latent dimension from m=10 to m=20 (ablation)GCAE · dSpritesaverage disentanglement scoresNo clear effect
Increase latent dimension from m=10 to m=20 (ablation)FactorVAE · dSpritesdisentanglement scoresHurt
Use Excess Entropy Power loss (LEEP) instead of direct gradient descent on LSI (ablation)GCAE · disentanglement experimentsMIG stabilityImproved
Increase λ and σ (ablation)GCAE · Beamsynthesis and dSpritesMSE reconstruction errorHurt
Increase λ and σ (ablation)GCAE · Beamsynthesis and dSpritesLSIImproved
Use GCAE rather than FactorVAEdisentanglement methods · dSprites, m=20 versus m=10robustness to latent dimensionImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy