AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Weakly supervised causal representation learning

Johann Brehmer, Pim De Haan, Phillip Lippe, Taco Cohen

NeurIPS 2022 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 13 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
model causal structure (ILCM) instead of assuming independent factors (dVAE)weakly supervised VAE · 2D toy dataDCI disentanglement: 0.35 -> 0.99Improved
model causal structure (ILCM) instead of independent factors (dVAE)weakly supervised VAE · Causal3DIdentDCI disentanglement: 0.82 -> 0.99Improved
model causal structure (ILCM) instead of independent factors (dVAE)weakly supervised VAE · CausalCircuitDCI disentanglement: 0.34 -> 0.97Improved
ILCM representations versus dVAE representations for causal graph recoveryILCM-E · CausalCircuitSHD: 5.00 -> 0.00Improved
use ENCO versus heuristic algorithm for graph extraction (ablation)ILCM · Causal3DIdentSHD: 0.00 vs 0.17No clear effect
use implicit instead of explicit graph parameterization (ILCM vs ELCM) (ablation)latent causal model · simple datasetsoptimization robustnessImproved
make causal variables discrete instead of continuous (ablation)ILCM · CausalCircuit variantdisentanglementHurt
increase number of causal variables beyond about 10 (ablation)ILCM · synthetic linear SCMsdisentanglement and graph accuracyHurt

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