AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Temporally Disentangled Representation Learning

Weiran Yao, Guangyi Chen, Kun Zhang

NeurIPS 2022 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 8 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 history and nonstationarity jointly (vs betaVAE)Ours · Changing dynamics simulationMCC: 0.523 -> 0.958Improved
nonparametric modular transition prior vs LEAPOurs · Modular dynamics simulationMCC: 0.657 -> 0.993Improved
model history vs KVAE under fixed dynamicsOurs · Fixed dynamics simulationMCC: 0.832 -> 0.954Improved
model changing dynamics vs KVAE under changing dynamicsOurs · Changing dynamics simulationMCC: 0.711 -> 0.958Improved
model changing dynamics vs DVBF under modular shiftOurs · Modular dynamics simulationMCC: 0.678 -> 0.993Improved
independent-source assumption (SlowVAE) vs OursOurs · Fixed dynamics simulationMCC: 0.954 -> 0.411Hurt
changing dynamics instead of fixed dynamics for OursOurs · SimulationMCC: 0.954 -> 0.958No clear effect
distribution shift for TCL from changing to modularTCL · SimulationMCC: 0.399 -> 0.297Hurt

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