AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Temporally Disentangled Representation Learning under Unknown Nonstationarity

Xiangchen Song, Weiran Yao, Yewen Fan, Xinshuai Dong, Guangyi Chen, Juan Carlos Niebles, Eric Xing, Kun Zhang

NeurIPS 2023 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 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
use NCTRL instead of TDRLNCTRL · Synthetic Dataset AMCC: 83.99 -> 98.85Improved
use NCTRL instead of TDRLNCTRL · Synthetic Dataset BMCC: 72.02 -> 99.01Improved
model unknown nonstationarity with Markov domain indices plus time-delayed causal links instead of HMNLICA (no time-delayed relations)NCTRL · Synthetic averageMCC: 58.54 -> 98.93Improved
use NCTRL instead of TDRL on CartPoleNCTRL · Modified CartPoleMCC: 85.26 -> 96.06Improved
use NCTRL instead of SKD (disentanglement without identifiability) on CartPoleNCTRL · Modified CartPoleMCC: 73.24 -> 96.06Improved
i-VAE moves from simple to complex nonlinear mixing (A to B)i-VAE · Synthetic datasetsMCC: 89.74 -> 44.50Hurt
TDRL moves from simple to complex nonlinear mixing (A to B)TDRL · Synthetic datasetsMCC: 83.99 -> 72.02Hurt
NCTRL moves from simple to complex nonlinear mixing (A to B)NCTRL · Synthetic datasetsMCC: 98.85 -> 99.01No clear effect
use NCTRL on CartPole instead of synthetic data for c_t inferenceNCTRL · c_t accuracyaccuracy: 89.96 -> 79.23Hurt
use NCTRL on CartPole instead of synthetic data for A estimationNCTRL · MSE estimating AMSE: 1.01 $\times 10^{-3}$ -> 5.01 $\times 10^{-2}$Hurt

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