Research map / Probabilistic and scientific modeling / Causal discovery
Temporally Disentangled Representation Learning
Weiran Yao, Guangyi Chen, Kun Zhang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| model history and nonstationarity jointly (vs betaVAE) | Ours · Changing dynamics simulation | MCC: 0.523 -> 0.958 | Improved |
| nonparametric modular transition prior vs LEAP | Ours · Modular dynamics simulation | MCC: 0.657 -> 0.993 | Improved |
| model history vs KVAE under fixed dynamics | Ours · Fixed dynamics simulation | MCC: 0.832 -> 0.954 | Improved |
| model changing dynamics vs KVAE under changing dynamics | Ours · Changing dynamics simulation | MCC: 0.711 -> 0.958 | Improved |
| model changing dynamics vs DVBF under modular shift | Ours · Modular dynamics simulation | MCC: 0.678 -> 0.993 | Improved |
| independent-source assumption (SlowVAE) vs Ours | Ours · Fixed dynamics simulation | MCC: 0.954 -> 0.411 | Hurt |
| changing dynamics instead of fixed dynamics for Ours | Ours · Simulation | MCC: 0.954 -> 0.958 | No clear effect |
| distribution shift for TCL from changing to modular | TCL · Simulation | MCC: 0.399 -> 0.297 | Hurt |
Closest papers by meaning
- Identifiable Latent Polynomial Causal Models through the Lens of Change (ICLR 2024 · similarity 0.93)
- Identifiability Guarantees for Causal Disentanglement from Purely Observational Data (NeurIPS 2024 · similarity 0.93)
- Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity (NeurIPS 2024 · similarity 0.92)
- Causal Representation Learning Made Identifiable by Grouping of Observational Variables (ICML 2024 · similarity 0.92)
- Causal Temporal Representation Learning with Nonstationary Sparse Transition (NeurIPS 2024 · similarity 0.91)
- Disentangled Representation Learning in Non-Markovian Causal Systems (NeurIPS 2024 · similarity 0.91)
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.
