Research map / Probabilistic and scientific modeling / Causal discovery
Identifying Weight-Variant Latent Causal Models
Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton van den Hengel, Kun Zhang, Javen Qinfeng Shi
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 |
|---|---|---|---|
| replace Gaussian latent noise with Uniform noise (ablation) | SuaVE · Synthetic data | MPC: 0.95 -> 0.83 | Hurt |
| replace Gaussian latent noise with Laplace noise (ablation) | SuaVE · Synthetic data | MPC: 0.95 -> 0.83 | Hurt |
| replace Gaussian latent noise with Gamma noise (ablation) | SuaVE · Synthetic data | MPC: 0.95 -> 0.82 | Hurt |
| vary regularization hyper-parameters gamma1 and gamma2 (ablation) | SuaVE · Synthetic data | MPC | No clear effect |
| keep some causal weights unchanged across environments u (ablation) | SuaVE · Synthetic chain z1->z2->z3->z4 | MPC | Hurt |
| use iVAE instead of SuaVE on independent latents | SuaVE · Synthetic i.i.d. latents | MPC | No clear effect |
| use SuaVE instead of beta-VAE, VAE, CausalVAE and iVAE | latent causal variable recovery · Synthetic data, varying number of segments | MPC | Improved |
Closest papers by meaning
- Identifiable Latent Polynomial Causal Models through the Lens of Change (ICLR 2024 · similarity 0.94)
- Identifiability Guarantees for Causal Disentanglement from Purely Observational Data (NeurIPS 2024 · similarity 0.92)
- Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity (NeurIPS 2024 · similarity 0.91)
- Identifying General Mechanism Shifts in Linear Causal Representations (NeurIPS 2024 · similarity 0.91)
- Differentiable Causal Discovery for Latent Hierarchical Causal Models (ICLR 2025 · similarity 0.90)
- On the Identification of Temporal Causal Representation with Instantaneous Dependence (ICLR 2025 · similarity 0.90)
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.
