Research map / Probabilistic and scientific modeling / Causal discovery
Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use GIN instead of LSTC for latent-cluster discovery | GIN algorithm · Synthetic Cases 2 and 4, N=500 and 1000 | Latent omission: Case 2, N=500: 0.20(4) -> 0.10(2); N=1000: 0.15(3) -> 0.05(1). Case 4, N=500: 0.40(6) -> 0.13(4); N=1000: 0.26(6) -> 0.1 | Helped |
| Use GIN instead of LSTC for latent-cluster discovery | GIN algorithm · Synthetic Cases 1 and 3, N=500 and 1000 | Latent omission: Case 1: 0.00(0) vs 0.00(0) at both sample sizes; Case 3, N=500: 0.20(3) vs 0.20(3); N=1000: 0.06(2) vs 0.13(2). | Mixed |
| Use GIN instead of LSTC for latent-cluster discovery | GIN algorithm · Synthetic Case 4, N=2000 | Latent omission: 0.32(6) -> 0.03(1) | Helped |
| Use GIN instead of FOFC for latent-cluster discovery | GIN algorithm · Synthetic Cases 1, 2, 3, and 4, N=2000 | Latent omission: Case 1: 1.00(10) -> 0.00(0); Case 2: 1.00(10) -> 0.00(0); Case 3: 0.50(10) -> 0.00(0); Case 4: 1.00(10) -> 0.03(1). | Helped |
| Use GIN instead of BPC for latent-cluster discovery | GIN algorithm · Synthetic Cases 1, 2, and 4, N=2000 | Latent omission: Case 1: 0.50(10) -> 0.00(0); Case 2: 0.50(10) -> 0.00(0); Case 4: 0.70(10) -> 0.03(1). | Helped |
| Increase sample size from N=500 to N=2000 | GIN algorithm · Synthetic Case 4 | Latent omission: 0.13(4) -> 0.03(1) | Helped |
| Use GIN instead of LSTC for causal-order learning | GIN algorithm · Synthetic Cases 1–4 | correct-ordering rate | Helped |
Closest papers by meaning
- Differentiable Causal Discovery for Latent Hierarchical Causal Models (ICLR 2025 · similarity 0.91)
- Identification of Causal Structure with Latent Variables Based on Higher Order Cumulants (AAAI 2024 · similarity 0.91)
- Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations (ICML 2025 · similarity 0.89)
- Learning Mixtures of Unknown Causal Interventions (NeurIPS 2024 · similarity 0.89)
- Causal Effect Identification in LiNGAM Models with Latent Confounders (ICML 2024 · similarity 0.89)
- Learning Discrete Latent Variable Structures with Tensor Rank Conditions (NeurIPS 2024 · similarity 0.89)
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.