Research map / Probabilistic and scientific modeling / Causal discovery
Novel Ordering-Based Approaches for Causal Structure Learning in the Presence of Unobserved Variables
Ehsan Mokhtarian, Mohmmadsadegh Khorasani, Jalal Etesami, Negar Kiyavash
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 |
|---|---|---|---|
| Use ROL_HC instead of L-MARVEL | MAG learning · Insurance | F1-score: 0.87 -> 0.89 | Improved |
| Use ROL_HC instead of L-MARVEL | MAG learning · Water | F1-score: 0.78 -> 0.86 | Improved |
| Use ROL_HC instead of L-MARVEL | MAG learning · Hailfinder | SHD: 12.8 -> 13.9 | Hurt |
| Use ROL_HC instead of L-MARVEL | MAG learning · Carpo | F1-score: 0.99 -> 1.00 | Improved |
| Use ROL_HC instead of L-MARVEL | MAG learning · Hepar2 | SHD: 12.3 -> 7.6 | Improved |
| Use ROL_HC instead of L-MARVEL | MAG learning · Arth150 | SHD: 21.2 -> 19.3 | Improved |
| Use ROL_HC instead of ROL_PG | MAG learning · Water | SHD: 35.3 -> 18.3 | Improved |
| Use ROL_VI instead of ROL_HC | small DAG learning · Survey | F1: 0.98 -> 1 | Improved |
| Use ROL_VI instead of ROL_HC | small DAG learning · Sachs | SHD: 1.6 -> 1 | Improved |
| Use ROL_VI instead of ROL_HC | small DAG learning · Earthquake | F1: 0.96 -> 0.96 | No clear effect |
| Use ROL_VI instead of ROL_HC | small DAG learning · Asia | SHD: 0.4 -> 0.4 | No clear effect |
| Initialize ROL_HC using recursive removable-variable discovery rather than a random permutation (ablation) | ROL_HC · experiments | accuracy | Improved |
Closest papers by meaning
- Learning Structural Causal Models from Ordering: Identifiable Flow Models (AAAI 2025 · similarity 0.89)
- A Fixed-Point Approach for Causal Generative Modeling (ICML 2024 · similarity 0.88)
- Differentiable Structure Learning with Partial Orders (NeurIPS 2024 · similarity 0.88)
- Standardizing Structural Causal Models (ICLR 2025 · similarity 0.87)
- Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery (NeurIPS 2025 · similarity 0.87)
- Differentiable Structure Learning with Ancestral Constraints (ICML 2025 · similarity 0.87)
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.
