Research map / Probabilistic and scientific modeling / Causal discovery
Efficient Ensemble Conditional Independence Test Framework for Causal Discovery
Zhengkang Guan, Kun Kuang
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 |
|---|---|---|---|
| wrap KCIT in the ensemble framework | KCIT · Flow-Cytometry dataset A | F1-score: 0.624 -> 0.695 | Improved |
| wrap LPCIT in the ensemble framework | LPCIT · Flow-Cytometry dataset A | F1-score: 0.691 -> 0.741 | Improved |
| wrap CMIknn in the ensemble framework | CMIknn · Flow-Cytometry dataset A | F1-score: 0.779 -> 0.756 | Hurt |
| wrap CCIT in the ensemble framework | CCIT · Flow-Cytometry dataset A | precision: 0.520 -> 0.618 | Improved |
| wrap RCIT in the ensemble (alpha=2.00) | RCIT · simulation n=1200, normal Z, df=4 | test power: 0.845 -> 0.906 | Improved |
| wrap RCIT in the ensemble (alpha=2.00) | RCIT · simulation n=1200, normal Z, df=2 | test power: 0.548 -> 0.609 | Improved |
| wrap FisherZ in the ensemble (alpha=1.75) | FisherZ · simulation n=1200, normal Z, df=4 | test power: 0.695 -> 0.766 | Improved |
| wrap CMIknn in the ensemble | CMIknn · simulation n=1200, normal Z, df=4 | test power: 0.990 -> 0.994 | No clear effect |
| wrap CCIT in the ensemble (alpha=1.75) | CCIT · simulation n=1200, normal Z, df=4 | Type I error: 0.450 -> 0.336 | Improved |
| wrap CCIT in the ensemble (alpha=1.75) | CCIT · simulation n=1200, normal Z, df=4 | test power: 0.896 -> 0.856 | Hurt |
| choose alpha=2.00 instead of 1.75 (ablation) | E-RCIT · simulation n=1200, normal Z, df=4 | test power: 0.891 -> 0.906 | Improved |
| choose alpha=2.00 instead of 1.75 (ablation) | E-FisherZ · simulation n=1200, normal Z, df=4 | test power: 0.766 -> 0.719 | Hurt |
Closest papers by meaning
- PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data (NeurIPS 2026 · similarity 0.91)
- On the sample complexity of conditional independence testing with Von Mises estimator with application to causal discovery (ICML 2024 · similarity 0.90)
- Causal Discovery via Conditional Independence Testing with Proxy Variables (ICML 2024 · similarity 0.90)
- Foundations of Testing for Finite-Sample Causal Discovery (ICML 2024 · similarity 0.88)
- Differentiable Constraint-Based Causal Discovery (NeurIPS 2025 · similarity 0.88)
- Causal Discovery with Fewer Conditional Independence Tests (ICML 2024 · similarity 0.88)
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.
