Research map / Probabilistic and scientific modeling / Causal discovery
Bivariate Causal Discovery for Categorical Data via Classification with Optimal Label Permutation
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 |
|---|---|---|---|
| learn the label ordering rather than fixing it at a potentially poor ordering (ablation) | COLP causal discovery · Synthetic Scenario 1, n=1,000 | causal identification accuracy: 0.17 -> 1 | Helped |
| fix the label ordering at Kendall's Tau 0.2 instead of 0 (ablation) | COLP causal discovery · Synthetic Scenario 1, n=1,000 | causal identification accuracy: 0.17 -> 0.33 | Helped |
| fix the label ordering at Kendall's Tau 0.4 instead of 0.2 (ablation) | COLP causal discovery · Synthetic Scenario 1, n=1,000 | causal identification accuracy: 0.33 -> 0.61 | Helped |
| fix the label ordering at Kendall's Tau 0.6 instead of 0.4 (ablation) | COLP causal discovery · Synthetic Scenario 1, n=1,000 | causal identification accuracy: 0.61 -> 0.82 | Helped |
| fix the label ordering at Kendall's Tau 0.8 instead of 0.6 (ablation) | COLP causal discovery · Synthetic Scenario 1, n=1,000 | causal identification accuracy: 0.82 -> 0.96 | Helped |
| fix the label ordering at Kendall's Tau 1 instead of 0.8 (ablation) | COLP causal discovery · Synthetic Scenario 1, n=1,000 | causal identification accuracy: 0.96 -> 1 | Helped |
| use COLP rather than HCR | causal direction discovery · Categorical Cause-Effect Pairs | causal direction accuracy: 70% vs 61% | Helped |
| use COLP rather than ECI | causal direction discovery · Categorical Cause-Effect Pairs | causal direction accuracy: 70% vs 52% | Helped |
| increase the category count from 3 to 12 | COLP causal discovery · Synthetic Scenario 1, n=1,000 | causal identification accuracy: 0.86 at 3; 0.88 at 12 | No clear effect |
Closest papers by meaning
- Bivariate Causal Discovery using Bayesian Model Selection (ICML 2024 · similarity 0.87)
- Differentiable Causal Discovery for Latent Hierarchical Causal Models (ICLR 2025 · similarity 0.86)
- A Meta-Learning Approach to Bayesian Causal Discovery (ICLR 2025 · similarity 0.86)
- Continuous Bayesian Model Selection for Multivariate Causal Discovery (ICML 2025 · similarity 0.86)
- Causal Discovery via Conditional Independence Testing with Proxy Variables (ICML 2024 · similarity 0.85)
- Discovering Mixtures of Structural Causal Models from Time Series Data (ICML 2024 · similarity 0.85)
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.