Research map / Probabilistic and scientific modeling / Causal discovery
Structural Agnostic Modeling: Adversarial Learning of Causal Graphs
Diviyan Kalainathan, Olivier Goudet, Isabelle Guyon, David Lopez-Paz, Michèle Sebag
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 |
|---|---|---|---|
| add adversarial loss instead of MSE loss (ablation) | SAM · Synthetic 20-variable graphs (Global) | AUPR: 0.41 -> 0.57 | Improved |
| add non-linear mechanisms instead of linear ones (ablation) | SAM · Synthetic 20-variable graphs (Global) | AUPR: 0.34 -> 0.57 | Improved |
| add both non-linear mechanisms and adversarial loss (ablation) | SAM · Synthetic 20-variable graphs (Global) | AUPR: 0.30 -> 0.57 | Improved |
| add adversarial loss instead of MSE loss (ablation) | SAM · Synthetic 100-variable graphs (Global) | AUPR: 0.25 -> 0.59 | Improved |
| add non-linear mechanisms instead of linear ones (ablation) | SAM · Synthetic 100-variable graphs (Global) | AUPR: 0.39 -> 0.59 | Improved |
| add both non-linear mechanisms and adversarial loss (ablation) | SAM · Synthetic 100-variable graphs (Global) | AUPR: 0.17 -> 0.59 | Improved |
| add adversarial loss instead of MSE loss (ablation) | SAM · Synthetic 20-variable graphs (Global) | SHD: 43.9 -> 35.9 | Improved |
| add non-linear mechanisms and adversarial loss on linear data (ablation) | SAM · Synthetic 20-variable graphs (Linear) | AUPR: 0.30 -> 0.32 | No clear effect |
| add the acyclicity (DAG) constraint (ablation) | SAM · Synthetic 20-variable GP Mix graphs, 500 samples | AUPR | Improved |
| average over more runs, keep majority edges (ablation) | SAM · Synthetic 20-variable GP graphs, 500 samples | AUPR | Improved |
| increase graph density from 0.1 to 0.2 | SAM · Synthetic 20-variable GP graphs, 500 samples | AUPR | Improved |
| increase graph density above 0.2 | SAM · Synthetic 20-variable GP graphs, 500 samples | AUPR | Hurt |
Closest papers by meaning
- Learning to Induce Causal Structure (ICLR 2023 · similarity 0.88)
- A Fixed-Point Approach for Causal Generative Modeling (ICML 2024 · similarity 0.87)
- Scores for Learning Discrete Causal Graphs with Unobserved Confounders (AAAI 2024 · similarity 0.87)
- Standardizing Structural Causal Models (ICLR 2025 · similarity 0.86)
- Differentiable Structure Learning with Ancestral Constraints (ICML 2025 · similarity 0.86)
- Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery (ICML 2025 · similarity 0.86)
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.
