Research map / Probabilistic and scientific modeling / Causal discovery
Learning Dynamic Causal Graphs Under Parametric Uncertainty via Polynomial Chaos Expansions
Liang Cao
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 polynomial chaos representation of edge weights (ablation) | PCT-CD · Chemical reactor | F1: 0.623 -> 0.909 | Improved |
| add multi-criteria refinement (ablation) | PCT-CD · Chemical reactor | F1: 0.722 -> 0.909 | Improved |
| add bootstrap uncertainty calibration (ablation) | PCT-CD · Chemical reactor | F1: 0.747 -> 0.909 | Improved |
| raise PCE order from 2 to 4 (ablation) | PCT-CD · Chemical reactor | F1: 0.600 -> 0.909 | Improved |
| raise PCE order from 4 to 5 (ablation) | PCT-CD · Chemical reactor | F1: 0.909 -> 0.832 | Hurt |
| raise penalty lambda from 1 to 10 (ablation) | PCT-CD · Chemical reactor | F1: 0.909 -> 0.787 | Hurt |
| lower penalty lambda from 1 to 0.01 (ablation) | PCT-CD · Chemical reactor | F1: 0.909 -> 0.700 | Hurt |
| increase samples from 10,000 to 100,000 (ablation) | PCT-CD · Chemical reactor | F1: 0.909 -> 0.964 | Improved |
| increase number of variables from 9 to 100 (ablation) | PCT-CD · Chemical reactor scaling | F1: 0.909 -> 0.698 | Hurt |
| use PCT-CD instead of best static baselines (CAM, GraNDAG, SAM) | causal discovery · Chemical reactor | F1: 0.640 -> 0.909 | Improved |
Closest papers by meaning
- CausalDynamics: A large‐scale benchmark for structural discovery of dynamical causal models (NeurIPS 2025 · similarity 0.90)
- MOCHA: Discovering Multi-Order Dynamic Causal Structure in Temporal Point Processes (NeurIPS 2026 · similarity 0.88)
- Marrying Causal Representation Learning with Dynamical Systems for Science (NeurIPS 2024 · similarity 0.88)
- Causal Discovery with Fewer Conditional Independence Tests (ICML 2024 · similarity 0.88)
- Systems with Switching Causal Relations: A Meta-Causal Perspective (ICLR 2025 · similarity 0.88)
- Learning Structural Causal Models from Ordering: Identifiable Flow Models (AAAI 2025 · 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.
