Research map / Probabilistic and scientific modeling / Causal discovery
Bayesian Active Causal Discovery with Multi-Fidelity Experiments
Zeyu Zhang, Chaozhuo Li, Xu Chen, Xing Xie
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 mutual information constraint to fidelity model (Licence vs w/o reg) (ablation) | Licence · ER 10 nodes, batch, budget 30 | AUPRC: 32.55 -> 37.94 | Improved |
| add mutual information constraint to fidelity model (ablation) | Licence · ER 10 nodes, batch, budget 30 | RMSE: 3.12 -> 2.66 | Improved |
| add mutual information constraint to fidelity model (ablation) | Licence · ER 10 nodes, batch, budget 30 | SHD: 17.10 -> 16.75 | Improved |
| use Licence multi-fidelity design instead of best baseline | Licence · ER 10 nodes | SHD: 27.74% | Improved |
| use Licence instead of best baseline | Licence · ER 10 nodes | AUPRC: 82.35% | Improved |
| use Licence instead of best baseline | Licence · ER 10 nodes | RMSE: 22.74% | Improved |
| use Licence instead of best baseline | Licence · SF 10 nodes | SHD: 17.69% | Improved |
| use Licence instead of best baseline | Licence · SF 10 nodes | AUPRC: 60.27% | Improved |
| use Licence instead of best baseline | Licence · SF 10 nodes | RMSE: 21.62% | Improved |
| randomly query fidelities instead of always using ground-truth oracle | AIT and CBED · ER 10 nodes | SHD, AUPRC, RMSE | Mixed |
| increase DAG regularization coefficient beta from 0.0 to 0.8 (ablation) | Licence · ER 10 nodes | AUPRC: peaks at beta = 0.8 | Improved |
| raise beta beyond 0.8 toward 1.0 (ablation) | Licence · ER 10 nodes | AUPRC | Hurt |
Closest papers by meaning
- Bayesian Active Learning for Bivariate Causal Discovery (ICML 2025 · similarity 0.88)
- ABC3: Active Bayesian Causal Inference with Cohn Criteria in Randomized Experiments (AAAI 2025 · similarity 0.88)
- Adaptive Online Experimental Design for Causal Discovery (ICML 2024 · similarity 0.88)
- Foundations of Testing for Finite-Sample Causal Discovery (ICML 2024 · similarity 0.87)
- On Causal Discovery in the Presence of Deterministic Relations (NeurIPS 2024 · similarity 0.87)
- A Meta-Learning Approach to Bayesian Causal Discovery (ICLR 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.
