Research map / Probabilistic and scientific modeling / Causal discovery
Causal Preference Elicitation
Edwin V. Bonilla, He Zhao, Daniel M. Steinberg
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 |
|---|---|---|---|
| select expert queries by expected information gain (CaPE) instead of random or uncertainty sampling | CaPE · Synthetic ER DAG (D=20) | entropy, SHD, ETCP | Improved |
| add 40 EIG-selected expert queries to the observational posterior | CaPE · Sachs (observational only) | SHD: approximately 14 edges | Improved |
| add 40 EIG-selected expert queries to the observational posterior | CaPE · Sachs (observational only) | orientation F1: more than 0.38 | Improved |
| use CaPE instead of random, uncertainty and static-EIG baselines | CaPE · CausalBench K562 50 genes | directed AUPRC and Top-K precision: clearly outperforming all baselines by T >= 100 | Improved |
| replace adaptive EIG with static EIG computed once from the initial posterior (STE) (ablation) | CaPE · CausalBench K562 50 genes | AUPRC | Hurt |
| use uncertainty sampling instead of EIG for query selection (ablation) | CaPE · CausalBench K562 50 genes | AUPRC | Hurt |
| initialize particles from a trained DAG-GFlowNet prior instead of bootstrap regression | CaPE · Sachs (observational only) | SHD, ETCP, entropy | Improved |
| misspecify the expert oracle (heterogeneous reliability, directional bias, abstention, noisy) | CaPE · Synthetic ER DAG (D=20), misspecified experts | ETCP | No clear effect |
Closest papers by meaning
- A Meta-Learning Approach to Bayesian Causal Discovery (ICLR 2025 · similarity 0.88)
- Sample Efficient Bayesian Learning of Causal Graphs from Interventions (NeurIPS 2024 · similarity 0.86)
- Adaptive Online Experimental Design for Causal Discovery (ICML 2024 · similarity 0.86)
- CausalTab: Pretraining Across Causal Environments for Tabular Causal Discovery (NeurIPS 2026 · similarity 0.86)
- Bayesian Active Learning for Bivariate Causal Discovery (ICML 2025 · similarity 0.86)
- Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits (NeurIPS 2024 · 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.
