Research map / Probabilistic and scientific modeling / Causal discovery
Bayesian Causal Structural Learning with Zero-Inflated Poisson Bayesian Networks
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 |
|---|---|---|---|
| model zero inflation explicitly (ZIPBN vs Poisson-based ODS) | Bayesian network structure learning · Simulated zero-inflated counts p=50 n=500 | MCC: 0.351 -> 0.826 | Helped |
| ZIPBN vs MRS (hyper-Poisson, test-based ordering) | Bayesian network structure learning · Simulated p=50 n=500 | MCC: 0.662 -> 0.826 | Helped |
| ZIPBN vs MRS at n=1000 p=25 | Bayesian network structure learning · Simulated n=1000 p=25 | MCC: 0.789 -> 0.825 | No clear effect |
| increase network size p from 25 to 75 | MRS · Simulated n=1000 | FDR: 0.268 -> 0.561 | Hurt |
| increase zeros from ~50% to ~75% | MRS · Simulated n=500 p=50 | FDR: 0.438 -> 0.805 | Hurt |
| increase zeros from ~50% to ~75% | ZIPBN · Simulated n=500 p=50 | MCC: 0.826 -> 0.684 | Hurt |
| increase sample size from 500 to 1000 | ZIPBN · Simulated p=50 | MCC: 0.826 -> 0.777 | Hurt |
| drop zero-inflation component (BayPBN) when data are pure Poisson (ablation) | ZIPBN · Poisson BN data | MCC: 0.736 -> 0.801 | Helped |
| ZIPBN vs MRS on misspecified ZI-NegBin data | Bayesian network structure learning · ZI-NegBin BN data | MCC: 0.455 -> 0.540 | Helped |
| ZIPBN vs MRS on real scRNA-seq TF-target orientation | Bayesian network structure learning · scRNA-seq 479 TF-target pairs | correct directions: 198 -> 304 | Helped |
Closest papers by meaning
- On the Identifiability of Poisson Branching Structural Causal Model Using Probability Generating Function (NeurIPS 2024 · similarity 0.89)
- Causal Discovery from Poisson Branching Structural Causal Model Using High-Order Cumulant with Path Analysis (AAAI 2024 · similarity 0.88)
- Bivariate Causal Discovery using Bayesian Model Selection (ICML 2024 · similarity 0.87)
- A Meta-Learning Approach to Bayesian Causal Discovery (ICLR 2025 · similarity 0.87)
- Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning (NeurIPS 2025 · similarity 0.87)
- Sample Efficient Bayesian Learning of Causal Graphs from Interventions (NeurIPS 2024 · 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.