Research map / Graph learning / Graph algorithms and clustering
Local-to-Global Bayesian Network Structure Learning
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 |
|---|---|---|---|
| Replace local-to-global AND-rule/SLL+C with GGSL growing procedure (DP as BNStructLearn) | GGSL-DP vs SLL+C-DP · ALARM, CHILDREN, HAILFINDER, CHILDREN3, 7BN | BDeu score | Helped |
| Use GGSL instead of global learning with CSL | GGSL-CSL · CHILDREN | BDeu score: -12600.0 vs -12690.0 | Helped |
| Use GGSL instead of global learning with CSL | GGSL-CSL · ALARM, HAILFINDER | BDeu score: -11033.4 vs -10989.8 (ALARM); -57794.1 vs -54375.6 (HAILFINDER) | Hurt |
| Use GGSL with GOBNILP instead of SLL+C-GOB | GGSL-GOB · ALARM | BDeu score: -10575.0 vs -10337.1 | Hurt |
| Use GGSL with DP instead of global DP for speed | GGSL-DP vs DP · ALARM | running time (s): 126 vs OOM for DP | Helped |
| Use GGSL with CSL instead of global CSL for speed | GGSL-CSL vs CSL · ALARM | running time (s): 577 vs 22220 | Helped |
| Use GGSL instead of SLL+C with CSL (speed) | GGSL-CSL vs SLL+C-CSL · HAILFINDER | running time (s): 950 vs 1017 | Helped |
| Use GGSL instead of SLL+C with GOBNILP (speed) | GGSL-GOB vs SLL+C-GOB · ALARM, CHILDREN, CHILDREN3, HAILFINDER | running time (s): e.g. 499 vs 369 (ALARM); 71 vs 63 (CHILDREN) | Hurt |
| Skip AND-rule in favor of GGSL's query-based conflict resolution | local-to-global learning · benchmark BNs | BDeu score | Helped |
Closest papers by meaning
- Extendable and Iterative Structure Learning Strategy for Bayesian Networks (ICLR 2025 · similarity 0.90)
- Parallel Bayesian Network Structure Learning (ICML 2018 · similarity 0.90)
- Efficient Bayesian Network Structure Learning via Parameterized Local Search on Topological Orderings (AAAI 2021 · similarity 0.88)
- OpenGSL: A Comprehensive Benchmark for Graph Structure Learning (NeurIPS 2023 · similarity 0.88)
- Efficient Bayesian network structure learning via local Markov boundary search (NeurIPS 2021 · similarity 0.87)
- Distribution Learning Meets Graph Structure Sampling (NeurIPS 2025 · similarity 0.85)
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.