Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Learning Bayesian Network Classifiers to Minimize Class Variable Parameters
Shouta Sugahara, Koya Kato, James Cussens, Maomi Ueno
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 |
|---|---|---|---|
| minimize class variable parameters (BNOC-BFS) instead of GBN-BDeu | Bayesian network classifier · 24 UCI datasets | accuracy: .8111 -> .8385 | Improved |
| minimize class variable parameters (BNOC-BFS) instead of ANB-BDeu | Bayesian network classifier · 24 UCI datasets | accuracy: .8201 -> .8385 | No clear effect |
| minimize NCP instead of all parameters (BNOC-BFS vs GBN-BDeu) | Bayesian network classifier · 24 UCI datasets | NCP: 10402.1 -> 1289.7 | Improved |
| minimize NCP instead of all parameters on small sample Hepatitis | Bayesian network classifier · Hepatitis | accuracy: .6125 -> .7875 | Improved |
| add branch-and-bound depth-first search (DFBnB) instead of breadth-first search (ablation) | BNOC · 24 UCI datasets | runtime (s): 1026.0 -> 49.4 | Improved |
| add branch-and-bound edge cutting (DFBnB vs BFS) (ablation) | BNOC · 24 UCI datasets | accuracy: .8385 -> .8354 | No clear effect |
| use integer programming with NCP penalty (BNOC-IP) instead of BFS | BNOC · 24 UCI datasets | accuracy: .8385 -> .7983 | Hurt |
| use integer programming (BNOC-IP) instead of DFBnB on large datasets | BNOC · 12 large UCI datasets | accuracy: .8880 -> .9075 | Improved |
| use BNOC-BFS instead of random forest on sparse data | Classifier · UCI small SPP datasets 1-12 | accuracy: .8779 -> .8498 | Hurt |
| use BNOC-BFS instead of random forest on dense data | Classifier · UCI large SPP datasets 13-24 | accuracy: .8134 -> .8271 | Improved |
| add chordalization and maximum CLL parameter estimation (PCMCE) to BNOC-BFS | BNOC-BFS · UCI large SPP datasets 13-24 | accuracy: .8271 -> .8389 | Improved |
| add chordalization and maximum CLL estimation (PCMCE) to BNOC-BFS | BNOC-BFS · UCI small SPP datasets 1-12 | accuracy: .8498 -> .8508 | No clear effect |
Closest papers by meaning
- Learning Bayesian Network Classifiers to Minimize the Class Variable Parameters (AAAI 2024 · similarity 0.94)
- Compiling Bayesian Network Classifiers into Decision Graphs (AAAI 2019 · similarity 0.87)
- Scalable Learning of Bayesian Network Classifiers (JMLR 2016 · similarity 0.86)
- Learning the Parameters of Bayesian Networks from Uncertain Data (AAAI 2021 · similarity 0.85)
- A Metalearned Neural Circuit for Nonparametric Bayesian Inference (NeurIPS 2024 · similarity 0.84)
- Random-Set Neural Networks (ICLR 2025 · similarity 0.83)
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.
