Research map / Probabilistic and scientific modeling / Variational and generative sampling
Latent Dependency Forest Models
Shanbo Chu, Yong Jiang, Kewei Tu
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 |
|---|---|---|---|
| replace fixed dependency structure with assignment-dependent latent dependency forests | LDFM versus baseline models · nine Bayesian-network datasets; 5000 training instances; 40% query, 30% evidence | normalized maximum CLL/CMLL | Mixed |
| use Gibbs sampling instead of tree-augmented sampling | LDFM inference · nine Bayesian-network datasets | normalized maximum CLL/CMLL | Improved |
| use tree-augmented sampling instead of Gibbs sampling | LDFM inference · nine Bayesian-network datasets | sampling speed: more than twenty times faster | Improved |
| add assignment-dependent stop weights and jointly model tree structure (ablation) | LDFM, yielding LDFM-S · Win95pts and Water; 5000 training samples; 40% query, 30% evidence | normalized maximum CLL/CMLL: Win95pts: -0.166 -> -0.130; Water: -0.399 -> -0.462 | Mixed |
Closest papers by meaning
- DP-GP-LVM: A Bayesian Non-Parametric Model for Learning Multivariate Dependency Structures (ICML 2019 · similarity 0.86)
- Towards Escaping from Class Dependency Modeling for Multi-Dimensional Classification (ICML 2025 · similarity 0.82)
- Generative Forests (NeurIPS 2024 · similarity 0.81)
- Dependency Parsing is More Parameter-Efficient with Normalization (NeurIPS 2025 · similarity 0.81)
- Partition Tree: Conditional Density Estimation over General Outcome Spaces (NeurIPS 2026 · similarity 0.81)
- Automated Statistical Model Discovery with Language Models (ICML 2024 · similarity 0.81)
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.
